2026-05-06 15:08:18,213 [INFO] BAL Chatbot Web API başlatılıyor... 2026-05-06 15:08:18,214 [INFO] FAISS index yükleniyor... 2026-05-06 15:08:18,237 [INFO] Chunk metadata yükleniyor... 2026-05-06 15:08:18,249 [INFO] Embedding modeli yükleniyor: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 2026-05-06 15:08:18,254 [INFO] Use pytorch device_name: cuda:0 2026-05-06 15:08:18,254 [INFO] Load pretrained SentenceTransformer: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 2026-05-06 15:09:58,847 [INFO] ✅ Vektör veritabanı hazır: 91 chunk 2026-05-06 15:09:58,859 [INFO] 🌐 Sunucu başlatılıyor: http://localhost:5000 2026-05-06 15:09:58,859 [INFO] Arayüz: web/index.html dosyasını tarayıcıda açın 2026-05-06 15:09:59,058 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-05-06 15:09:59,059 [INFO] Press CTRL+C to quit 2026-05-06 15:11:54,138 [INFO] 127.0.0.1 - - [06/May/2026 15:11:54] "GET / HTTP/1.1" 404 - 2026-05-06 15:11:55,160 [INFO] 127.0.0.1 - - [06/May/2026 15:11:55] "GET /favicon.ico HTTP/1.1" 404 - 2026-05-06 15:16:29,543 [INFO] BAL Chatbot Web API başlatılıyor... 2026-05-06 15:16:29,543 [INFO] FAISS index yükleniyor... 2026-05-06 15:16:29,568 [INFO] Chunk metadata yükleniyor... 2026-05-06 15:16:29,580 [INFO] Embedding modeli yükleniyor: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 2026-05-06 15:16:29,585 [INFO] Use pytorch device_name: cuda:0 2026-05-06 15:16:29,585 [INFO] Load pretrained SentenceTransformer: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 2026-05-06 15:16:35,162 [INFO] ✅ Vektör veritabanı hazır: 91 chunk 2026-05-06 15:16:35,162 [INFO] 🌐 Sunucu başlatılıyor: http://localhost:5000 2026-05-06 15:16:35,162 [INFO] Arayüz: web/index.html dosyasını tarayıcıda açın 2026-05-06 15:16:35,165 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-05-06 15:16:35,165 [INFO] Press CTRL+C to quit 2026-05-06 15:16:59,283 [INFO] 127.0.0.1 - - [06/May/2026 15:16:59] "GET / HTTP/1.1" 200 - 2026-05-06 15:16:59,848 [INFO] 127.0.0.1 - - [06/May/2026 15:16:59] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:17:23,408 [INFO] 127.0.0.1 - - [06/May/2026 15:17:23] "OPTIONS /api/chat HTTP/1.1" 200 - 2026-05-06 15:17:24,024 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 231, in chat retrieved = retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 157, in retrieve scores, indices = faiss_index.search(embedding, top_k) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/faiss/class_wrappers.py", line 383, in replacement_search assert d == self.d ^^^^^^^^^^^ AssertionError 2026-05-06 15:17:24,437 [INFO] 127.0.0.1 - - [06/May/2026 15:17:24] "POST /api/chat HTTP/1.1" 500 - 2026-05-06 15:17:29,856 [INFO] 127.0.0.1 - - [06/May/2026 15:17:29] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:17:59,867 [INFO] 127.0.0.1 - - [06/May/2026 15:17:59] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:18:29,879 [INFO] 127.0.0.1 - - [06/May/2026 15:18:29] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:18:59,897 [INFO] 127.0.0.1 - - [06/May/2026 15:18:59] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:19:30,604 [INFO] 127.0.0.1 - - [06/May/2026 15:19:30] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:20:33,818 [INFO] BAL Chatbot Web API başlatılıyor... 2026-05-06 15:20:33,818 [INFO] FAISS index yükleniyor... 2026-05-06 15:20:33,818 [INFO] Chunk metadata yükleniyor... 2026-05-06 15:20:33,819 [INFO] Embedding modeli yükleniyor: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 2026-05-06 15:20:33,820 [INFO] Use pytorch device_name: cuda:0 2026-05-06 15:20:33,820 [INFO] Load pretrained SentenceTransformer: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 2026-05-06 15:20:37,523 [INFO] ✅ Vektör veritabanı hazır: 91 chunk 2026-05-06 15:20:37,523 [INFO] 🌐 Sunucu başlatılıyor: http://localhost:5000 2026-05-06 15:20:37,523 [INFO] Arayüz: web/index.html dosyasını tarayıcıda açın 2026-05-06 15:20:37,526 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-05-06 15:20:37,526 [INFO] Press CTRL+C to quit 2026-05-06 15:21:03,913 [INFO] 127.0.0.1 - - [06/May/2026 15:21:03] "GET / HTTP/1.1" 304 - 2026-05-06 15:21:04,032 [INFO] 127.0.0.1 - - [06/May/2026 15:21:04] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:21:10,778 [INFO] 127.0.0.1 - - [06/May/2026 15:21:10] "OPTIONS /api/chat HTTP/1.1" 200 - 2026-05-06 15:21:11,057 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 231, in chat retrieved = retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 157, in retrieve scores, indices = faiss_index.search(embedding, top_k) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/faiss/class_wrappers.py", line 383, in replacement_search assert d == self.d ^^^^^^^^^^^ AssertionError 2026-05-06 15:21:11,058 [INFO] 127.0.0.1 - - [06/May/2026 15:21:11] "POST /api/chat HTTP/1.1" 500 - 2026-05-06 15:21:34,200 [INFO] 127.0.0.1 - - [06/May/2026 15:21:34] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:22:04,201 [INFO] 127.0.0.1 - - [06/May/2026 15:22:04] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:22:34,195 [INFO] 127.0.0.1 - - [06/May/2026 15:22:34] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:23:04,204 [INFO] 127.0.0.1 - - [06/May/2026 15:23:04] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:23:34,202 [INFO] 127.0.0.1 - - [06/May/2026 15:23:34] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:24:04,202 [INFO] 127.0.0.1 - - [06/May/2026 15:24:04] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:24:39,079 [INFO] BAL Chatbot Web API başlatılıyor... 2026-05-06 15:24:39,079 [INFO] FAISS index yükleniyor... 2026-05-06 15:24:39,079 [INFO] Chunk metadata yükleniyor... 2026-05-06 15:24:39,080 [INFO] Embedding modeli yükleniyor: intfloat/multilingual-e5-large 2026-05-06 15:24:39,081 [INFO] Use pytorch device_name: cuda:0 2026-05-06 15:24:39,081 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-05-06 15:24:54,407 [INFO] ✅ Vektör veritabanı hazır: 91 chunk 2026-05-06 15:24:54,407 [INFO] 🌐 Sunucu başlatılıyor: http://localhost:5000 2026-05-06 15:24:54,407 [INFO] Arayüz: web/index.html dosyasını tarayıcıda açın 2026-05-06 15:24:54,410 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-05-06 15:24:54,410 [INFO] Press CTRL+C to quit 2026-05-06 15:25:04,294 [INFO] 127.0.0.1 - - [06/May/2026 15:25:04] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:25:11,110 [INFO] 127.0.0.1 - - [06/May/2026 15:25:11] "GET / HTTP/1.1" 304 - 2026-05-06 15:25:11,248 [INFO] 127.0.0.1 - - [06/May/2026 15:25:11] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:25:15,297 [INFO] 127.0.0.1 - - [06/May/2026 15:25:15] "OPTIONS /api/chat HTTP/1.1" 200 - 2026-05-06 15:25:30,292 [INFO] 127.0.0.1 - - [06/May/2026 15:25:30] "POST /api/chat HTTP/1.1" 200 - 2026-05-06 15:25:41,299 [INFO] 127.0.0.1 - - [06/May/2026 15:25:41] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:26:11,300 [INFO] 127.0.0.1 - - [06/May/2026 15:26:11] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:26:25,207 [INFO] 127.0.0.1 - - [06/May/2026 15:26:25] "OPTIONS /api/chat HTTP/1.1" 200 - 2026-05-06 15:26:26,087 [INFO] 127.0.0.1 - - [06/May/2026 15:26:26] "POST /api/chat HTTP/1.1" 200 - 2026-05-06 15:26:41,489 [INFO] 127.0.0.1 - - [06/May/2026 15:26:41] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:26:49,480 [INFO] 127.0.0.1 - - [06/May/2026 15:26:49] "OPTIONS /api/chat HTTP/1.1" 200 - 2026-05-06 15:26:51,340 [INFO] 127.0.0.1 - - [06/May/2026 15:26:51] "POST /api/chat HTTP/1.1" 200 - 2026-05-06 15:27:12,727 [INFO] 127.0.0.1 - - [06/May/2026 15:27:12] "GET /api/health HTTP/1.1" 200 - 2026-05-06 15:27:42,727 [INFO] 127.0.0.1 - - [06/May/2026 15:27:42] "GET /api/health HTTP/1.1" 200 - 2026-05-12 10:00:01,888 [INFO] BAL Chatbot Web API starting... 2026-05-12 10:00:01,943 [INFO] Backend: api 2026-05-12 10:00:01,943 [ERROR] FAISS index not found: ../data/bal_faiss.index Run '01_build_vectorstore.py' first. 2026-05-31 15:40:28,321 [INFO] BAL Chatbot Web API starting... 2026-05-31 15:40:28,321 [INFO] Runtime pid=892981 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-05-31 15:40:28,322 [INFO] Provider: groq 2026-05-31 15:40:28,322 [INFO] HTTPS enforcement: True 2026-05-31 15:40:28,322 [INFO] Loading FAISS index... 2026-05-31 15:40:28,344 [INFO] Loading chunk metadata... 2026-05-31 15:40:28,368 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-05-31 15:40:28,374 [INFO] Use pytorch device_name: cuda:0 2026-05-31 15:40:28,374 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-05-31 15:40:32,657 [INFO] Vector store ready — 108 chunks 2026-05-31 15:40:32,658 [INFO] Groq configured — model: llama-3.3-70b-versatile 2026-05-31 15:40:32,658 [INFO] LLM gateway ready — active provider: groq 2026-05-31 15:40:32,658 [INFO] Server starting on https://localhost:5000 2026-05-31 15:40:32,712 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-05-31 15:40:32,712 [INFO] Press CTRL+C to quit 2026-05-31 15:40:35,461 [INFO] 127.0.0.1 - - [31/May/2026 15:40:35] "GET / HTTP/1.1" 200 - 2026-05-31 15:40:35,989 [INFO] 127.0.0.1 - - [31/May/2026 15:40:35] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:40:36,177 [INFO] 127.0.0.1 - - [31/May/2026 15:40:36] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 15:41:05,715 [INFO] 127.0.0.1 - - [31/May/2026 15:41:05] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:41:07,446 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '167', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ksz0ts2tfhttbtybbpf0w5va'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 552, in stream_groq resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 15:41:07,460 [INFO] 127.0.0.1 - - [31/May/2026 15:41:07] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 15:41:35,731 [INFO] 127.0.0.1 - - [31/May/2026 15:41:35] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:42:05,718 [INFO] 127.0.0.1 - - [31/May/2026 15:42:05] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:42:35,732 [INFO] 127.0.0.1 - - [31/May/2026 15:42:35] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:43:05,721 [INFO] 127.0.0.1 - - [31/May/2026 15:43:05] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:43:35,738 [INFO] 127.0.0.1 - - [31/May/2026 15:43:35] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:44:05,720 [INFO] 127.0.0.1 - - [31/May/2026 15:44:05] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:44:35,735 [INFO] 127.0.0.1 - - [31/May/2026 15:44:35] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:45:05,721 [INFO] 127.0.0.1 - - [31/May/2026 15:45:05] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:45:35,731 [INFO] 127.0.0.1 - - [31/May/2026 15:45:35] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:45:55,029 [INFO] 127.0.0.1 - - [31/May/2026 15:45:55] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 15:45:59,000 [INFO] 127.0.0.1 - - [31/May/2026 15:45:59] "POST /api/chat HTTP/1.1" 429 - 2026-05-31 15:46:04,997 [INFO] 127.0.0.1 - - [31/May/2026 15:46:04] "GET / HTTP/1.1" 304 - 2026-05-31 15:46:05,258 [INFO] 127.0.0.1 - - [31/May/2026 15:46:05] "GET /api/health HTTP/1.1" 200 - 2026-05-31 15:46:05,673 [INFO] 127.0.0.1 - - [31/May/2026 15:46:05] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 16:05:41,893 [INFO] BAL Chatbot Web API starting... 2026-05-31 16:05:41,893 [INFO] Runtime pid=1104063 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-05-31 16:05:41,893 [INFO] Provider: groq 2026-05-31 16:05:41,893 [INFO] HTTPS enforcement: True 2026-05-31 16:05:41,893 [INFO] Loading FAISS index... 2026-05-31 16:05:41,894 [INFO] Loading chunk metadata... 2026-05-31 16:05:41,894 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-05-31 16:05:41,896 [INFO] Use pytorch device_name: cuda:0 2026-05-31 16:05:41,896 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-05-31 16:05:46,376 [INFO] Vector store ready — 108 chunks 2026-05-31 16:05:46,376 [INFO] Groq configured — primary model: llama-3.3-70b-versatile 2026-05-31 16:05:46,376 [INFO] LLM gateway ready — active provider: groq 2026-05-31 16:05:46,376 [INFO] Server starting on https://localhost:5000 2026-05-31 16:05:46,427 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-05-31 16:05:46,427 [INFO] Press CTRL+C to quit 2026-05-31 16:06:26,717 [INFO] 127.0.0.1 - - [31/May/2026 16:06:26] "GET / HTTP/1.1" 200 - 2026-05-31 16:06:27,240 [INFO] 127.0.0.1 - - [31/May/2026 16:06:27] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:06:27,455 [INFO] 127.0.0.1 - - [31/May/2026 16:06:27] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 16:06:35,170 [INFO] 127.0.0.1 - - [31/May/2026 16:06:35] "POST /api/auth/logout HTTP/1.1" 200 - 2026-05-31 16:06:35,197 [INFO] 127.0.0.1 - - [31/May/2026 16:06:35] "GET / HTTP/1.1" 304 - 2026-05-31 16:06:35,216 [INFO] 127.0.0.1 - - [31/May/2026 16:06:35] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 16:06:35,410 [INFO] 127.0.0.1 - - [31/May/2026 16:06:35] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:06:49,497 [INFO] 127.0.0.1 - - [31/May/2026 16:06:49] "POST /api/auth/login HTTP/1.1" 200 - 2026-05-31 16:07:00,175 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1563', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ksz2a5dneeet6h88h1cmr155'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 564, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:07:00,340 [WARNING] Groq fallback switching from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-05-31 16:07:00,340 [INFO] 127.0.0.1 - - [31/May/2026 16:07:00] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 16:07:00,471 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ksz2a5pve7ar0gb46ngfvx49'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 564, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:07:05,483 [INFO] 127.0.0.1 - - [31/May/2026 16:07:05] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:07:36,083 [INFO] 127.0.0.1 - - [31/May/2026 16:07:36] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:10:16,837 [INFO] BAL Chatbot Web API starting... 2026-05-31 16:10:16,838 [INFO] Runtime pid=1141512 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-05-31 16:10:16,838 [INFO] Provider: groq 2026-05-31 16:10:16,838 [INFO] HTTPS enforcement: True 2026-05-31 16:10:16,838 [INFO] Loading FAISS index... 2026-05-31 16:10:16,904 [INFO] Loading chunk metadata... 2026-05-31 16:10:16,925 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-05-31 16:10:16,928 [INFO] Use pytorch device_name: cuda:0 2026-05-31 16:10:16,928 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-05-31 16:10:21,164 [INFO] Vector store ready — 108 chunks 2026-05-31 16:10:21,164 [INFO] Groq configured — primary model: llama-3.3-70b-versatile 2026-05-31 16:10:21,164 [INFO] LLM gateway ready — active provider: groq 2026-05-31 16:10:21,164 [INFO] Server starting on https://localhost:5000 2026-05-31 16:10:21,225 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-05-31 16:10:21,225 [INFO] Press CTRL+C to quit 2026-05-31 16:10:24,085 [INFO] 127.0.0.1 - - [31/May/2026 16:10:24] "GET / HTTP/1.1" 304 - 2026-05-31 16:10:24,356 [INFO] 127.0.0.1 - - [31/May/2026 16:10:24] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:10:25,052 [INFO] 127.0.0.1 - - [31/May/2026 16:10:25] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 16:10:33,115 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '981', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ksz2gnbyeg5rp2th4pepcb9t'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 564, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:10:33,116 [WARNING] Groq fallback switching from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-05-31 16:10:33,116 [INFO] 127.0.0.1 - - [31/May/2026 16:10:33] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 16:10:33,244 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ksz2gng3fhzv0h8rapaqjzny'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 564, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:10:33,245 [WARNING] Groq fallback switching from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-05-31 16:10:34,205 [WARNING] Groq fallback succeeded original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-05-31 16:10:54,090 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1867', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ksz2h9vje43rpq86zmfkqxvz'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 564, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:10:54,091 [WARNING] Groq fallback switching from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-05-31 16:10:54,091 [INFO] 127.0.0.1 - - [31/May/2026 16:10:54] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 16:10:54,321 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ksz2ha0ve45997vnndze85qa'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 564, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:10:54,322 [WARNING] Groq fallback switching from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-05-31 16:10:54,387 [INFO] 127.0.0.1 - - [31/May/2026 16:10:54] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:10:55,224 [WARNING] Groq fallback succeeded original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-05-31 16:11:24,481 [INFO] 127.0.0.1 - - [31/May/2026 16:11:24] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:15:20,562 [INFO] BAL Chatbot Web API starting... 2026-05-31 16:15:20,562 [INFO] Runtime pid=1185382 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-05-31 16:15:20,562 [INFO] Provider: groq 2026-05-31 16:15:20,562 [INFO] HTTPS enforcement: True 2026-05-31 16:15:20,562 [INFO] Loading FAISS index... 2026-05-31 16:15:20,562 [INFO] Loading chunk metadata... 2026-05-31 16:15:20,564 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-05-31 16:15:20,566 [INFO] Use pytorch device_name: cuda:0 2026-05-31 16:15:20,566 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-05-31 16:15:24,800 [INFO] Vector store ready — 108 chunks 2026-05-31 16:15:24,800 [INFO] Groq configured — primary model: llama-3.3-70b-versatile 2026-05-31 16:15:24,800 [INFO] LLM gateway ready — active provider: groq 2026-05-31 16:15:24,800 [INFO] Server starting on https://localhost:5000 2026-05-31 16:15:24,853 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-05-31 16:15:24,853 [INFO] Press CTRL+C to quit 2026-05-31 16:15:28,609 [INFO] 127.0.0.1 - - [31/May/2026 16:15:28] "GET / HTTP/1.1" 200 - 2026-05-31 16:15:28,831 [INFO] 127.0.0.1 - - [31/May/2026 16:15:28] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:15:29,581 [INFO] 127.0.0.1 - - [31/May/2026 16:15:29] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 16:15:38,498 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1043', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ksz2szk1e1qa6np0wmyncs5n'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 577, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:15:38,501 [WARNING] Groq fallback switching from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-05-31 16:15:38,501 [INFO] 127.0.0.1 - - [31/May/2026 16:15:38] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 16:15:38,637 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ksz2szqhf2xa33rm3cqq56wq'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 577, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:15:38,638 [WARNING] Groq fallback switching from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-05-31 16:15:39,528 [WARNING] Groq fallback succeeded original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-05-31 16:15:58,837 [INFO] 127.0.0.1 - - [31/May/2026 16:15:58] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:16:03,478 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '650', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ksz2tqztfv3b2s7kzwpmbxd0'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 577, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:16:03,480 [WARNING] Groq fallback switching from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-05-31 16:16:03,480 [INFO] 127.0.0.1 - - [31/May/2026 16:16:03] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 16:16:03,617 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ksz2tr45fv39fmz3msnek082'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 577, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-05-31 16:16:03,618 [WARNING] Groq fallback switching from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-05-31 16:16:06,100 [WARNING] Groq fallback succeeded original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-05-31 16:16:28,870 [INFO] 127.0.0.1 - - [31/May/2026 16:16:28] "GET /api/health HTTP/1.1" 200 - 2026-05-31 16:16:58,840 [INFO] 127.0.0.1 - - [31/May/2026 16:16:58] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:09:53,629 [INFO] BAL Chatbot Web API starting... 2026-05-31 20:09:53,658 [INFO] Runtime pid=167601 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-05-31 20:09:53,658 [INFO] Provider: groq 2026-05-31 20:09:53,658 [INFO] HTTPS enforcement: True 2026-05-31 20:09:53,658 [INFO] Loading FAISS index... 2026-05-31 20:09:53,675 [INFO] Loading chunk metadata... 2026-05-31 20:09:53,696 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-05-31 20:09:53,699 [INFO] Use pytorch device_name: cuda:0 2026-05-31 20:09:53,699 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-05-31 20:10:19,266 [INFO] Vector store ready — 108 chunks 2026-05-31 20:10:19,267 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-05-31 20:10:19,267 [INFO] LLM gateway ready — active provider: groq 2026-05-31 20:10:19,267 [INFO] Server starting on https://localhost:5000 2026-05-31 20:10:19,394 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-05-31 20:10:19,394 [INFO] Press CTRL+C to quit 2026-05-31 20:10:28,256 [INFO] 127.0.0.1 - - [31/May/2026 20:10:28] "GET / HTTP/1.1" 200 - 2026-05-31 20:10:28,328 [INFO] 127.0.0.1 - - [31/May/2026 20:10:28] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 20:10:28,533 [INFO] 127.0.0.1 - - [31/May/2026 20:10:28] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:10:49,955 [INFO] 127.0.0.1 - - [31/May/2026 20:10:49] "POST /api/auth/login HTTP/1.1" 200 - 2026-05-31 20:10:58,528 [INFO] 127.0.0.1 - - [31/May/2026 20:10:58] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:11:06,503 [INFO] 127.0.0.1 - - [31/May/2026 20:11:06] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 20:11:28,573 [INFO] 127.0.0.1 - - [31/May/2026 20:11:28] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:11:37,720 [INFO] 127.0.0.1 - - [31/May/2026 20:11:37] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 20:11:58,585 [INFO] 127.0.0.1 - - [31/May/2026 20:11:58] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:18:47,679 [INFO] BAL Chatbot Web API starting... 2026-05-31 20:18:47,679 [INFO] Runtime pid=259673 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-05-31 20:18:47,679 [INFO] Provider: groq 2026-05-31 20:18:47,680 [INFO] HTTPS enforcement: True 2026-05-31 20:18:47,680 [INFO] Loading FAISS index... 2026-05-31 20:18:47,746 [INFO] Loading chunk metadata... 2026-05-31 20:18:47,768 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-05-31 20:18:47,773 [INFO] Use pytorch device_name: cuda:0 2026-05-31 20:18:47,773 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-05-31 20:18:52,680 [INFO] Vector store ready — 108 chunks 2026-05-31 20:18:52,680 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-05-31 20:18:52,680 [INFO] LLM gateway ready — active provider: groq 2026-05-31 20:18:52,680 [INFO] Server starting on https://localhost:5000 2026-05-31 20:18:52,761 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-05-31 20:18:52,761 [INFO] Press CTRL+C to quit 2026-05-31 20:19:06,145 [INFO] 127.0.0.1 - - [31/May/2026 20:19:06] "GET / HTTP/1.1" 200 - 2026-05-31 20:19:06,379 [INFO] 127.0.0.1 - - [31/May/2026 20:19:06] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:19:07,151 [INFO] 127.0.0.1 - - [31/May/2026 20:19:07] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 20:19:17,780 [INFO] 127.0.0.1 - - [31/May/2026 20:19:17] "POST /api/chat HTTP/1.1" 200 - 2026-05-31 20:19:29,426 [INFO] 127.0.0.1 - - [31/May/2026 20:19:29] "POST /api/auth/logout HTTP/1.1" 200 - 2026-05-31 20:19:29,456 [INFO] 127.0.0.1 - - [31/May/2026 20:19:29] "GET / HTTP/1.1" 304 - 2026-05-31 20:19:29,485 [INFO] 127.0.0.1 - - [31/May/2026 20:19:29] "GET /api/auth/status HTTP/1.1" 200 - 2026-05-31 20:19:29,679 [INFO] 127.0.0.1 - - [31/May/2026 20:19:29] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:19:59,860 [INFO] 127.0.0.1 - - [31/May/2026 20:19:59] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:20:30,002 [INFO] 127.0.0.1 - - [31/May/2026 20:20:30] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:21:00,207 [INFO] 127.0.0.1 - - [31/May/2026 20:21:00] "GET /api/health HTTP/1.1" 200 - 2026-05-31 20:37:00,036 [INFO] BAL Chatbot Web API starting... 2026-05-31 20:37:00,036 [INFO] Runtime pid=442435 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-05-31 20:37:00,037 [INFO] Provider: groq 2026-05-31 20:37:00,037 [INFO] HTTPS enforcement: True 2026-05-31 20:37:00,037 [INFO] Loading FAISS index... 2026-05-31 20:37:00,038 [INFO] Loading chunk metadata... 2026-05-31 20:37:00,040 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-05-31 20:37:00,045 [INFO] Use pytorch device_name: cuda:0 2026-05-31 20:37:00,045 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-05-31 20:37:05,156 [INFO] Vector store ready — 108 chunks 2026-05-31 20:37:05,156 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-05-31 20:37:05,157 [INFO] LLM gateway ready — active provider: groq 2026-05-31 20:37:05,157 [INFO] Server starting on https://0.0.0.0:5000 2026-05-31 20:37:05,233 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-05-31 20:37:05,233 [INFO] Press CTRL+C to quit 2026-06-01 18:13:13,306 [INFO] BAL Chatbot Web API starting... 2026-06-01 18:13:13,307 [INFO] Runtime pid=248788 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-01 18:13:13,307 [INFO] Provider: groq 2026-06-01 18:13:13,307 [INFO] HTTPS enforcement: True 2026-06-01 18:13:13,308 [INFO] Loading FAISS index... 2026-06-01 18:13:13,324 [INFO] Loading chunk metadata... 2026-06-01 18:13:13,327 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-06-01 18:13:13,332 [INFO] Use pytorch device_name: cuda:0 2026-06-01 18:13:13,332 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-06-01 18:13:42,284 [INFO] Vector store ready — 108 chunks 2026-06-01 18:13:42,284 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-01 18:13:42,284 [INFO] LLM gateway ready — active provider: groq 2026-06-01 18:13:42,284 [INFO] Server starting on https://0.0.0.0:5000 2026-06-01 18:13:42,981 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-01 18:13:42,982 [INFO] Press CTRL+C to quit 2026-06-01 18:14:07,259 [INFO] 127.0.0.1 - - [01/Jun/2026 18:14:07] "GET / HTTP/1.1" 404 - 2026-06-01 18:15:31,118 [INFO] BAL Chatbot Web API starting... 2026-06-01 18:15:31,119 [INFO] Runtime pid=250746 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-01 18:15:31,119 [INFO] Provider: groq 2026-06-01 18:15:31,119 [INFO] HTTPS enforcement: True 2026-06-01 18:15:31,120 [INFO] Loading FAISS index... 2026-06-01 18:15:31,235 [INFO] Loading chunk metadata... 2026-06-01 18:15:31,248 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-06-01 18:15:31,254 [INFO] Use pytorch device_name: cuda:0 2026-06-01 18:15:31,254 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-06-01 18:15:38,267 [INFO] Vector store ready — 108 chunks 2026-06-01 18:15:38,267 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-01 18:15:38,267 [INFO] LLM gateway ready — active provider: groq 2026-06-01 18:15:38,267 [INFO] Server starting on https://0.0.0.0:5000 2026-06-01 18:15:38,393 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-01 18:15:38,393 [INFO] Press CTRL+C to quit 2026-06-01 18:15:57,794 [INFO] 127.0.0.1 - - [01/Jun/2026 18:15:57] "GET / HTTP/1.1" 200 - 2026-06-01 18:15:58,665 [INFO] 127.0.0.1 - - [01/Jun/2026 18:15:58] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-01 18:15:58,856 [INFO] 127.0.0.1 - - [01/Jun/2026 18:15:58] "GET /api/health HTTP/1.1" 200 - 2026-06-01 18:16:02,227 [INFO] 127.0.0.1 - - [01/Jun/2026 18:16:02] "POST /api/auth/guest HTTP/1.1" 200 - 2026-06-01 18:16:15,632 [INFO] 127.0.0.1 - - [01/Jun/2026 18:16:15] "POST /api/chat HTTP/1.1" 200 - 2026-06-01 18:16:19,731 [INFO] 127.0.0.1 - - [01/Jun/2026 18:16:19] "POST /api/auth/logout HTTP/1.1" 200 - 2026-06-01 18:16:19,772 [INFO] 127.0.0.1 - - [01/Jun/2026 18:16:19] "GET / HTTP/1.1" 304 - 2026-06-01 18:16:19,897 [INFO] 127.0.0.1 - - [01/Jun/2026 18:16:19] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-01 18:16:20,120 [INFO] 127.0.0.1 - - [01/Jun/2026 18:16:20] "GET /api/health HTTP/1.1" 200 - 2026-06-02 17:42:13,453 [INFO] BAL Chatbot Web API starting... 2026-06-02 17:42:13,453 [INFO] Runtime pid=9574 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-02 17:42:13,454 [INFO] Provider: groq 2026-06-02 17:42:13,454 [INFO] HTTPS enforcement: True 2026-06-02 17:42:13,454 [INFO] Loading FAISS index... 2026-06-02 17:42:13,477 [INFO] Loading chunk metadata... 2026-06-02 17:42:13,478 [INFO] Loading embedding model: intfloat/multilingual-e5-large 2026-06-02 17:42:13,486 [INFO] Use pytorch device_name: cuda:0 2026-06-02 17:42:13,486 [INFO] Load pretrained SentenceTransformer: intfloat/multilingual-e5-large 2026-06-02 17:42:38,872 [INFO] Vector store ready — 108 chunks 2026-06-02 17:42:38,872 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-02 17:42:38,872 [INFO] LLM gateway ready — active provider: groq 2026-06-02 17:42:38,872 [INFO] Server starting on https://0.0.0.0:5000 2026-06-02 17:42:39,023 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-02 17:42:39,023 [INFO] Press CTRL+C to quit 2026-06-02 17:44:07,893 [INFO] 127.0.0.1 - - [02/Jun/2026 17:44:07] "GET / HTTP/1.1" 200 - 2026-06-02 17:44:08,072 [INFO] 127.0.0.1 - - [02/Jun/2026 17:44:08] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-02 17:44:08,293 [INFO] 127.0.0.1 - - [02/Jun/2026 17:44:08] "GET /api/health HTTP/1.1" 200 - 2026-06-02 17:44:22,578 [INFO] 127.0.0.1 - - [02/Jun/2026 17:44:22] "POST /api/auth/guest HTTP/1.1" 200 - 2026-06-02 17:44:38,850 [INFO] 127.0.0.1 - - [02/Jun/2026 17:44:38] "GET /api/health HTTP/1.1" 200 - 2026-06-02 17:44:40,957 [INFO] 127.0.0.1 - - [02/Jun/2026 17:44:40] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 17:45:08,653 [INFO] 127.0.0.1 - - [02/Jun/2026 17:45:08] "GET /api/health HTTP/1.1" 200 - 2026-06-02 17:45:11,015 [INFO] 127.0.0.1 - - [02/Jun/2026 17:45:11] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 17:45:29,695 [INFO] 127.0.0.1 - - [02/Jun/2026 17:45:29] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 17:45:38,680 [INFO] 127.0.0.1 - - [02/Jun/2026 17:45:38] "GET /api/health HTTP/1.1" 200 - 2026-06-02 17:45:57,940 [INFO] 127.0.0.1 - - [02/Jun/2026 17:45:57] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 17:46:08,939 [INFO] 127.0.0.1 - - [02/Jun/2026 17:46:08] "GET /api/health HTTP/1.1" 200 - 2026-06-02 17:46:38,690 [INFO] 127.0.0.1 - - [02/Jun/2026 17:46:38] "GET /api/health HTTP/1.1" 200 - 2026-06-02 17:47:09,139 [INFO] 127.0.0.1 - - [02/Jun/2026 17:47:09] "GET /api/health HTTP/1.1" 200 - 2026-06-02 17:47:39,138 [INFO] 127.0.0.1 - - [02/Jun/2026 17:47:39] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:36:14,735 [INFO] BAL Chatbot Web API starting... 2026-06-02 18:36:14,753 [INFO] Runtime pid=55558 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-02 18:36:14,754 [INFO] Provider: groq 2026-06-02 18:36:14,754 [INFO] HTTPS enforcement: True 2026-06-02 18:36:14,754 [INFO] Loading FAISS index... 2026-06-02 18:36:14,771 [INFO] Loading chunk metadata... 2026-06-02 18:36:14,774 [INFO] Vector store ready — 108 chunks 2026-06-02 18:36:14,775 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-02 18:36:14,775 [ERROR] No Gemini API key configured. 2026-06-02 18:37:11,008 [INFO] BAL Chatbot Web API starting... 2026-06-02 18:37:11,009 [INFO] Runtime pid=56409 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-02 18:37:11,009 [INFO] Provider: groq 2026-06-02 18:37:11,009 [INFO] HTTPS enforcement: True 2026-06-02 18:37:11,009 [INFO] Loading FAISS index... 2026-06-02 18:37:11,010 [INFO] Loading chunk metadata... 2026-06-02 18:37:11,013 [INFO] Vector store ready — 108 chunks 2026-06-02 18:37:11,013 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-02 18:37:11,013 [INFO] LLM gateway ready — active provider: groq 2026-06-02 18:37:11,014 [INFO] Server starting on https://0.0.0.0:5000 2026-06-02 18:37:11,063 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-02 18:37:11,063 [INFO] Press CTRL+C to quit 2026-06-02 18:37:31,998 [INFO] 127.0.0.1 - - [02/Jun/2026 18:37:31] "GET / HTTP/1.1" 304 - 2026-06-02 18:37:32,781 [INFO] 127.0.0.1 - - [02/Jun/2026 18:37:32] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:37:32,944 [INFO] 127.0.0.1 - - [02/Jun/2026 18:37:32] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-02 18:37:36,405 [WARNING] Gemini embedding failed key=1 error=404 models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods. 2026-06-02 18:37:36,406 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 1082, in chat retrieved = vector_store.retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 542, in retrieve raise RuntimeError( RuntimeError: All Gemini embedding keys failed: 404 models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods. 2026-06-02 18:37:36,424 [INFO] 127.0.0.1 - - [02/Jun/2026 18:37:36] "POST /api/chat HTTP/1.1" 500 - 2026-06-02 18:38:02,674 [INFO] 127.0.0.1 - - [02/Jun/2026 18:38:02] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:38:15,181 [WARNING] Gemini embedding failed key=1 error=404 models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods. 2026-06-02 18:38:15,182 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 1082, in chat retrieved = vector_store.retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 542, in retrieve raise RuntimeError( RuntimeError: All Gemini embedding keys failed: 404 models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods. 2026-06-02 18:38:15,185 [INFO] 127.0.0.1 - - [02/Jun/2026 18:38:15] "POST /api/chat HTTP/1.1" 500 - 2026-06-02 18:38:32,789 [INFO] 127.0.0.1 - - [02/Jun/2026 18:38:32] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:39:02,787 [INFO] 127.0.0.1 - - [02/Jun/2026 18:39:02] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:39:32,789 [INFO] 127.0.0.1 - - [02/Jun/2026 18:39:32] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:41:04,983 [INFO] BAL Chatbot Web API starting... 2026-06-02 18:41:04,984 [INFO] Runtime pid=59641 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-02 18:41:04,984 [INFO] Provider: groq 2026-06-02 18:41:04,984 [INFO] HTTPS enforcement: True 2026-06-02 18:41:04,984 [INFO] Loading FAISS index... 2026-06-02 18:41:04,985 [INFO] Loading chunk metadata... 2026-06-02 18:41:04,988 [INFO] Vector store ready — 108 chunks 2026-06-02 18:41:04,988 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-02 18:41:04,988 [INFO] LLM gateway ready — active provider: groq 2026-06-02 18:41:04,988 [INFO] Server starting on https://0.0.0.0:5000 2026-06-02 18:41:05,032 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-02 18:41:05,032 [INFO] Press CTRL+C to quit 2026-06-02 18:41:15,387 [INFO] 127.0.0.1 - - [02/Jun/2026 18:41:15] "GET / HTTP/1.1" 304 - 2026-06-02 18:41:15,634 [INFO] 127.0.0.1 - - [02/Jun/2026 18:41:15] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:41:16,693 [INFO] 127.0.0.1 - - [02/Jun/2026 18:41:16] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-02 18:41:20,102 [WARNING] Gemini embedding failed key=1 error=404 models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods. 2026-06-02 18:41:20,103 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 1082, in chat retrieved = vector_store.retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 542, in retrieve raise RuntimeError( RuntimeError: All Gemini embedding keys failed: 404 models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods. 2026-06-02 18:41:20,107 [INFO] 127.0.0.1 - - [02/Jun/2026 18:41:20] "POST /api/chat HTTP/1.1" 500 - 2026-06-02 18:41:39,021 [WARNING] Gemini embedding failed key=1 error=404 models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods. 2026-06-02 18:41:39,021 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 1082, in chat retrieved = vector_store.retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 542, in retrieve raise RuntimeError( RuntimeError: All Gemini embedding keys failed: 404 models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods. 2026-06-02 18:41:39,024 [INFO] 127.0.0.1 - - [02/Jun/2026 18:41:39] "POST /api/chat HTTP/1.1" 500 - 2026-06-02 18:41:45,694 [INFO] 127.0.0.1 - - [02/Jun/2026 18:41:45] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:42:15,910 [INFO] 127.0.0.1 - - [02/Jun/2026 18:42:15] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:44:12,173 [INFO] BAL Chatbot Web API starting... 2026-06-02 18:44:12,173 [INFO] Runtime pid=62239 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-02 18:44:12,174 [INFO] Provider: groq 2026-06-02 18:44:12,174 [INFO] HTTPS enforcement: True 2026-06-02 18:44:12,174 [INFO] Loading FAISS index... 2026-06-02 18:44:12,175 [INFO] Loading chunk metadata... 2026-06-02 18:44:12,177 [INFO] Vector store ready — 108 chunks 2026-06-02 18:44:12,178 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-02 18:44:12,178 [INFO] LLM gateway ready — active provider: groq 2026-06-02 18:44:12,178 [INFO] Server starting on https://0.0.0.0:5000 2026-06-02 18:44:12,200 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-02 18:44:12,200 [INFO] Press CTRL+C to quit 2026-06-02 18:44:19,479 [INFO] 127.0.0.1 - - [02/Jun/2026 18:44:19] "GET / HTTP/1.1" 304 - 2026-06-02 18:44:19,743 [INFO] 127.0.0.1 - - [02/Jun/2026 18:44:19] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:44:20,484 [INFO] 127.0.0.1 - - [02/Jun/2026 18:44:20] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-02 18:44:28,176 [WARNING] Gemini embedding failed key=1 error=module 'google.genai' has no attribute 'configure' 2026-06-02 18:44:28,176 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 1086, in chat retrieved = vector_store.retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 546, in retrieve raise RuntimeError( RuntimeError: All Gemini embedding keys failed: module 'google.genai' has no attribute 'configure' 2026-06-02 18:44:28,182 [INFO] 127.0.0.1 - - [02/Jun/2026 18:44:28] "POST /api/chat HTTP/1.1" 500 - 2026-06-02 18:44:48,211 [WARNING] Gemini embedding failed key=1 error=module 'google.genai' has no attribute 'configure' 2026-06-02 18:44:48,212 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 1086, in chat retrieved = vector_store.retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 546, in retrieve raise RuntimeError( RuntimeError: All Gemini embedding keys failed: module 'google.genai' has no attribute 'configure' 2026-06-02 18:44:48,215 [INFO] 127.0.0.1 - - [02/Jun/2026 18:44:48] "POST /api/chat HTTP/1.1" 500 - 2026-06-02 18:44:49,805 [INFO] 127.0.0.1 - - [02/Jun/2026 18:44:49] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:45:20,151 [INFO] 127.0.0.1 - - [02/Jun/2026 18:45:20] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:46:56,939 [INFO] BAL Chatbot Web API starting... 2026-06-02 18:46:56,940 [INFO] Runtime pid=64510 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-02 18:46:56,940 [INFO] Provider: groq 2026-06-02 18:46:56,940 [INFO] HTTPS enforcement: True 2026-06-02 18:46:56,940 [INFO] Loading FAISS index... 2026-06-02 18:46:56,941 [INFO] Loading chunk metadata... 2026-06-02 18:46:56,944 [INFO] Vector store ready — 108 chunks 2026-06-02 18:46:56,944 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-02 18:46:56,945 [INFO] LLM gateway ready — active provider: groq 2026-06-02 18:46:56,945 [INFO] Server starting on https://0.0.0.0:5000 2026-06-02 18:46:56,982 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-02 18:46:56,982 [INFO] Press CTRL+C to quit 2026-06-02 18:47:44,482 [INFO] 127.0.0.1 - - [02/Jun/2026 18:47:44] "GET / HTTP/1.1" 304 - 2026-06-02 18:47:44,752 [INFO] 127.0.0.1 - - [02/Jun/2026 18:47:44] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:47:45,486 [INFO] 127.0.0.1 - - [02/Jun/2026 18:47:45] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-02 18:47:49,216 [INFO] 127.0.0.1 - - [02/Jun/2026 18:47:49] "POST /api/chat HTTP/1.1" 429 - 2026-06-02 18:47:53,891 [INFO] 127.0.0.1 - - [02/Jun/2026 18:47:53] "POST /api/auth/logout HTTP/1.1" 200 - 2026-06-02 18:47:53,932 [INFO] 127.0.0.1 - - [02/Jun/2026 18:47:53] "GET / HTTP/1.1" 304 - 2026-06-02 18:47:53,965 [INFO] 127.0.0.1 - - [02/Jun/2026 18:47:53] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-02 18:47:54,175 [INFO] 127.0.0.1 - - [02/Jun/2026 18:47:54] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:48:07,075 [INFO] 127.0.0.1 - - [02/Jun/2026 18:48:07] "POST /api/auth/login HTTP/1.1" 200 - 2026-06-02 18:48:11,329 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/text-embedding-004:batchEmbedContents "HTTP/1.1 404 Not Found" 2026-06-02 18:48:11,331 [WARNING] Gemini embedding failed key=1 error=404 NOT_FOUND. {'error': {'code': 404, 'message': 'models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods.', 'status': 'NOT_FOUND'}} 2026-06-02 18:48:11,332 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 1083, in chat retrieved = vector_store.retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 543, in retrieve raise RuntimeError( RuntimeError: All Gemini embedding keys failed: 404 NOT_FOUND. {'error': {'code': 404, 'message': 'models/text-embedding-004 is not found for API version v1beta, or is not supported for embedContent. Call ModelService.ListModels to see the list of available models and their supported methods.', 'status': 'NOT_FOUND'}} 2026-06-02 18:48:11,334 [INFO] 127.0.0.1 - - [02/Jun/2026 18:48:11] "POST /api/chat HTTP/1.1" 500 - 2026-06-02 18:48:24,206 [INFO] 127.0.0.1 - - [02/Jun/2026 18:48:24] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:57:09,722 [INFO] BAL Chatbot Web API starting... 2026-06-02 18:57:09,729 [INFO] Runtime pid=72985 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-02 18:57:09,729 [INFO] Provider: groq 2026-06-02 18:57:09,729 [INFO] HTTPS enforcement: True 2026-06-02 18:57:09,730 [INFO] Loading FAISS index... 2026-06-02 18:57:09,732 [INFO] Loading chunk metadata... 2026-06-02 18:57:09,735 [INFO] Vector store ready — 108 chunks 2026-06-02 18:57:09,735 [INFO] Groq configured — key_count=1 primary_model=llama-3.3-70b-versatile 2026-06-02 18:57:09,735 [INFO] LLM gateway ready — active provider: groq 2026-06-02 18:57:09,735 [INFO] Server starting on https://0.0.0.0:5000 2026-06-02 18:57:09,763 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-02 18:57:09,763 [INFO] Press CTRL+C to quit 2026-06-02 18:57:17,395 [INFO] 127.0.0.1 - - [02/Jun/2026 18:57:17] "GET / HTTP/1.1" 304 - 2026-06-02 18:57:17,652 [INFO] 127.0.0.1 - - [02/Jun/2026 18:57:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:57:18,425 [INFO] 127.0.0.1 - - [02/Jun/2026 18:57:18] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-02 18:57:23,352 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 18:57:23,851 [INFO] 127.0.0.1 - - [02/Jun/2026 18:57:23] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 18:57:47,708 [INFO] 127.0.0.1 - - [02/Jun/2026 18:57:47] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:58:17,718 [INFO] 127.0.0.1 - - [02/Jun/2026 18:58:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:58:47,712 [INFO] 127.0.0.1 - - [02/Jun/2026 18:58:47] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:59:17,722 [INFO] 127.0.0.1 - - [02/Jun/2026 18:59:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 18:59:47,711 [INFO] 127.0.0.1 - - [02/Jun/2026 18:59:47] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:00:17,720 [INFO] 127.0.0.1 - - [02/Jun/2026 19:00:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:00:47,712 [INFO] 127.0.0.1 - - [02/Jun/2026 19:00:47] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:01:17,722 [INFO] 127.0.0.1 - - [02/Jun/2026 19:01:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:01:47,715 [INFO] 127.0.0.1 - - [02/Jun/2026 19:01:47] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:02:17,719 [INFO] 127.0.0.1 - - [02/Jun/2026 19:02:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:02:47,716 [INFO] 127.0.0.1 - - [02/Jun/2026 19:02:47] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:03:17,722 [INFO] 127.0.0.1 - - [02/Jun/2026 19:03:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:03:47,717 [INFO] 127.0.0.1 - - [02/Jun/2026 19:03:47] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:04:17,724 [INFO] 127.0.0.1 - - [02/Jun/2026 19:04:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:04:47,718 [INFO] 127.0.0.1 - - [02/Jun/2026 19:04:47] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:05:17,727 [INFO] 127.0.0.1 - - [02/Jun/2026 19:05:17] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:05:48,092 [INFO] 127.0.0.1 - - [02/Jun/2026 19:05:48] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:06:18,448 [INFO] 127.0.0.1 - - [02/Jun/2026 19:06:18] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:06:36,304 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 19:06:36,918 [INFO] 127.0.0.1 - - [02/Jun/2026 19:06:36] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 19:06:46,375 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 19:06:46,798 [INFO] 127.0.0.1 - - [02/Jun/2026 19:06:46] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 19:06:48,491 [INFO] 127.0.0.1 - - [02/Jun/2026 19:06:48] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:07:04,965 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 19:07:05,707 [INFO] 127.0.0.1 - - [02/Jun/2026 19:07:05] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 19:07:18,501 [INFO] 127.0.0.1 - - [02/Jun/2026 19:07:18] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:07:20,657 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 19:07:21,243 [INFO] 127.0.0.1 - - [02/Jun/2026 19:07:21] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 19:07:35,043 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 19:07:35,431 [INFO] 127.0.0.1 - - [02/Jun/2026 19:07:35] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 19:07:48,492 [INFO] 127.0.0.1 - - [02/Jun/2026 19:07:48] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:08:02,314 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 19:08:02,652 [INFO] 127.0.0.1 - - [02/Jun/2026 19:08:02] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 19:08:12,657 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 19:08:13,104 [INFO] 127.0.0.1 - - [02/Jun/2026 19:08:13] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 19:08:18,504 [INFO] 127.0.0.1 - - [02/Jun/2026 19:08:18] "GET /api/health HTTP/1.1" 200 - 2026-06-02 19:08:34,595 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-02 19:08:35,538 [INFO] 127.0.0.1 - - [02/Jun/2026 19:08:35] "POST /api/chat HTTP/1.1" 200 - 2026-06-02 19:08:48,491 [INFO] 127.0.0.1 - - [02/Jun/2026 19:08:48] "GET /api/health HTTP/1.1" 200 - 2026-06-03 21:42:43,463 [INFO] Loading FAISS index... 2026-06-03 21:42:43,546 [INFO] Loading chunk metadata... 2026-06-03 21:42:43,549 [INFO] Vector store ready — 107 chunks 2026-06-03 21:42:45,097 [INFO] BAL Chatbot Web API starting... 2026-06-03 21:42:45,098 [INFO] Runtime pid=14356 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 21:42:45,098 [INFO] Provider: groq 2026-06-03 21:42:45,098 [INFO] HTTPS enforcement: True 2026-06-03 21:42:45,098 [INFO] Loading FAISS index... 2026-06-03 21:42:45,101 [INFO] Loading chunk metadata... 2026-06-03 21:42:45,103 [INFO] Vector store ready — 107 chunks 2026-06-03 21:42:45,103 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 21:42:45,103 [INFO] LLM gateway ready — active provider: groq 2026-06-03 21:42:45,103 [INFO] Server starting on https://0.0.0.0:5000 2026-06-03 21:42:45,185 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-03 21:42:45,185 [INFO] Press CTRL+C to quit 2026-06-03 21:43:00,644 [INFO] 127.0.0.1 - - [03/Jun/2026 21:43:00] "GET / HTTP/1.1" 200 - 2026-06-03 21:43:00,903 [INFO] 127.0.0.1 - - [03/Jun/2026 21:43:00] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 21:49:27,343 [INFO] Loading FAISS index... 2026-06-03 21:49:27,346 [INFO] FAISS index loaded: 107 vectors 2026-06-03 21:49:27,346 [INFO] Loading chunk metadata... 2026-06-03 21:49:27,349 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 21:49:27,349 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 21:49:28,017 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 21:49:28,047 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 21:49:28,049 [INFO] Vector store ready — 107 chunks 2026-06-03 21:49:29,551 [INFO] BAL Chatbot Web API starting... 2026-06-03 21:49:29,551 [INFO] Runtime pid=18092 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 21:49:29,552 [INFO] Provider: groq 2026-06-03 21:49:29,552 [INFO] HTTPS enforcement: True 2026-06-03 21:49:29,552 [INFO] Loading FAISS index... 2026-06-03 21:49:29,554 [INFO] FAISS index loaded: 107 vectors 2026-06-03 21:49:29,554 [INFO] Loading chunk metadata... 2026-06-03 21:49:29,557 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 21:49:29,557 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 21:49:30,071 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 21:49:30,103 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 21:49:30,103 [INFO] Vector store ready — 107 chunks 2026-06-03 21:49:30,104 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 21:49:30,104 [INFO] LLM gateway ready — active provider: groq 2026-06-03 21:49:30,104 [INFO] Server starting on https://0.0.0.0:5000 2026-06-03 21:49:30,117 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-03 21:49:30,118 [INFO] Press CTRL+C to quit 2026-06-03 21:49:45,641 [INFO] 127.0.0.1 - - [03/Jun/2026 21:49:45] "GET / HTTP/1.1" 304 - 2026-06-03 21:49:45,682 [INFO] 127.0.0.1 - - [03/Jun/2026 21:49:45] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 21:50:18,719 [INFO] BAL Chatbot Web API starting... 2026-06-03 21:50:18,720 [INFO] Runtime pid=18596 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 21:50:18,720 [INFO] Provider: groq 2026-06-03 21:50:18,720 [INFO] HTTPS enforcement: True 2026-06-03 21:50:18,720 [INFO] Loading FAISS index... 2026-06-03 21:50:18,723 [INFO] FAISS index loaded: 107 vectors 2026-06-03 21:50:18,723 [INFO] Loading chunk metadata... 2026-06-03 21:50:18,726 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 21:50:18,726 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 21:50:19,199 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 21:50:19,228 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 21:50:19,229 [INFO] Vector store ready — 107 chunks 2026-06-03 21:50:19,230 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 21:50:19,230 [INFO] LLM gateway ready — active provider: groq 2026-06-03 21:50:19,230 [INFO] Server starting on https://0.0.0.0:5000 2026-06-03 21:50:19,271 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-03 21:50:19,272 [INFO] Press CTRL+C to quit 2026-06-03 21:50:31,405 [INFO] 127.0.0.1 - - [03/Jun/2026 21:50:31] "GET / HTTP/1.1" 304 - 2026-06-03 21:50:31,447 [INFO] 127.0.0.1 - - [03/Jun/2026 21:50:31] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 21:56:51,642 [INFO] BAL Chatbot Web API starting... 2026-06-03 21:56:51,643 [INFO] Runtime pid=24210 cwd=/home/burak/Masaüstü/ChatbotBAL log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 21:56:51,643 [INFO] Provider: groq 2026-06-03 21:56:51,643 [INFO] HTTPS enforcement: True 2026-06-03 21:56:51,643 [INFO] Loading FAISS index... 2026-06-03 21:56:51,646 [INFO] FAISS index loaded: 107 vectors 2026-06-03 21:56:51,646 [INFO] Loading chunk metadata... 2026-06-03 21:56:51,648 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 21:56:51,648 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 21:56:52,152 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 21:56:52,180 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 21:56:52,181 [INFO] Vector store ready — 107 chunks 2026-06-03 21:56:52,182 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 21:56:52,182 [INFO] LLM gateway ready — active provider: groq 2026-06-03 21:56:52,182 [INFO] Server starting on https://0.0.0.0:5000 2026-06-03 21:57:19,464 [INFO] 127.0.0.1 - - [03/Jun/2026 21:57:19] "GET /api/health HTTP/1.1" 200 - 2026-06-03 21:57:49,880 [INFO] BAL Chatbot Web API starting... 2026-06-03 21:57:49,881 [INFO] Runtime pid=24919 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 21:57:49,881 [INFO] Provider: groq 2026-06-03 21:57:49,881 [INFO] HTTPS enforcement: True 2026-06-03 21:57:49,882 [INFO] Loading FAISS index... 2026-06-03 21:57:49,884 [INFO] FAISS index loaded: 107 vectors 2026-06-03 21:57:49,884 [INFO] Loading chunk metadata... 2026-06-03 21:57:49,887 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 21:57:49,887 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 21:57:50,489 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 21:57:50,518 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 21:57:50,519 [INFO] Vector store ready — 107 chunks 2026-06-03 21:57:50,520 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 21:57:50,520 [INFO] LLM gateway ready — active provider: groq 2026-06-03 21:57:50,520 [INFO] Server starting on https://0.0.0.0:5000 2026-06-03 21:57:50,555 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-03 21:57:50,555 [INFO] Press CTRL+C to quit 2026-06-03 21:57:57,112 [INFO] 127.0.0.1 - - [03/Jun/2026 21:57:57] "GET / HTTP/1.1" 200 - 2026-06-03 21:57:57,159 [INFO] 127.0.0.1 - - [03/Jun/2026 21:57:57] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 21:57:57,394 [INFO] 127.0.0.1 - - [03/Jun/2026 21:57:57] "GET /api/health HTTP/1.1" 200 - 2026-06-03 21:57:57,869 [INFO] No existing user with fingerprint found: b519f8d30a65ecfd729c80d72ac25c44365d61b385d22ec4a3d4b900acfeb0d1 2026-06-03 21:57:58,154 [INFO] Created visitor user id=31 fingerprint=b519f8d30a65ecfd729c80d72ac25c44365d61b385d22ec4a3d4b900acfeb0d1 2026-06-03 21:57:58,635 [INFO] 127.0.0.1 - - [03/Jun/2026 21:57:58] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 21:58:01,805 [INFO] Found existing user id=31 for fingerprint 2026-06-03 21:58:03,111 [WARNING] Embedding failed with key 1: signal only works in main thread of the main interpreter 2026-06-03 21:58:03,152 [WARNING] Embedding failed with key 2: signal only works in main thread of the main interpreter 2026-06-03 21:58:03,193 [WARNING] Embedding failed with key 3: signal only works in main thread of the main interpreter 2026-06-03 21:58:03,194 [ERROR] Could not embed query (all Gemini keys failed): LGS taban puanı? 2026-06-03 21:58:03,195 [ERROR] Exception on /api/chat [POST] Traceback (most recent call last): File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 1511, in wsgi_app response = self.full_dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 919, in full_dispatch_request rv = self.handle_user_exception(e) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask_cors/extension.py", line 176, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) ^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 917, in full_dispatch_request rv = self.dispatch_request() ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/venv/lib/python3.12/site-packages/flask/app.py", line 902, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 1123, in chat retrieved = vector_store.retrieve(user_message, top_k=CONFIG["retrieval_top_k"]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 668, in retrieve raise RuntimeError( RuntimeError: Sorgu embedding'i başarısız. Lütfen daha sonra tekrar deneyin. 2026-06-03 21:58:03,274 [INFO] 127.0.0.1 - - [03/Jun/2026 21:58:03] "POST /api/chat HTTP/1.1" 500 - 2026-06-03 21:58:27,733 [INFO] 127.0.0.1 - - [03/Jun/2026 21:58:27] "GET /api/health HTTP/1.1" 200 - 2026-06-03 21:58:58,220 [INFO] 127.0.0.1 - - [03/Jun/2026 21:58:58] "GET /api/health HTTP/1.1" 200 - 2026-06-03 21:59:28,223 [INFO] 127.0.0.1 - - [03/Jun/2026 21:59:28] "GET /api/health HTTP/1.1" 200 - 2026-06-03 21:59:58,286 [INFO] 127.0.0.1 - - [03/Jun/2026 21:59:58] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:00:27,115 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:00:27,115 [INFO] Runtime pid=26776 cwd=/home/burak/Masaüstü/ChatbotBAL log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:00:27,115 [INFO] Provider: groq 2026-06-03 22:00:27,116 [INFO] HTTPS enforcement: True 2026-06-03 22:00:27,116 [INFO] Loading FAISS index... 2026-06-03 22:00:27,118 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:00:27,118 [INFO] Loading chunk metadata... 2026-06-03 22:00:27,121 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:00:27,121 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:00:27,798 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:00:27,832 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:00:27,832 [INFO] Vector store ready — 107 chunks 2026-06-03 22:00:27,833 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:00:27,833 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:00:27,833 [INFO] Server starting on http://0.0.0.0:5001 2026-06-03 22:00:27,841 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5001 * Running on http://192.168.1.2:5001 2026-06-03 22:00:27,841 [INFO] Press CTRL+C to quit 2026-06-03 22:00:28,285 [INFO] 127.0.0.1 - - [03/Jun/2026 22:00:28] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:00:58,954 [INFO] 127.0.0.1 - - [03/Jun/2026 22:00:58] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:01:23,959 [INFO] No existing user with fingerprint found: fe4b2e03cd91ae11c3eb76efda6521adb3328e2c2b707bc52072b8d453a0ff69 2026-06-03 22:01:24,228 [INFO] Created visitor user id=32 fingerprint=fe4b2e03cd91ae11c3eb76efda6521adb3328e2c2b707bc52072b8d453a0ff69 2026-06-03 22:01:26,064 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:01:26,454 [INFO] 127.0.0.1 - - [03/Jun/2026 22:01:26] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:01:26,467 [INFO] 127.0.0.1 - - [03/Jun/2026 22:01:26] "POST /api/chat HTTP/1.1" 200 - 2026-06-03 22:01:28,945 [INFO] 127.0.0.1 - - [03/Jun/2026 22:01:28] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:02:01,428 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:02:01,429 [INFO] Runtime pid=27693 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:02:01,429 [INFO] Provider: groq 2026-06-03 22:02:01,429 [INFO] HTTPS enforcement: True 2026-06-03 22:02:01,429 [INFO] Loading FAISS index... 2026-06-03 22:02:01,432 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:02:01,433 [INFO] Loading chunk metadata... 2026-06-03 22:02:01,436 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:02:01,436 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:02:01,949 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:02:01,977 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:02:01,979 [INFO] Vector store ready — 107 chunks 2026-06-03 22:02:01,979 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:02:01,979 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:02:01,979 [INFO] Server starting on https://0.0.0.0:5000 2026-06-03 22:02:02,016 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-03 22:02:02,016 [INFO] Press CTRL+C to quit 2026-06-03 22:02:07,608 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:07] "GET / HTTP/1.1" 304 - 2026-06-03 22:02:07,643 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:07] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 22:02:07,857 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:07] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:02:08,078 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:02:08,553 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:08] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:02:09,440 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:02:11,185 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:02:11,626 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:11] "POST /api/chat HTTP/1.1" 200 - 2026-06-03 22:02:12,218 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:02:12,684 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:12] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:02:18,634 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:02:20,396 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:02:20,587 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '5', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '11387', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '3.065s', 'x-request-id': 'req_01kt7dtz4pey1vbmrvds8r3350'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:02:20,606 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-03 22:02:20,758 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kt7dtza0ey3tke0y5gscn16c'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:02:20,759 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-03 22:02:21,561 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:21] "POST /api/chat HTTP/1.1" 200 - 2026-06-03 22:02:21,985 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-03 22:02:22,418 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:02:22,881 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:22] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:02:37,897 [INFO] 127.0.0.1 - - [03/Jun/2026 22:02:37] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:03:08,477 [INFO] 127.0.0.1 - - [03/Jun/2026 22:03:08] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:03:22,788 [INFO] 127.0.0.1 - - [03/Jun/2026 22:03:22] "GET / HTTP/1.1" 304 - 2026-06-03 22:03:22,807 [INFO] 127.0.0.1 - - [03/Jun/2026 22:03:22] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 22:03:22,970 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:03:23,024 [INFO] 127.0.0.1 - - [03/Jun/2026 22:03:23] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:03:23,434 [INFO] 127.0.0.1 - - [03/Jun/2026 22:03:23] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:03:24,510 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:03:26,303 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:03:26,725 [INFO] 127.0.0.1 - - [03/Jun/2026 22:03:26] "POST /api/chat HTTP/1.1" 200 - 2026-06-03 22:03:27,409 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:03:27,875 [INFO] 127.0.0.1 - - [03/Jun/2026 22:03:27] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:03:53,088 [INFO] 127.0.0.1 - - [03/Jun/2026 22:03:53] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:04:23,095 [INFO] 127.0.0.1 - - [03/Jun/2026 22:04:23] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:04:53,089 [INFO] 127.0.0.1 - - [03/Jun/2026 22:04:53] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:05:55,297 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:05:55,298 [INFO] Runtime pid=30484 cwd=/home/burak/Masaüstü/ChatbotBAL log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:05:55,298 [INFO] Provider: groq 2026-06-03 22:05:55,298 [INFO] HTTPS enforcement: True 2026-06-03 22:05:55,299 [INFO] Loading FAISS index... 2026-06-03 22:05:55,301 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:05:55,301 [INFO] Loading chunk metadata... 2026-06-03 22:05:55,304 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:05:55,304 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:05:55,778 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:05:55,808 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:05:55,809 [INFO] Vector store ready — 107 chunks 2026-06-03 22:05:55,809 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:05:55,809 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:05:55,809 [INFO] Server starting on http://0.0.0.0:5002 2026-06-03 22:05:55,816 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5002 * Running on http://192.168.1.2:5002 2026-06-03 22:05:55,816 [INFO] Press CTRL+C to quit 2026-06-03 22:07:41,695 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:07:41,696 [INFO] Runtime pid=32644 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:07:41,696 [INFO] Provider: groq 2026-06-03 22:07:41,696 [INFO] HTTPS enforcement: True 2026-06-03 22:07:41,696 [INFO] Loading FAISS index... 2026-06-03 22:07:41,699 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:07:41,699 [INFO] Loading chunk metadata... 2026-06-03 22:07:41,701 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:07:41,701 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:07:42,259 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:07:42,288 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:07:42,289 [INFO] Vector store ready — 107 chunks 2026-06-03 22:07:42,290 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:07:42,290 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:07:42,290 [INFO] Server starting on http://0.0.0.0:5000 2026-06-03 22:07:42,295 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-03 22:07:42,295 [INFO] Press CTRL+C to quit 2026-06-03 22:07:46,113 [ERROR] 127.0.0.1 - - [03/Jun/2026 22:07:46] code 400, message Bad request version ('\x13\x01\x13\x03\x13\x02À+À/̨̩À,À0À') 2026-06-03 22:07:46,113 [INFO] 127.0.0.1 - - [03/Jun/2026 22:07:46] "\x16\x03\x01\x07_\x01\x00\x07[\x03\x03 C¹\x12vµ\x89\x87ÉÂ\x0bê\x0c@3Úü>i`\\Áj^\x97rAÿ§\x9f\x1b¾ ú=ö\x08~3¼C\x0cÎÙÃÏ\x0fB\x1c\x18V¿\x1f{<¦\x04\x9b\x0dNMô\x93®l\x00 \x13\x01\x13\x03\x13\x02À+À/̨̩À,À0À" 400 - 2026-06-03 22:07:46,120 [ERROR] 127.0.0.1 - - [03/Jun/2026 22:07:46] code 400, message Bad request syntax ('\x16\x03\x01\x07_\x01\x00\x07[\x03\x03$ǽ') 2026-06-03 22:07:46,120 [INFO] 127.0.0.1 - - [03/Jun/2026 22:07:46] "\x16\x03\x01\x07_\x01\x00\x07[\x03\x03$ǽ" 400 - 2026-06-03 22:08:35,479 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:08:35,479 [INFO] Runtime pid=34130 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:08:35,479 [INFO] Provider: groq 2026-06-03 22:08:35,479 [INFO] HTTPS enforcement: True 2026-06-03 22:08:35,480 [INFO] Loading FAISS index... 2026-06-03 22:08:35,482 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:08:35,482 [INFO] Loading chunk metadata... 2026-06-03 22:08:35,485 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:08:35,485 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:08:36,120 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:08:36,144 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:08:36,144 [INFO] Vector store ready — 107 chunks 2026-06-03 22:08:36,144 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:08:36,144 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:08:36,144 [INFO] Server starting on https://0.0.0.0:5000 2026-06-03 22:08:36,180 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on https://127.0.0.1:5000 * Running on https://192.168.1.2:5000 2026-06-03 22:08:36,180 [INFO] Press CTRL+C to quit 2026-06-03 22:09:17,159 [INFO] 127.0.0.1 - - [03/Jun/2026 22:09:17] "GET / HTTP/1.1" 304 - 2026-06-03 22:09:17,213 [INFO] 127.0.0.1 - - [03/Jun/2026 22:09:17] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 22:09:17,429 [INFO] 127.0.0.1 - - [03/Jun/2026 22:09:17] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:09:17,649 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:09:18,124 [INFO] 127.0.0.1 - - [03/Jun/2026 22:09:18] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:09:20,739 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:09:22,501 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:09:22,740 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1525', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kt7e7vctey48r4nqj4s33xbe'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:09:22,744 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-03 22:09:22,883 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kt7e7vhbf6pvymvrxyx5x0aa'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:09:22,885 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-03 22:09:23,363 [INFO] 127.0.0.1 - - [03/Jun/2026 22:09:23] "POST /api/chat HTTP/1.1" 200 - 2026-06-03 22:09:24,322 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-03 22:09:24,763 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:09:25,225 [INFO] 127.0.0.1 - - [03/Jun/2026 22:09:25] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:09:47,995 [INFO] 127.0.0.1 - - [03/Jun/2026 22:09:47] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:10:18,260 [INFO] 127.0.0.1 - - [03/Jun/2026 22:10:18] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:10:48,269 [INFO] 127.0.0.1 - - [03/Jun/2026 22:10:48] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:11:18,360 [INFO] 127.0.0.1 - - [03/Jun/2026 22:11:18] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:11:48,378 [INFO] 127.0.0.1 - - [03/Jun/2026 22:11:48] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:12:18,760 [INFO] 127.0.0.1 - - [03/Jun/2026 22:12:18] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:12:48,765 [INFO] 127.0.0.1 - - [03/Jun/2026 22:12:48] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:13:15,262 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:13:17,046 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:13:17,226 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1969', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kt7ef0ccfcbtbc8fm1md7dak'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:13:17,229 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-03 22:13:17,374 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kt7ef0h1f3stftrsnkwxt8dd'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:13:17,375 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-03 22:13:17,737 [INFO] 127.0.0.1 - - [03/Jun/2026 22:13:17] "POST /api/chat HTTP/1.1" 200 - 2026-06-03 22:13:18,356 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-03 22:13:18,771 [INFO] 127.0.0.1 - - [03/Jun/2026 22:13:18] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:13:18,772 [INFO] Found existing user id=31 for fingerprint 2026-06-03 22:13:19,243 [INFO] 127.0.0.1 - - [03/Jun/2026 22:13:19] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:13:48,772 [INFO] 127.0.0.1 - - [03/Jun/2026 22:13:48] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:14:18,760 [INFO] 127.0.0.1 - - [03/Jun/2026 22:14:18] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:14:48,765 [INFO] 127.0.0.1 - - [03/Jun/2026 22:14:48] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:15:02,371 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:15:02,372 [INFO] Runtime pid=37586 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:15:02,372 [INFO] Provider: groq 2026-06-03 22:15:02,372 [INFO] HTTPS enforcement: False 2026-06-03 22:15:02,372 [INFO] Loading FAISS index... 2026-06-03 22:15:02,375 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:15:02,375 [INFO] Loading chunk metadata... 2026-06-03 22:15:02,377 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:15:02,378 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:15:02,883 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:15:02,912 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:15:02,913 [INFO] Vector store ready — 107 chunks 2026-06-03 22:15:02,913 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:15:02,913 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:15:02,913 [INFO] Server starting on http://0.0.0.0:5000 2026-06-03 22:15:02,919 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-03 22:15:02,920 [INFO] Press CTRL+C to quit 2026-06-03 22:15:19,119 [ERROR] 127.0.0.1 - - [03/Jun/2026 22:15:19] code 400, message Bad request version ('\x13\x01\x13\x03\x13\x02À+À/̨̩À,À0À') 2026-06-03 22:15:19,119 [INFO] 127.0.0.1 - - [03/Jun/2026 22:15:19] "\x16\x03\x01\x09\x8a\x01\x00\x09\x86\x03\x03ÔÁL%E\x80\x19\x84Y\x99BË\x85\x12ã´`÷¢xð7\x96\x9d¥¬Z6ºKè> .ï;`¥%>Â\x1b´öÁFX;ïOFè`P\x87\x1dº_\x0be\x9bU \x88Æ\x00 \x13\x01\x13\x03\x13\x02À+À/̨̩À,À0À" 400 - 2026-06-03 22:15:21,257 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:21] "GET / HTTP/1.1" 200 - 2026-06-03 22:15:21,472 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:21] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 22:15:21,882 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:21] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:15:21,974 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:21] "GET /favicon.ico HTTP/1.1" 404 - 2026-06-03 22:15:22,081 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:15:22,563 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:22] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:15:29,467 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:15:31,255 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:15:31,496 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1734', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kt7ek3gaerrrhh50v4nxcx1h'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:15:31,499 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-03 22:15:31,644 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kt7ek3n1fdjrncq42d3z5k8n'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:15:31,646 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-03 22:15:32,703 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:32] "POST /api/chat HTTP/1.1" 200 - 2026-06-03 22:15:33,720 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-03 22:15:34,276 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:15:34,747 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:34] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:15:39,331 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:15:41,190 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:15:41,379 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '2926', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kt7ekd55f948ey6gtprja4wh'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:15:41,381 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-03 22:15:41,526 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kt7ekd9tfj78drmqxg7s1a2z'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:15:41,527 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-03 22:15:41,691 [ERROR] Groq API HTTP error status=429 model=qwen/qwen3-32b rate_headers={'retry-after': '4', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '6000', 'x-ratelimit-remaining-requests': '999', 'x-ratelimit-remaining-tokens': '4205', 'x-ratelimit-reset-requests': '1m26.4s', 'x-ratelimit-reset-tokens': '17.95s', 'x-request-id': 'req_01kt7ekdewfj9s95wepnr3jq3z'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 756, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-03 22:15:41,693 [WARNING] Groq fallback switching key_index=1 from_model=qwen/qwen3-32b to_model=meta-llama/llama-4-scout-17b-16e-instruct reason=http_429 2026-06-03 22:15:42,088 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:42] "POST /api/chat HTTP/1.1" 200 - 2026-06-03 22:15:42,151 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=meta-llama/llama-4-scout-17b-16e-instruct 2026-06-03 22:15:42,686 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:15:43,158 [INFO] 212.252.116.251 - - [03/Jun/2026 22:15:43] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:18:12,240 [INFO] 212.252.116.251 - - [03/Jun/2026 22:18:12] "GET / HTTP/1.1" 304 - 2026-06-03 22:18:12,403 [INFO] 212.252.116.251 - - [03/Jun/2026 22:18:12] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 22:18:12,599 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:18:12,632 [INFO] 212.252.116.251 - - [03/Jun/2026 22:18:12] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:18:13,074 [INFO] 212.252.116.251 - - [03/Jun/2026 22:18:13] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:18:42,720 [INFO] 212.252.116.251 - - [03/Jun/2026 22:18:42] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:19:12,731 [INFO] 212.252.116.251 - - [03/Jun/2026 22:19:12] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:19:42,880 [INFO] 212.252.116.251 - - [03/Jun/2026 22:19:42] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:19:57,264 [INFO] 127.0.0.1 - - [03/Jun/2026 22:19:57] "GET /BAL_Logo.png HTTP/1.1" 404 - 2026-06-03 22:19:57,284 [INFO] 127.0.0.1 - - [03/Jun/2026 22:19:57] "GET /favicon.ico HTTP/1.1" 404 - 2026-06-03 22:20:12,895 [INFO] 212.252.116.251 - - [03/Jun/2026 22:20:12] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:20:42,876 [INFO] 212.252.116.251 - - [03/Jun/2026 22:20:42] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:21:12,902 [INFO] 212.252.116.251 - - [03/Jun/2026 22:21:12] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:21:42,882 [INFO] 212.252.116.251 - - [03/Jun/2026 22:21:42] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:22:12,899 [INFO] 212.252.116.251 - - [03/Jun/2026 22:22:12] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:22:42,881 [INFO] 212.252.116.251 - - [03/Jun/2026 22:22:42] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:23:12,897 [INFO] 212.252.116.251 - - [03/Jun/2026 22:23:12] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:23:30,689 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:23:30,690 [INFO] Runtime pid=41796 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:23:30,690 [INFO] Provider: groq 2026-06-03 22:23:30,690 [INFO] HTTPS enforcement: False 2026-06-03 22:23:30,690 [INFO] Loading FAISS index... 2026-06-03 22:23:30,693 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:23:30,693 [INFO] Loading chunk metadata... 2026-06-03 22:23:30,695 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:23:30,696 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:23:31,170 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:23:31,200 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:23:31,201 [INFO] Vector store ready — 107 chunks 2026-06-03 22:23:31,201 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:23:31,201 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:23:31,201 [INFO] Server starting on http://0.0.0.0:5000 2026-06-03 22:23:31,207 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-03 22:23:31,207 [INFO] Press CTRL+C to quit 2026-06-03 22:23:52,989 [INFO] 212.252.116.251 - - [03/Jun/2026 22:23:52] "GET / HTTP/1.1" 304 - 2026-06-03 22:23:53,140 [INFO] 212.252.116.251 - - [03/Jun/2026 22:23:53] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-03 22:23:53,394 [INFO] 212.252.116.251 - - [03/Jun/2026 22:23:53] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:23:54,378 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:23:54,851 [INFO] 212.252.116.251 - - [03/Jun/2026 22:23:54] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:25:34,263 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:25:34,264 [INFO] Runtime pid=43525 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:25:34,264 [INFO] Provider: groq 2026-06-03 22:25:34,264 [INFO] HTTPS enforcement: False 2026-06-03 22:25:34,265 [INFO] Loading FAISS index... 2026-06-03 22:25:34,267 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:25:34,267 [INFO] Loading chunk metadata... 2026-06-03 22:25:34,270 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:25:34,270 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:25:34,884 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:25:34,914 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:25:34,916 [INFO] Vector store ready — 107 chunks 2026-06-03 22:25:34,916 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:25:34,916 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:25:34,917 [INFO] Server starting on http://0.0.0.0:5000 2026-06-03 22:25:34,922 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-03 22:25:34,922 [INFO] Press CTRL+C to quit 2026-06-03 22:25:45,877 [INFO] 212.252.116.251 - - [03/Jun/2026 22:25:45] "GET / HTTP/1.1" 304 - 2026-06-03 22:25:46,024 [INFO] 212.252.116.251 - - [03/Jun/2026 22:25:46] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-03 22:25:46,213 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:25:46,532 [INFO] 212.252.116.251 - - [03/Jun/2026 22:25:46] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:25:46,673 [INFO] 212.252.116.251 - - [03/Jun/2026 22:25:46] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:25:54,325 [INFO] 212.252.116.251 - - [03/Jun/2026 22:25:54] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:26:16,283 [INFO] 212.252.116.251 - - [03/Jun/2026 22:26:16] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:26:24,324 [INFO] 212.252.116.251 - - [03/Jun/2026 22:26:24] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:26:46,430 [INFO] 212.252.116.251 - - [03/Jun/2026 22:26:46] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:26:55,097 [INFO] 212.252.116.251 - - [03/Jun/2026 22:26:55] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:27:17,365 [INFO] 212.252.116.251 - - [03/Jun/2026 22:27:17] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:27:25,090 [INFO] 212.252.116.251 - - [03/Jun/2026 22:27:25] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:27:47,949 [INFO] 212.252.116.251 - - [03/Jun/2026 22:27:47] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:27:55,368 [INFO] 212.252.116.251 - - [03/Jun/2026 22:27:55] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:28:18,148 [INFO] 212.252.116.251 - - [03/Jun/2026 22:28:18] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:28:25,367 [INFO] 212.252.116.251 - - [03/Jun/2026 22:28:25] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:28:48,597 [INFO] 212.252.116.251 - - [03/Jun/2026 22:28:48] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:28:55,417 [INFO] 212.252.116.251 - - [03/Jun/2026 22:28:55] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:29:02,538 [INFO] BAL Chatbot Web API starting... 2026-06-03 22:29:02,538 [INFO] Runtime pid=45336 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-03 22:29:02,538 [INFO] Provider: groq 2026-06-03 22:29:02,538 [INFO] HTTPS enforcement: False 2026-06-03 22:29:02,538 [INFO] Loading FAISS index... 2026-06-03 22:29:02,539 [INFO] FAISS index loaded: 107 vectors 2026-06-03 22:29:02,539 [INFO] Loading chunk metadata... 2026-06-03 22:29:02,540 [INFO] Chunk metadata loaded: 107 chunks 2026-06-03 22:29:02,540 [INFO] Testing embedding API with 3 key(s)... 2026-06-03 22:29:03,023 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-03 22:29:03,051 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-03 22:29:03,053 [INFO] Vector store ready — 107 chunks 2026-06-03 22:29:03,053 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-03 22:29:03,053 [INFO] LLM gateway ready — active provider: groq 2026-06-03 22:29:03,053 [INFO] Server starting on http://0.0.0.0:5000 2026-06-03 22:29:03,060 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-03 22:29:03,060 [INFO] Press CTRL+C to quit 2026-06-03 22:29:18,771 [INFO] 212.252.116.251 - - [03/Jun/2026 22:29:18] "GET / HTTP/1.1" 200 - 2026-06-03 22:29:19,006 [INFO] 212.252.116.251 - - [03/Jun/2026 22:29:19] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-03 22:29:19,223 [INFO] 212.252.116.251 - - [03/Jun/2026 22:29:19] "GET /api/health HTTP/1.1" 200 - 2026-06-03 22:29:19,447 [INFO] Found existing user id=27 for fingerprint 2026-06-03 22:29:19,914 [INFO] 212.252.116.251 - - [03/Jun/2026 22:29:19] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-03 22:29:25,425 [INFO] 212.252.116.251 - - [03/Jun/2026 22:29:25] "GET /api/health HTTP/1.1" 200 - 2026-06-04 12:58:01,006 [INFO] BAL Chatbot Web API starting... 2026-06-04 12:58:01,039 [INFO] Runtime pid=59976 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 12:58:01,039 [INFO] Provider: groq 2026-06-04 12:58:01,039 [INFO] HTTPS enforcement: False 2026-06-04 12:58:01,040 [INFO] Loading FAISS index... 2026-06-04 12:58:01,065 [INFO] FAISS index loaded: 107 vectors 2026-06-04 12:58:01,065 [INFO] Loading chunk metadata... 2026-06-04 12:58:01,067 [INFO] Chunk metadata loaded: 107 chunks 2026-06-04 12:58:01,068 [INFO] Testing embedding API with 3 key(s)... 2026-06-04 12:58:01,747 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 12:58:01,776 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 12:58:01,778 [INFO] Vector store ready — 107 chunks 2026-06-04 12:58:01,778 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 12:58:01,778 [INFO] LLM gateway ready — active provider: groq 2026-06-04 12:58:01,778 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 12:58:01,795 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 12:58:01,796 [INFO] Press CTRL+C to quit 2026-06-04 12:58:49,922 [INFO] 212.252.116.251 - - [04/Jun/2026 12:58:49] "GET / HTTP/1.1" 304 - 2026-06-04 12:58:50,100 [INFO] 212.252.116.251 - - [04/Jun/2026 12:58:50] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 12:58:50,334 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:58:50,671 [INFO] 212.252.116.251 - - [04/Jun/2026 12:58:50] "GET /api/health HTTP/1.1" 200 - 2026-06-04 12:58:50,818 [INFO] 212.252.116.251 - - [04/Jun/2026 12:58:50] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 12:58:52,833 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:58:54,567 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 12:58:55,179 [INFO] 212.252.116.251 - - [04/Jun/2026 12:58:55] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 12:58:55,977 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:58:56,439 [INFO] 212.252.116.251 - - [04/Jun/2026 12:58:56] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 12:59:20,418 [INFO] 212.252.116.251 - - [04/Jun/2026 12:59:20] "GET /api/health HTTP/1.1" 200 - 2026-06-04 12:59:22,776 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:59:24,541 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 12:59:24,935 [INFO] 212.252.116.251 - - [04/Jun/2026 12:59:24] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 12:59:25,489 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:59:25,954 [INFO] 212.252.116.251 - - [04/Jun/2026 12:59:25] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 12:59:33,486 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:59:35,228 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 12:59:35,682 [INFO] 212.252.116.251 - - [04/Jun/2026 12:59:35] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 12:59:36,225 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:59:36,686 [INFO] 212.252.116.251 - - [04/Jun/2026 12:59:36] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 12:59:43,195 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:59:44,974 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 12:59:45,394 [INFO] 212.252.116.251 - - [04/Jun/2026 12:59:45] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 12:59:46,201 [INFO] Found existing user id=27 for fingerprint 2026-06-04 12:59:46,663 [INFO] 212.252.116.251 - - [04/Jun/2026 12:59:46] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 12:59:50,639 [INFO] 212.252.116.251 - - [04/Jun/2026 12:59:50] "GET /api/health HTTP/1.1" 200 - 2026-06-04 12:59:59,796 [INFO] Found existing user id=27 for fingerprint 2026-06-04 13:00:01,594 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 13:00:02,928 [INFO] 212.252.116.251 - - [04/Jun/2026 13:00:02] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 13:00:03,465 [INFO] Found existing user id=27 for fingerprint 2026-06-04 13:00:03,930 [INFO] 212.252.116.251 - - [04/Jun/2026 13:00:03] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 13:00:30,795 [INFO] 46.155.100.108 - - [04/Jun/2026 13:00:30] "GET / HTTP/1.1" 200 - 2026-06-04 13:00:31,070 [INFO] 46.155.100.108 - - [04/Jun/2026 13:00:31] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-04 13:00:31,467 [INFO] No existing user with fingerprint found: 93b080b1d8e3e6bd1f6eb98af67c9e69ef5efea307628cbde62fb64a21de9b3b 2026-06-04 13:00:31,741 [INFO] Created visitor user id=33 fingerprint=93b080b1d8e3e6bd1f6eb98af67c9e69ef5efea307628cbde62fb64a21de9b3b 2026-06-04 13:00:31,831 [INFO] 46.155.100.108 - - [04/Jun/2026 13:00:31] "GET /api/health HTTP/1.1" 200 - 2026-06-04 13:00:32,568 [INFO] 46.155.100.108 - - [04/Jun/2026 13:00:32] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 13:00:37,192 [INFO] Found existing user id=33 for fingerprint 2026-06-04 13:00:38,959 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 13:00:39,453 [INFO] 46.155.100.108 - - [04/Jun/2026 13:00:39] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 13:00:40,381 [INFO] Found existing user id=33 for fingerprint 2026-06-04 13:00:40,857 [INFO] 46.155.100.108 - - [04/Jun/2026 13:00:40] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 13:12:25,820 [INFO] 46.155.100.108 - - [04/Jun/2026 13:12:25] "GET /api/health HTTP/1.1" 200 - 2026-06-04 13:12:41,695 [INFO] Found existing user id=33 for fingerprint 2026-06-04 13:12:43,490 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 13:12:43,901 [INFO] 46.155.100.108 - - [04/Jun/2026 13:12:43] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 13:12:44,549 [INFO] Found existing user id=33 for fingerprint 2026-06-04 13:12:45,008 [INFO] 46.155.100.108 - - [04/Jun/2026 13:12:45] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 13:12:54,180 [INFO] 46.155.100.108 - - [04/Jun/2026 13:12:54] "GET /api/health HTTP/1.1" 200 - 2026-06-04 13:12:54,814 [INFO] Found existing user id=33 for fingerprint 2026-06-04 13:12:56,515 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 13:12:56,866 [INFO] 46.155.100.108 - - [04/Jun/2026 13:12:56] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 13:12:57,474 [INFO] Found existing user id=33 for fingerprint 2026-06-04 13:12:57,935 [INFO] 46.155.100.108 - - [04/Jun/2026 13:12:57] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 13:13:06,897 [INFO] Found existing user id=33 for fingerprint 2026-06-04 13:13:08,643 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 13:13:09,283 [INFO] 46.155.100.108 - - [04/Jun/2026 13:13:09] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 13:13:10,144 [INFO] Found existing user id=33 for fingerprint 2026-06-04 13:13:10,604 [INFO] 46.155.100.108 - - [04/Jun/2026 13:13:10] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 15:04:34,603 [INFO] Found existing user id=33 for fingerprint 2026-06-04 15:04:36,609 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 15:04:37,643 [INFO] 46.155.100.108 - - [04/Jun/2026 15:04:37] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 19:24:25,071 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:25] "GET / HTTP/1.1" 304 - 2026-06-04 19:24:25,225 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:25] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 19:24:25,883 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:24:25,911 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:25] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:24:26,371 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:26] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 19:24:32,029 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:24:34,019 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 19:24:34,473 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:34] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 19:24:35,209 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:24:35,699 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:35] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 19:24:50,395 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:24:52,515 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 19:24:53,087 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:53] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 19:24:53,861 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:24:54,349 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:54] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 19:24:55,463 [INFO] 212.252.116.251 - - [04/Jun/2026 19:24:55] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:25:09,977 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:25:11,718 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 429 Too Many Requests" 2026-06-04 19:25:11,720 [WARNING] Embedding failed with key 1: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.', 'status': 'RESOURCE_EXHAUSTED'}} 2026-06-04 19:25:12,386 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 19:25:12,826 [INFO] 212.252.116.251 - - [04/Jun/2026 19:25:12] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 19:25:13,402 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:25:13,891 [INFO] 212.252.116.251 - - [04/Jun/2026 19:25:13] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 19:25:25,567 [INFO] 212.252.116.251 - - [04/Jun/2026 19:25:25] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:25:34,789 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:25:36,578 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 429 Too Many Requests" 2026-06-04 19:25:36,581 [WARNING] Embedding failed with key 1: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.', 'status': 'RESOURCE_EXHAUSTED'}} 2026-06-04 19:25:37,137 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 19:25:37,540 [INFO] 212.252.116.251 - - [04/Jun/2026 19:25:37] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 19:25:38,116 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:25:38,605 [INFO] 212.252.116.251 - - [04/Jun/2026 19:25:38] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 19:25:56,130 [INFO] 212.252.116.251 - - [04/Jun/2026 19:25:56] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:26:11,871 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:26:13,785 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 19:26:14,353 [INFO] 212.252.116.251 - - [04/Jun/2026 19:26:14] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 19:26:14,918 [INFO] Found existing user id=27 for fingerprint 2026-06-04 19:26:15,406 [INFO] 212.252.116.251 - - [04/Jun/2026 19:26:15] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 19:26:26,148 [INFO] 212.252.116.251 - - [04/Jun/2026 19:26:26] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:26:56,132 [INFO] 212.252.116.251 - - [04/Jun/2026 19:26:56] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:27:26,463 [INFO] 212.252.116.251 - - [04/Jun/2026 19:27:26] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:27:56,448 [INFO] 212.252.116.251 - - [04/Jun/2026 19:27:56] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:28:26,615 [INFO] 212.252.116.251 - - [04/Jun/2026 19:28:26] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:28:56,601 [INFO] 212.252.116.251 - - [04/Jun/2026 19:28:56] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:29:26,626 [INFO] 212.252.116.251 - - [04/Jun/2026 19:29:26] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:29:56,602 [INFO] 212.252.116.251 - - [04/Jun/2026 19:29:56] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:30:27,169 [INFO] 212.252.116.251 - - [04/Jun/2026 19:30:27] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:30:57,149 [INFO] 212.252.116.251 - - [04/Jun/2026 19:30:57] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:31:27,934 [INFO] 212.252.116.251 - - [04/Jun/2026 19:31:27] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:31:57,923 [INFO] 212.252.116.251 - - [04/Jun/2026 19:31:57] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:32:28,441 [INFO] 212.252.116.251 - - [04/Jun/2026 19:32:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:32:58,424 [INFO] 212.252.116.251 - - [04/Jun/2026 19:32:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:33:28,442 [INFO] 212.252.116.251 - - [04/Jun/2026 19:33:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:33:58,456 [INFO] 212.252.116.251 - - [04/Jun/2026 19:33:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:34:28,471 [INFO] 212.252.116.251 - - [04/Jun/2026 19:34:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:34:58,455 [INFO] 212.252.116.251 - - [04/Jun/2026 19:34:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:35:28,471 [INFO] 212.252.116.251 - - [04/Jun/2026 19:35:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:35:58,456 [INFO] 212.252.116.251 - - [04/Jun/2026 19:35:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:36:28,473 [INFO] 212.252.116.251 - - [04/Jun/2026 19:36:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:36:58,457 [INFO] 212.252.116.251 - - [04/Jun/2026 19:36:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:37:28,476 [INFO] 212.252.116.251 - - [04/Jun/2026 19:37:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:37:58,459 [INFO] 212.252.116.251 - - [04/Jun/2026 19:37:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:38:28,474 [INFO] 212.252.116.251 - - [04/Jun/2026 19:38:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:38:58,461 [INFO] 212.252.116.251 - - [04/Jun/2026 19:38:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:39:28,477 [INFO] 212.252.116.251 - - [04/Jun/2026 19:39:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:39:58,459 [INFO] 212.252.116.251 - - [04/Jun/2026 19:39:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:40:28,476 [INFO] 212.252.116.251 - - [04/Jun/2026 19:40:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:40:58,461 [INFO] 212.252.116.251 - - [04/Jun/2026 19:40:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:41:28,477 [INFO] 212.252.116.251 - - [04/Jun/2026 19:41:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:41:58,460 [INFO] 212.252.116.251 - - [04/Jun/2026 19:41:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:42:28,478 [INFO] 212.252.116.251 - - [04/Jun/2026 19:42:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:42:58,461 [INFO] 212.252.116.251 - - [04/Jun/2026 19:42:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:43:28,494 [INFO] 212.252.116.251 - - [04/Jun/2026 19:43:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:43:58,476 [INFO] 212.252.116.251 - - [04/Jun/2026 19:43:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:44:28,493 [INFO] 212.252.116.251 - - [04/Jun/2026 19:44:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:44:58,480 [INFO] 212.252.116.251 - - [04/Jun/2026 19:44:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:45:28,494 [INFO] 212.252.116.251 - - [04/Jun/2026 19:45:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:45:58,477 [INFO] 212.252.116.251 - - [04/Jun/2026 19:45:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:46:28,492 [INFO] 212.252.116.251 - - [04/Jun/2026 19:46:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:46:58,476 [INFO] 212.252.116.251 - - [04/Jun/2026 19:46:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:47:28,778 [INFO] 212.252.116.251 - - [04/Jun/2026 19:47:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:47:58,762 [INFO] 212.252.116.251 - - [04/Jun/2026 19:47:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:48:28,780 [INFO] 212.252.116.251 - - [04/Jun/2026 19:48:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:48:58,766 [INFO] 212.252.116.251 - - [04/Jun/2026 19:48:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:49:28,779 [INFO] 212.252.116.251 - - [04/Jun/2026 19:49:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:49:58,761 [INFO] 212.252.116.251 - - [04/Jun/2026 19:49:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:50:29,098 [INFO] 212.252.116.251 - - [04/Jun/2026 19:50:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:50:59,083 [INFO] 212.252.116.251 - - [04/Jun/2026 19:50:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:51:29,100 [INFO] 212.252.116.251 - - [04/Jun/2026 19:51:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:51:59,083 [INFO] 212.252.116.251 - - [04/Jun/2026 19:51:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:52:29,097 [INFO] 212.252.116.251 - - [04/Jun/2026 19:52:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:52:59,088 [INFO] 212.252.116.251 - - [04/Jun/2026 19:52:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:53:29,102 [INFO] 212.252.116.251 - - [04/Jun/2026 19:53:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:53:59,085 [INFO] 212.252.116.251 - - [04/Jun/2026 19:53:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:54:29,417 [INFO] 212.252.116.251 - - [04/Jun/2026 19:54:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:54:59,405 [INFO] 212.252.116.251 - - [04/Jun/2026 19:54:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:55:29,422 [INFO] 212.252.116.251 - - [04/Jun/2026 19:55:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:55:59,407 [INFO] 212.252.116.251 - - [04/Jun/2026 19:55:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:56:29,422 [INFO] 212.252.116.251 - - [04/Jun/2026 19:56:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:56:59,408 [INFO] 212.252.116.251 - - [04/Jun/2026 19:56:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:57:29,425 [INFO] 212.252.116.251 - - [04/Jun/2026 19:57:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:57:59,409 [INFO] 212.252.116.251 - - [04/Jun/2026 19:57:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:58:29,423 [INFO] 212.252.116.251 - - [04/Jun/2026 19:58:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:58:59,744 [INFO] 212.252.116.251 - - [04/Jun/2026 19:58:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 19:59:30,554 [INFO] 212.252.116.251 - - [04/Jun/2026 19:59:30] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:00:00,539 [INFO] 212.252.116.251 - - [04/Jun/2026 20:00:00] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:00:31,340 [INFO] 212.252.116.251 - - [04/Jun/2026 20:00:31] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:01:01,321 [INFO] 212.252.116.251 - - [04/Jun/2026 20:01:01] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:01:31,340 [INFO] 212.252.116.251 - - [04/Jun/2026 20:01:31] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:02:01,324 [INFO] 212.252.116.251 - - [04/Jun/2026 20:02:01] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:02:32,051 [INFO] 212.252.116.251 - - [04/Jun/2026 20:02:32] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:03:02,032 [INFO] 212.252.116.251 - - [04/Jun/2026 20:03:02] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:03:32,830 [INFO] 212.252.116.251 - - [04/Jun/2026 20:03:32] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:06:28,129 [INFO] BAL Chatbot Web API starting... 2026-06-04 20:06:28,129 [INFO] Runtime pid=249899 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 20:06:28,130 [INFO] Provider: groq 2026-06-04 20:06:28,130 [INFO] HTTPS enforcement: False 2026-06-04 20:06:28,130 [INFO] Loading FAISS index... 2026-06-04 20:06:28,132 [INFO] FAISS index loaded: 107 vectors 2026-06-04 20:06:28,133 [INFO] Loading chunk metadata... 2026-06-04 20:06:28,135 [INFO] Chunk metadata loaded: 107 chunks 2026-06-04 20:06:28,135 [INFO] Testing embedding API with 3 key(s)... 2026-06-04 20:06:28,707 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:06:28,735 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 20:06:28,737 [INFO] Vector store ready — 107 chunks 2026-06-04 20:06:28,737 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 20:06:28,737 [INFO] LLM gateway ready — active provider: groq 2026-06-04 20:06:28,738 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 20:06:28,744 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 20:06:28,744 [INFO] Press CTRL+C to quit 2026-06-04 20:06:42,202 [INFO] 212.252.116.251 - - [04/Jun/2026 20:06:42] "GET / HTTP/1.1" 200 - 2026-06-04 20:06:42,423 [INFO] 212.252.116.251 - - [04/Jun/2026 20:06:42] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 20:06:42,638 [INFO] 212.252.116.251 - - [04/Jun/2026 20:06:42] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:06:42,916 [INFO] Found existing user id=27 for fingerprint 2026-06-04 20:06:43,386 [INFO] 212.252.116.251 - - [04/Jun/2026 20:06:43] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:07:12,746 [INFO] 212.252.116.251 - - [04/Jun/2026 20:07:12] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:07:42,748 [INFO] 212.252.116.251 - - [04/Jun/2026 20:07:42] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:08:12,750 [INFO] 212.252.116.251 - - [04/Jun/2026 20:08:12] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:08:42,749 [INFO] 212.252.116.251 - - [04/Jun/2026 20:08:42] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:09:10,538 [INFO] Found existing user id=27 for fingerprint 2026-06-04 20:09:12,389 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:09:12,747 [INFO] 212.252.116.251 - - [04/Jun/2026 20:09:12] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:09:12,780 [INFO] 212.252.116.251 - - [04/Jun/2026 20:09:12] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 20:09:13,474 [INFO] Found existing user id=27 for fingerprint 2026-06-04 20:09:13,936 [INFO] 212.252.116.251 - - [04/Jun/2026 20:09:13] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:09:42,748 [INFO] 212.252.116.251 - - [04/Jun/2026 20:09:42] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:10:12,761 [INFO] 212.252.116.251 - - [04/Jun/2026 20:10:12] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:10:42,826 [INFO] 212.252.116.251 - - [04/Jun/2026 20:10:42] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:11:13,893 [INFO] 212.252.116.251 - - [04/Jun/2026 20:11:13] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:11:44,713 [INFO] 212.252.116.251 - - [04/Jun/2026 20:11:44] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:12:55,616 [INFO] BAL Chatbot Web API starting... 2026-06-04 20:12:55,617 [INFO] Runtime pid=254474 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 20:12:55,617 [INFO] Provider: groq 2026-06-04 20:12:55,617 [INFO] HTTPS enforcement: False 2026-06-04 20:12:55,618 [INFO] Loading FAISS index... 2026-06-04 20:12:55,620 [INFO] FAISS index loaded: 107 vectors 2026-06-04 20:12:55,620 [INFO] Loading chunk metadata... 2026-06-04 20:12:55,623 [INFO] Chunk metadata loaded: 107 chunks 2026-06-04 20:12:55,623 [INFO] Testing embedding API with 3 key(s)... 2026-06-04 20:12:56,223 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:12:56,252 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 20:12:56,254 [INFO] Vector store ready — 107 chunks 2026-06-04 20:12:56,254 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 20:12:56,254 [INFO] LLM gateway ready — active provider: groq 2026-06-04 20:12:56,254 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 20:12:56,261 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 20:12:56,261 [INFO] Press CTRL+C to quit 2026-06-04 20:13:10,241 [INFO] 212.252.116.251 - - [04/Jun/2026 20:13:10] "GET / HTTP/1.1" 200 - 2026-06-04 20:13:10,473 [INFO] 212.252.116.251 - - [04/Jun/2026 20:13:10] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 20:13:10,487 [INFO] 212.252.116.251 - - [04/Jun/2026 20:13:10] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-04 20:13:10,743 [INFO] 212.252.116.251 - - [04/Jun/2026 20:13:10] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:13:11,170 [INFO] No existing user with fingerprint found: e8ab6fadb0777553bad05c11bec31a60 2026-06-04 20:13:11,592 [INFO] Created visitor user id=34 fingerprint=e8ab6fadb0777553bad05c11bec31a60 2026-06-04 20:13:12,096 [INFO] 212.252.116.251 - - [04/Jun/2026 20:13:12] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:13:41,687 [INFO] 212.252.116.251 - - [04/Jun/2026 20:13:41] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:14:24,049 [INFO] BAL Chatbot Web API starting... 2026-06-04 20:14:24,050 [INFO] Runtime pid=255540 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 20:14:24,050 [INFO] Provider: groq 2026-06-04 20:14:24,050 [INFO] HTTPS enforcement: False 2026-06-04 20:14:24,050 [INFO] Loading FAISS index... 2026-06-04 20:14:24,053 [INFO] FAISS index loaded: 107 vectors 2026-06-04 20:14:24,053 [INFO] Loading chunk metadata... 2026-06-04 20:14:24,056 [INFO] Chunk metadata loaded: 107 chunks 2026-06-04 20:14:24,056 [INFO] Testing embedding API with 3 key(s)... 2026-06-04 20:14:24,624 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:14:24,654 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 20:14:24,656 [INFO] Vector store ready — 107 chunks 2026-06-04 20:14:24,656 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 20:14:24,656 [INFO] LLM gateway ready — active provider: groq 2026-06-04 20:14:24,656 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 20:14:24,662 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 20:14:24,663 [INFO] Press CTRL+C to quit 2026-06-04 20:14:40,006 [INFO] 212.252.116.251 - - [04/Jun/2026 20:14:40] "GET / HTTP/1.1" 304 - 2026-06-04 20:14:40,159 [INFO] 212.252.116.251 - - [04/Jun/2026 20:14:40] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 20:14:40,163 [INFO] 212.252.116.251 - - [04/Jun/2026 20:14:40] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-04 20:14:40,361 [INFO] 212.252.116.251 - - [04/Jun/2026 20:14:40] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:14:40,674 [INFO] Found existing user id=34 for fingerprint 2026-06-04 20:14:41,136 [INFO] 212.252.116.251 - - [04/Jun/2026 20:14:41] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:14:41,620 [INFO] Found existing user id=34 for fingerprint 2026-06-04 20:14:43,362 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:14:43,778 [INFO] 212.252.116.251 - - [04/Jun/2026 20:14:43] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 20:14:44,539 [INFO] Found existing user id=34 for fingerprint 2026-06-04 20:14:44,992 [INFO] 212.252.116.251 - - [04/Jun/2026 20:14:44] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:15:27,054 [INFO] BAL Chatbot Web API starting... 2026-06-04 20:15:27,055 [INFO] Runtime pid=256254 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 20:15:27,055 [INFO] Provider: groq 2026-06-04 20:15:27,055 [INFO] HTTPS enforcement: False 2026-06-04 20:15:27,055 [INFO] Loading FAISS index... 2026-06-04 20:15:27,058 [INFO] FAISS index loaded: 107 vectors 2026-06-04 20:15:27,058 [INFO] Loading chunk metadata... 2026-06-04 20:15:27,060 [INFO] Chunk metadata loaded: 107 chunks 2026-06-04 20:15:27,060 [INFO] Testing embedding API with 3 key(s)... 2026-06-04 20:15:27,562 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:15:27,596 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 20:15:27,596 [INFO] Vector store ready — 107 chunks 2026-06-04 20:15:27,596 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 20:15:27,596 [INFO] LLM gateway ready — active provider: groq 2026-06-04 20:15:27,596 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 20:15:27,602 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 20:15:27,603 [INFO] Press CTRL+C to quit 2026-06-04 20:16:01,793 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:01] "GET /favicon.ico HTTP/1.1" 404 - 2026-06-04 20:16:01,797 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:01] "GET /apple-touch-icon.png HTTP/1.1" 404 - 2026-06-04 20:16:01,801 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:01] "GET /apple-touch-icon-precomposed.png HTTP/1.1" 404 - 2026-06-04 20:16:03,151 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:03] "GET / HTTP/1.1" 200 - 2026-06-04 20:16:03,423 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:03] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-04 20:16:03,612 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:03] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-04 20:16:03,829 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:03] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:16:04,941 [INFO] No existing user with fingerprint found: bbcb100810305989ec557da311d941b4 2026-06-04 20:16:05,212 [INFO] Created visitor user id=35 fingerprint=bbcb100810305989ec557da311d941b4 2026-06-04 20:16:05,687 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:05] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:16:10,665 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:10] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:16:12,983 [INFO] Found existing user id=35 for fingerprint 2026-06-04 20:16:14,765 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:16:15,150 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:15] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 20:16:16,093 [INFO] Found existing user id=35 for fingerprint 2026-06-04 20:16:16,566 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:16] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:16:33,835 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:33] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:16:40,540 [INFO] 212.252.116.251 - - [04/Jun/2026 20:16:40] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:17:10,541 [INFO] 212.252.116.251 - - [04/Jun/2026 20:17:10] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:17:37,356 [INFO] 198.44.142.218 - - [04/Jun/2026 20:17:37] "GET / HTTP/1.1" 200 - 2026-06-04 20:17:38,002 [INFO] 198.44.142.218 - - [04/Jun/2026 20:17:38] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-04 20:17:38,575 [INFO] 198.44.142.218 - - [04/Jun/2026 20:17:38] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-04 20:17:38,778 [INFO] 198.44.142.218 - - [04/Jun/2026 20:17:38] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:17:40,234 [INFO] Found existing user id=35 for fingerprint 2026-06-04 20:17:40,704 [INFO] 198.44.142.218 - - [04/Jun/2026 20:17:40] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:17:40,808 [INFO] 212.252.116.251 - - [04/Jun/2026 20:17:40] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:17:41,476 [INFO] Found existing user id=35 for fingerprint 2026-06-04 20:17:43,245 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:17:43,584 [INFO] 198.44.142.218 - - [04/Jun/2026 20:17:43] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 20:17:44,675 [INFO] Found existing user id=35 for fingerprint 2026-06-04 20:17:45,133 [INFO] 198.44.142.218 - - [04/Jun/2026 20:17:45] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:18:10,687 [INFO] 212.252.116.251 - - [04/Jun/2026 20:18:10] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:18:39,220 [INFO] 198.44.142.218 - - [04/Jun/2026 20:18:39] "GET / HTTP/1.1" 200 - 2026-06-04 20:18:39,808 [INFO] 198.44.142.218 - - [04/Jun/2026 20:18:39] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-04 20:18:40,422 [INFO] 198.44.142.218 - - [04/Jun/2026 20:18:40] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-04 20:18:40,619 [INFO] 198.44.142.218 - - [04/Jun/2026 20:18:40] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:18:40,690 [INFO] 212.252.116.251 - - [04/Jun/2026 20:18:40] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:18:42,345 [INFO] Found existing user id=35 for fingerprint 2026-06-04 20:18:42,804 [INFO] 198.44.142.218 - - [04/Jun/2026 20:18:42] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:18:46,389 [INFO] Found existing user id=35 for fingerprint 2026-06-04 20:18:48,115 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 20:18:48,462 [INFO] 198.44.142.218 - - [04/Jun/2026 20:18:48] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 20:18:49,679 [INFO] Found existing user id=35 for fingerprint 2026-06-04 20:18:50,137 [INFO] 198.44.142.218 - - [04/Jun/2026 20:18:50] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 20:19:10,629 [INFO] 198.44.142.218 - - [04/Jun/2026 20:19:10] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:19:10,678 [INFO] 212.252.116.251 - - [04/Jun/2026 20:19:10] "GET /api/health HTTP/1.1" 200 - 2026-06-04 20:19:40,691 [INFO] 212.252.116.251 - - [04/Jun/2026 20:19:40] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:03:58,141 [INFO] BAL Chatbot Web API starting... 2026-06-04 21:03:58,142 [INFO] Runtime pid=279574 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 21:03:58,142 [INFO] Provider: groq 2026-06-04 21:03:58,142 [INFO] HTTPS enforcement: False 2026-06-04 21:03:58,142 [INFO] Loading FAISS index... 2026-06-04 21:03:58,145 [INFO] FAISS index loaded: 107 vectors 2026-06-04 21:03:58,145 [INFO] Loading chunk metadata... 2026-06-04 21:03:58,147 [INFO] Chunk metadata loaded: 107 chunks 2026-06-04 21:03:58,148 [INFO] Testing embedding API with 3 key(s)... 2026-06-04 21:03:58,747 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:03:58,779 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 21:03:58,780 [INFO] Vector store ready — 107 chunks 2026-06-04 21:03:58,781 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 21:03:58,781 [INFO] LLM gateway ready — active provider: groq 2026-06-04 21:03:58,781 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 21:03:58,787 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 21:03:58,787 [INFO] Press CTRL+C to quit 2026-06-04 21:04:14,793 [INFO] 212.252.116.251 - - [04/Jun/2026 21:04:14] "GET / HTTP/1.1" 200 - 2026-06-04 21:04:15,045 [INFO] 212.252.116.251 - - [04/Jun/2026 21:04:15] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 21:04:15,104 [INFO] 212.252.116.251 - - [04/Jun/2026 21:04:15] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-04 21:04:15,328 [INFO] 212.252.116.251 - - [04/Jun/2026 21:04:15] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:04:15,632 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:04:16,160 [INFO] 212.252.116.251 - - [04/Jun/2026 21:04:16] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:04:21,430 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:04:23,220 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 429 Too Many Requests" 2026-06-04 21:04:23,222 [WARNING] Embedding failed with key 1: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.', 'status': 'RESOURCE_EXHAUSTED'}} 2026-06-04 21:04:23,658 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 429 Too Many Requests" 2026-06-04 21:04:23,660 [WARNING] Embedding failed with key 2: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.', 'status': 'RESOURCE_EXHAUSTED'}} 2026-06-04 21:04:24,228 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:04:24,809 [INFO] 212.252.116.251 - - [04/Jun/2026 21:04:24] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:04:25,538 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:04:26,051 [INFO] 212.252.116.251 - - [04/Jun/2026 21:04:26] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:04:46,196 [INFO] 212.252.116.251 - - [04/Jun/2026 21:04:46] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:05:16,189 [INFO] 212.252.116.251 - - [04/Jun/2026 21:05:16] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:05:46,232 [INFO] 212.252.116.251 - - [04/Jun/2026 21:05:46] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:05:51,075 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:05:53,054 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:05:53,498 [INFO] 212.252.116.251 - - [04/Jun/2026 21:05:53] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:05:54,203 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:05:54,716 [INFO] 212.252.116.251 - - [04/Jun/2026 21:05:54] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:06:12,666 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:06:14,659 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:06:15,032 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:15] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:06:15,767 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:06:16,284 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:16] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:06:16,592 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:16] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:06:25,433 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:06:27,324 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:06:27,961 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:27] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:06:28,668 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:06:29,158 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:29] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:06:33,379 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:06:35,243 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:06:35,769 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:35] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:06:36,438 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:06:36,928 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:36] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:06:46,319 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:46] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:06:53,733 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:06:55,486 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 429 Too Many Requests" 2026-06-04 21:06:55,492 [WARNING] Embedding failed with key 1: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.', 'status': 'RESOURCE_EXHAUSTED'}} 2026-06-04 21:06:56,095 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:06:56,483 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:56] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:06:57,252 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:06:57,745 [INFO] 212.252.116.251 - - [04/Jun/2026 21:06:57] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:07:05,251 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:07:07,063 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:07:07,617 [INFO] 212.252.116.251 - - [04/Jun/2026 21:07:07] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:07:08,834 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:07:09,337 [INFO] 212.252.116.251 - - [04/Jun/2026 21:07:09] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:07:16,305 [INFO] 212.252.116.251 - - [04/Jun/2026 21:07:16] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:53:51,939 [INFO] BAL Chatbot Web API starting... 2026-06-04 21:53:51,940 [INFO] Runtime pid=302928 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 21:53:51,940 [INFO] Provider: groq 2026-06-04 21:53:51,940 [INFO] HTTPS enforcement: False 2026-06-04 21:53:51,941 [INFO] Loading FAISS index... 2026-06-04 21:53:51,944 [INFO] FAISS index loaded: 137 vectors 2026-06-04 21:53:51,944 [INFO] Loading chunk metadata... 2026-06-04 21:53:51,946 [INFO] Chunk metadata loaded: 137 chunks 2026-06-04 21:53:51,946 [INFO] Testing embedding API with 5 key(s)... 2026-06-04 21:53:52,435 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:53:52,465 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 21:53:52,465 [INFO] Vector store ready — 137 chunks 2026-06-04 21:53:52,465 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 21:53:52,465 [INFO] LLM gateway ready — active provider: groq 2026-06-04 21:53:52,466 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 21:53:52,472 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 21:53:52,472 [INFO] Press CTRL+C to quit 2026-06-04 21:54:05,202 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:05] "GET / HTTP/1.1" 304 - 2026-06-04 21:54:05,691 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:05] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 21:54:05,713 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:05] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-04 21:54:06,900 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:06] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:54:07,094 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:54:08,048 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:08] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:54:15,290 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:54:17,057 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:54:17,566 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:17] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:54:18,383 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:54:18,860 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:18] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:54:24,956 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:54:26,743 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:54:26,916 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '596', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '999', 'x-ratelimit-remaining-tokens': '10602', 'x-ratelimit-reset-requests': '1m26.4s', 'x-ratelimit-reset-tokens': '6.99s', 'x-request-id': 'req_01kt9zs7j3en38x103jp5gr56m'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 757, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 21:54:26,948 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 21:54:27,089 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kt9zs7qgen4afrw1qhnk18jx'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 757, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 21:54:27,089 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 21:54:27,570 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:27] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:54:29,008 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-04 21:54:29,540 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:54:30,007 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:30] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:54:35,599 [INFO] 212.252.116.251 - - [04/Jun/2026 21:54:35] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:55:05,859 [INFO] 212.252.116.251 - - [04/Jun/2026 21:55:05] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:57:25,746 [INFO] BAL Chatbot Web API starting... 2026-06-04 21:57:25,747 [INFO] Runtime pid=304894 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 21:57:25,747 [INFO] Provider: groq 2026-06-04 21:57:25,747 [INFO] HTTPS enforcement: False 2026-06-04 21:57:25,747 [INFO] Loading FAISS index... 2026-06-04 21:57:25,750 [INFO] FAISS index loaded: 137 vectors 2026-06-04 21:57:25,751 [INFO] Loading chunk metadata... 2026-06-04 21:57:25,754 [INFO] Chunk metadata loaded: 137 chunks 2026-06-04 21:57:25,754 [INFO] Testing embedding API with 5 key(s)... 2026-06-04 21:57:26,244 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:57:26,274 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 21:57:26,275 [INFO] Vector store ready — 137 chunks 2026-06-04 21:57:26,275 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 21:57:26,275 [INFO] LLM gateway ready — active provider: groq 2026-06-04 21:57:26,275 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 21:57:26,281 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 21:57:26,282 [INFO] Press CTRL+C to quit 2026-06-04 21:57:34,583 [INFO] 212.252.116.251 - - [04/Jun/2026 21:57:34] "GET / HTTP/1.1" 304 - 2026-06-04 21:57:34,775 [INFO] 212.252.116.251 - - [04/Jun/2026 21:57:34] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 21:57:34,779 [INFO] 212.252.116.251 - - [04/Jun/2026 21:57:34] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-04 21:57:35,063 [INFO] 212.252.116.251 - - [04/Jun/2026 21:57:35] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:57:35,367 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:57:36,192 [INFO] 212.252.116.251 - - [04/Jun/2026 21:57:36] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:57:48,464 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:57:52,339 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:57:52,633 [INFO] 212.252.116.251 - - [04/Jun/2026 21:57:52] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 21:57:54,399 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:57:55,593 [INFO] 212.252.116.251 - - [04/Jun/2026 21:57:55] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 21:58:05,015 [INFO] 212.252.116.251 - - [04/Jun/2026 21:58:05] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:58:35,125 [INFO] 212.252.116.251 - - [04/Jun/2026 21:58:35] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:59:05,125 [INFO] 212.252.116.251 - - [04/Jun/2026 21:59:05] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:59:43,816 [INFO] BAL Chatbot Web API starting... 2026-06-04 21:59:43,816 [INFO] Runtime pid=306126 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 21:59:43,817 [INFO] Provider: groq 2026-06-04 21:59:43,817 [INFO] HTTPS enforcement: False 2026-06-04 21:59:43,817 [INFO] Loading FAISS index... 2026-06-04 21:59:43,820 [INFO] FAISS index loaded: 137 vectors 2026-06-04 21:59:43,820 [INFO] Loading chunk metadata... 2026-06-04 21:59:43,823 [INFO] Chunk metadata loaded: 137 chunks 2026-06-04 21:59:43,823 [INFO] Testing embedding API with 5 key(s)... 2026-06-04 21:59:44,304 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 21:59:44,334 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 21:59:44,334 [INFO] Vector store ready — 137 chunks 2026-06-04 21:59:44,334 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 21:59:44,334 [INFO] LLM gateway ready — active provider: groq 2026-06-04 21:59:44,334 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 21:59:44,341 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 21:59:44,341 [INFO] Press CTRL+C to quit 2026-06-04 21:59:58,146 [INFO] 212.252.116.251 - - [04/Jun/2026 21:59:58] "GET / HTTP/1.1" 304 - 2026-06-04 21:59:58,292 [INFO] 212.252.116.251 - - [04/Jun/2026 21:59:58] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 21:59:58,297 [INFO] 212.252.116.251 - - [04/Jun/2026 21:59:58] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-04 21:59:58,502 [INFO] 212.252.116.251 - - [04/Jun/2026 21:59:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 21:59:58,764 [INFO] Found existing user id=34 for fingerprint 2026-06-04 21:59:59,230 [INFO] 212.252.116.251 - - [04/Jun/2026 21:59:59] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 22:00:06,555 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:00:08,376 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 22:00:08,621 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '471', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta03n89f9cavty3vxqkqsc5'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:00:08,625 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 22:00:08,770 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta03ncxf9hva4mrxb54cnrs'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:00:08,772 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 22:00:09,112 [INFO] 212.252.116.251 - - [04/Jun/2026 22:00:09] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 22:00:09,950 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-04 22:00:10,484 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:00:10,946 [INFO] 212.252.116.251 - - [04/Jun/2026 22:00:10] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 22:00:25,131 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:00:26,908 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 22:00:27,085 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '947', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta04799fh98dzfy567wbyzb'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:00:27,087 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 22:00:27,229 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta047dsf98vwvfmbpdd6x0j'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:00:27,231 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 22:00:27,764 [INFO] 212.252.116.251 - - [04/Jun/2026 22:00:27] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 22:00:28,505 [INFO] 212.252.116.251 - - [04/Jun/2026 22:00:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:00:29,839 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-04 22:00:30,103 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:00:30,563 [INFO] 212.252.116.251 - - [04/Jun/2026 22:00:30] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 22:00:37,625 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:00:39,403 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 22:00:39,580 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '934', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta04kfpfs5vm43gbk7bmaaz'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:00:39,582 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 22:00:39,724 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta04km7fahrvvx5x7aw4sbw'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:00:39,725 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 22:00:39,875 [ERROR] Groq API HTTP error status=429 model=qwen/qwen3-32b rate_headers={'retry-after': '13', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '6000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '1604', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '43.96s', 'x-request-id': 'req_01kta04krsfsabr5tbzm8aqsbm'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:00:39,877 [WARNING] Groq fallback switching key_index=1 from_model=qwen/qwen3-32b to_model=meta-llama/llama-4-scout-17b-16e-instruct reason=http_429 2026-06-04 22:00:40,477 [INFO] 212.252.116.251 - - [04/Jun/2026 22:00:40] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 22:00:41,136 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=meta-llama/llama-4-scout-17b-16e-instruct 2026-06-04 22:00:41,660 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:00:42,127 [INFO] 212.252.116.251 - - [04/Jun/2026 22:00:42] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 22:00:58,608 [INFO] 212.252.116.251 - - [04/Jun/2026 22:00:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:01:21,920 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:01:23,777 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 22:01:23,937 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '2217', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta05yszeytazmxp7y6vt5nd'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:01:23,938 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 22:01:24,092 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta05yymfmw90dwy4wfyxcp2'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:01:24,093 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 22:01:24,646 [INFO] 212.252.116.251 - - [04/Jun/2026 22:01:24] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 22:01:25,747 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-04 22:01:26,274 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:01:26,736 [INFO] 212.252.116.251 - - [04/Jun/2026 22:01:26] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 22:01:28,613 [INFO] 212.252.116.251 - - [04/Jun/2026 22:01:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:01:38,522 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:01:40,276 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 22:01:40,462 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1118', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta06ey7e9majet7d1p0f3tt'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:01:40,464 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 22:01:40,609 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta06f2we9ntfrqwwf00kd8c'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 22:01:40,610 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 22:01:41,088 [INFO] 212.252.116.251 - - [04/Jun/2026 22:01:41] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 22:01:42,614 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-04 22:01:43,140 [INFO] Found existing user id=34 for fingerprint 2026-06-04 22:01:43,621 [INFO] 212.252.116.251 - - [04/Jun/2026 22:01:43] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 22:01:58,607 [INFO] 212.252.116.251 - - [04/Jun/2026 22:01:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:02:28,611 [INFO] 212.252.116.251 - - [04/Jun/2026 22:02:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:02:58,614 [INFO] 212.252.116.251 - - [04/Jun/2026 22:02:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:03:28,611 [INFO] 212.252.116.251 - - [04/Jun/2026 22:03:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:03:58,654 [INFO] 212.252.116.251 - - [04/Jun/2026 22:03:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:04:28,746 [INFO] 212.252.116.251 - - [04/Jun/2026 22:04:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:04:58,826 [INFO] 212.252.116.251 - - [04/Jun/2026 22:04:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:05:28,812 [INFO] 212.252.116.251 - - [04/Jun/2026 22:05:28] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:05:58,811 [INFO] 212.252.116.251 - - [04/Jun/2026 22:05:58] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:06:29,127 [INFO] 212.252.116.251 - - [04/Jun/2026 22:06:29] "GET /api/health HTTP/1.1" 200 - 2026-06-04 22:06:59,950 [INFO] 212.252.116.251 - - [04/Jun/2026 22:06:59] "GET /api/health HTTP/1.1" 200 - 2026-06-04 23:38:48,268 [INFO] BAL Chatbot Web API starting... 2026-06-04 23:38:48,268 [INFO] Runtime pid=349971 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-04 23:38:48,269 [INFO] Provider: groq 2026-06-04 23:38:48,269 [INFO] HTTPS enforcement: False 2026-06-04 23:38:48,269 [INFO] Loading FAISS index... 2026-06-04 23:38:48,273 [INFO] FAISS index loaded: 134 vectors 2026-06-04 23:38:48,273 [INFO] Loading chunk metadata... 2026-06-04 23:38:48,276 [INFO] Chunk metadata loaded: 134 chunks 2026-06-04 23:38:48,276 [INFO] Testing embedding API with 5 key(s)... 2026-06-04 23:38:48,751 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 23:38:48,782 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-04 23:38:48,783 [INFO] Vector store ready — 134 chunks 2026-06-04 23:38:48,783 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-04 23:38:48,783 [INFO] LLM gateway ready — active provider: groq 2026-06-04 23:38:48,783 [INFO] Server starting on http://0.0.0.0:5000 2026-06-04 23:38:48,790 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-04 23:38:48,790 [INFO] Press CTRL+C to quit 2026-06-04 23:39:16,975 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:16] "GET / HTTP/1.1" 304 - 2026-06-04 23:39:17,122 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:17] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-04 23:39:17,289 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:17] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-04 23:39:17,500 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:17] "GET /api/health HTTP/1.1" 200 - 2026-06-04 23:39:17,769 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:39:18,264 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:18] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 23:39:26,820 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:39:28,612 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 23:39:29,074 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:29] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 23:39:30,055 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:39:30,541 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:30] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 23:39:47,503 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:47] "GET /api/health HTTP/1.1" 200 - 2026-06-04 23:39:48,944 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:39:50,698 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 23:39:51,107 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:51] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 23:39:51,894 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:39:52,374 [INFO] 212.252.116.251 - - [04/Jun/2026 23:39:52] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 23:39:58,560 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:40:00,344 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 23:40:00,536 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1850', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '11362', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '3.19s', 'x-request-id': 'req_01kta5tgqmef1b01kahxa098jc'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:40:00,539 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 23:40:00,686 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta5tgwhfpgvxs49exct1tmn'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:40:00,687 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 23:40:01,092 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:01] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 23:40:03,400 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-04 23:40:03,945 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:40:04,432 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:04] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 23:40:17,819 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:17] "GET /api/health HTTP/1.1" 200 - 2026-06-04 23:40:33,020 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:40:34,829 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 23:40:35,017 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1674', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta5vjdaft7v67fj1zst95rd'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:40:35,019 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 23:40:35,174 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta5vjj9e06tj1qb4nckracz'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:40:35,176 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 23:40:35,339 [ERROR] Groq API HTTP error status=429 model=qwen/qwen3-32b rate_headers={'retry-after': '12', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '6000', 'x-ratelimit-remaining-requests': '999', 'x-ratelimit-remaining-tokens': '3551', 'x-ratelimit-reset-requests': '1m26.4s', 'x-ratelimit-reset-tokens': '24.49s', 'x-request-id': 'req_01kta5vjq7ft9b8vygzyc791tn'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:40:35,341 [WARNING] Groq fallback switching key_index=1 from_model=qwen/qwen3-32b to_model=meta-llama/llama-4-scout-17b-16e-instruct reason=http_429 2026-06-04 23:40:35,707 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:35] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 23:40:35,743 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=meta-llama/llama-4-scout-17b-16e-instruct 2026-06-04 23:40:36,286 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:40:36,766 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:36] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 23:40:44,359 [INFO] Session cleared: session_sq9evyb 2026-06-04 23:40:44,360 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:44] "POST /api/clear HTTP/1.1" 200 - 2026-06-04 23:40:45,662 [INFO] Session cleared: session_sq9evyb 2026-06-04 23:40:45,663 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:45] "POST /api/clear HTTP/1.1" 200 - 2026-06-04 23:40:47,818 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:47] "GET /api/health HTTP/1.1" 200 - 2026-06-04 23:40:49,611 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:40:51,383 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 23:40:51,566 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '784', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta5w2jhe4dvmzxk472s2hh0'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:40:51,568 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 23:40:51,716 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta5w2q5e4dtxemybs4fkzbx'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:40:51,717 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 23:40:52,108 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:52] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 23:40:53,303 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-04 23:40:53,844 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:40:54,326 [INFO] 212.252.116.251 - - [04/Jun/2026 23:40:54] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 23:41:05,520 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:41:07,287 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 23:41:07,475 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1195', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta5wj3mf11a3gn3n29r97a1'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:41:07,476 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 23:41:07,626 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta5wj8ce0nbxtan2r75xrj1'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:41:07,627 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 23:41:07,782 [ERROR] Groq API HTTP error status=429 model=qwen/qwen3-32b rate_headers={'retry-after': '18', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '6000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '1828', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '41.72s', 'x-request-id': 'req_01kta5wjd6e77a9kzvr3h7p5h2'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:41:07,784 [WARNING] Groq fallback switching key_index=1 from_model=qwen/qwen3-32b to_model=meta-llama/llama-4-scout-17b-16e-instruct reason=http_429 2026-06-04 23:41:08,181 [INFO] 212.252.116.251 - - [04/Jun/2026 23:41:08] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 23:41:08,228 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=meta-llama/llama-4-scout-17b-16e-instruct 2026-06-04 23:41:08,770 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:41:09,253 [INFO] 212.252.116.251 - - [04/Jun/2026 23:41:09] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 23:41:12,297 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:41:14,022 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-04 23:41:14,201 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1017', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kta5wrnre24ap1e17svgr24z'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:41:14,202 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-04 23:41:14,350 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kta5wrtfe25aty40as81gf8g'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:41:14,351 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-04 23:41:14,508 [ERROR] Groq API HTTP error status=429 model=qwen/qwen3-32b rate_headers={'retry-after': '9', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '6000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '2501', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '34.99s', 'x-request-id': 'req_01kta5wrzae9a9dsf4pg56cwhn'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 758, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-04 23:41:14,510 [WARNING] Groq fallback switching key_index=1 from_model=qwen/qwen3-32b to_model=meta-llama/llama-4-scout-17b-16e-instruct reason=http_429 2026-06-04 23:41:14,881 [INFO] 212.252.116.251 - - [04/Jun/2026 23:41:14] "POST /api/chat HTTP/1.1" 200 - 2026-06-04 23:41:14,917 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=meta-llama/llama-4-scout-17b-16e-instruct 2026-06-04 23:41:15,459 [INFO] Found existing user id=34 for fingerprint 2026-06-04 23:41:15,940 [INFO] 212.252.116.251 - - [04/Jun/2026 23:41:15] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-04 23:41:18,086 [INFO] 212.252.116.251 - - [04/Jun/2026 23:41:18] "GET /api/health HTTP/1.1" 200 - 2026-06-05 10:51:42,498 [INFO] BAL Chatbot Web API starting... 2026-06-05 10:51:42,524 [INFO] Runtime pid=37845 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-05 10:51:42,524 [INFO] Provider: groq 2026-06-05 10:51:42,524 [INFO] HTTPS enforcement: False 2026-06-05 10:51:42,525 [INFO] Loading FAISS index... 2026-06-05 10:51:42,544 [INFO] FAISS index loaded: 134 vectors 2026-06-05 10:51:42,544 [INFO] Loading chunk metadata... 2026-06-05 10:51:42,554 [INFO] Chunk metadata loaded: 134 chunks 2026-06-05 10:51:42,555 [INFO] Testing embedding API with 5 key(s)... 2026-06-05 10:51:43,206 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 10:51:43,238 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-05 10:51:43,238 [INFO] Vector store ready — 134 chunks 2026-06-05 10:51:43,239 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-05 10:51:43,239 [INFO] LLM gateway ready — active provider: groq 2026-06-05 10:51:43,239 [INFO] Server starting on http://0.0.0.0:5000 2026-06-05 10:51:43,263 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-05 10:51:43,263 [INFO] Press CTRL+C to quit 2026-06-05 15:23:49,631 [INFO] 77.67.129.135 - - [05/Jun/2026 15:23:49] "GET / HTTP/1.1" 200 - 2026-06-05 15:23:49,898 [INFO] 77.67.129.135 - - [05/Jun/2026 15:23:49] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-05 15:23:50,298 [INFO] 77.67.129.135 - - [05/Jun/2026 15:23:50] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-05 15:23:51,813 [INFO] 77.67.129.135 - - [05/Jun/2026 15:23:51] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:23:57,790 [INFO] No existing user with fingerprint found: 38254dc93cf3ac09ca869f0082fc2c1e 2026-06-05 15:23:58,055 [INFO] Created visitor user id=37 fingerprint=38254dc93cf3ac09ca869f0082fc2c1e 2026-06-05 15:23:58,512 [INFO] 77.67.129.135 - - [05/Jun/2026 15:23:58] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 15:24:20,501 [INFO] 77.67.129.135 - - [05/Jun/2026 15:24:20] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:24:22,168 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:24:23,878 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 15:24:24,362 [INFO] 77.67.129.135 - - [05/Jun/2026 15:24:24] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 15:24:24,975 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:24:25,418 [INFO] 77.67.129.135 - - [05/Jun/2026 15:24:25] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 15:24:51,008 [INFO] 77.67.129.135 - - [05/Jun/2026 15:24:51] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:24:58,616 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:25:00,297 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 15:25:00,805 [INFO] 77.67.129.135 - - [05/Jun/2026 15:25:00] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 15:25:01,409 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:25:01,865 [INFO] 77.67.129.135 - - [05/Jun/2026 15:25:01] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 15:25:21,332 [INFO] 77.67.129.135 - - [05/Jun/2026 15:25:21] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:25:46,201 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:25:47,859 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 15:25:48,310 [INFO] 77.67.129.135 - - [05/Jun/2026 15:25:48] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 15:25:48,932 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:25:49,375 [INFO] 77.67.129.135 - - [05/Jun/2026 15:25:49] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 15:25:51,355 [INFO] 77.67.129.135 - - [05/Jun/2026 15:25:51] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:26:21,364 [INFO] 77.67.129.135 - - [05/Jun/2026 15:26:21] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:26:51,395 [INFO] 77.67.129.135 - - [05/Jun/2026 15:26:51] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:27:21,773 [INFO] 77.67.129.135 - - [05/Jun/2026 15:27:21] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:27:51,778 [INFO] 77.67.129.135 - - [05/Jun/2026 15:27:51] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:27:52,332 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:27:54,005 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 15:27:54,441 [INFO] 77.67.129.135 - - [05/Jun/2026 15:27:54] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 15:27:55,056 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:27:55,498 [INFO] 77.67.129.135 - - [05/Jun/2026 15:27:55] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 15:28:19,574 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:28:21,233 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 15:28:21,688 [INFO] 77.67.129.135 - - [05/Jun/2026 15:28:21] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 15:28:22,250 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:28:22,358 [INFO] 77.67.129.135 - - [05/Jun/2026 15:28:22] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:28:22,702 [INFO] 77.67.129.135 - - [05/Jun/2026 15:28:22] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 15:28:52,058 [INFO] 77.67.129.135 - - [05/Jun/2026 15:28:52] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:29:22,073 [INFO] 77.67.129.135 - - [05/Jun/2026 15:29:22] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:29:51,178 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:29:52,134 [INFO] 77.67.129.135 - - [05/Jun/2026 15:29:52] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:29:52,868 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 15:29:53,243 [INFO] 77.67.129.135 - - [05/Jun/2026 15:29:53] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 15:29:53,814 [INFO] Found existing user id=37 for fingerprint 2026-06-05 15:29:54,265 [INFO] 77.67.129.135 - - [05/Jun/2026 15:29:54] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 15:30:22,135 [INFO] 77.67.129.135 - - [05/Jun/2026 15:30:22] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:30:52,119 [INFO] 77.67.129.135 - - [05/Jun/2026 15:30:52] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:32:26,436 [INFO] 77.67.129.135 - - [05/Jun/2026 15:32:26] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:32:56,118 [INFO] 77.67.129.135 - - [05/Jun/2026 15:32:56] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:33:26,145 [INFO] 77.67.129.135 - - [05/Jun/2026 15:33:26] "GET /api/health HTTP/1.1" 200 - 2026-06-05 15:42:40,719 [INFO] 77.67.129.135 - - [05/Jun/2026 15:42:40] "GET /api/health HTTP/1.1" 200 - 2026-06-05 17:00:17,601 [INFO] 212.252.116.251 - - [05/Jun/2026 17:00:17] "GET / HTTP/1.1" 200 - 2026-06-05 17:00:17,882 [INFO] 212.252.116.251 - - [05/Jun/2026 17:00:17] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-05 17:00:17,916 [INFO] 212.252.116.251 - - [05/Jun/2026 17:00:17] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-05 17:00:19,334 [INFO] 212.252.116.251 - - [05/Jun/2026 17:00:19] "GET /api/health HTTP/1.1" 200 - 2026-06-05 17:00:19,474 [INFO] No existing user with fingerprint found: 0c921994f31b2d951d6f3ec64cee0c0a 2026-06-05 17:00:20,027 [INFO] Created visitor user id=38 fingerprint=0c921994f31b2d951d6f3ec64cee0c0a 2026-06-05 17:00:20,511 [INFO] 212.252.116.251 - - [05/Jun/2026 17:00:20] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 17:00:22,492 [INFO] Found existing user id=38 for fingerprint 2026-06-05 17:00:24,288 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 17:00:25,346 [INFO] 212.252.116.251 - - [05/Jun/2026 17:00:25] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 17:00:26,149 [INFO] Found existing user id=38 for fingerprint 2026-06-05 17:00:26,623 [INFO] 212.252.116.251 - - [05/Jun/2026 17:00:26] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 17:57:04,954 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:04] "GET / HTTP/1.1" 304 - 2026-06-05 17:57:05,126 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:05] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-05 17:57:05,131 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:05] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-05 17:57:06,532 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:06] "GET /api/health HTTP/1.1" 200 - 2026-06-05 17:57:06,550 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:57:07,032 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:07] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 17:57:16,143 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:57:18,015 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 17:57:18,451 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:18] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 17:57:19,040 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:57:19,514 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:19] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 17:57:33,512 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:57:35,344 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 17:57:35,740 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:35] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 17:57:35,967 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:35] "GET /api/health HTTP/1.1" 200 - 2026-06-05 17:57:36,547 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:57:37,022 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:37] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 17:57:45,756 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:57:47,554 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 17:57:47,885 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:47] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 17:57:48,555 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:57:49,030 [INFO] 212.252.116.251 - - [05/Jun/2026 17:57:49] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 17:58:02,053 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:58:03,891 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 17:58:04,289 [INFO] 212.252.116.251 - - [05/Jun/2026 17:58:04] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 17:58:04,931 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:58:05,406 [INFO] 212.252.116.251 - - [05/Jun/2026 17:58:05] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 17:58:06,031 [INFO] 212.252.116.251 - - [05/Jun/2026 17:58:06] "GET /api/health HTTP/1.1" 200 - 2026-06-05 17:58:17,371 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:58:19,155 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 17:58:19,548 [INFO] 212.252.116.251 - - [05/Jun/2026 17:58:19] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 17:58:20,195 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:58:20,672 [INFO] 212.252.116.251 - - [05/Jun/2026 17:58:20] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 17:58:36,427 [INFO] 212.252.116.251 - - [05/Jun/2026 17:58:36] "GET /api/health HTTP/1.1" 200 - 2026-06-05 17:59:06,425 [INFO] 212.252.116.251 - - [05/Jun/2026 17:59:06] "GET /api/health HTTP/1.1" 200 - 2026-06-05 17:59:36,431 [INFO] 212.252.116.251 - - [05/Jun/2026 17:59:36] "GET /api/health HTTP/1.1" 200 - 2026-06-05 17:59:54,465 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:59:56,317 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 17:59:56,714 [INFO] 212.252.116.251 - - [05/Jun/2026 17:59:56] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 17:59:57,586 [INFO] Found existing user id=34 for fingerprint 2026-06-05 17:59:58,062 [INFO] 212.252.116.251 - - [05/Jun/2026 17:59:58] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:00:06,524 [INFO] 212.252.116.251 - - [05/Jun/2026 18:00:06] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:00:12,418 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:00:14,190 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:00:17,274 [INFO] 212.252.116.251 - - [05/Jun/2026 18:00:17] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:00:17,863 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:00:18,337 [INFO] 212.252.116.251 - - [05/Jun/2026 18:00:18] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:00:37,150 [INFO] 212.252.116.251 - - [05/Jun/2026 18:00:37] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:01:07,709 [INFO] 212.252.116.251 - - [05/Jun/2026 18:01:07] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:01:37,902 [INFO] 212.252.116.251 - - [05/Jun/2026 18:01:37] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:02:08,436 [INFO] 212.252.116.251 - - [05/Jun/2026 18:02:08] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:02:38,423 [INFO] 212.252.116.251 - - [05/Jun/2026 18:02:38] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:03:09,204 [INFO] 212.252.116.251 - - [05/Jun/2026 18:03:09] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:03:39,205 [INFO] 212.252.116.251 - - [05/Jun/2026 18:03:39] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:04:09,982 [INFO] 212.252.116.251 - - [05/Jun/2026 18:04:09] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:04:40,199 [INFO] 212.252.116.251 - - [05/Jun/2026 18:04:40] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:05:10,960 [INFO] 212.252.116.251 - - [05/Jun/2026 18:05:10] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:05:37,449 [INFO] BAL Chatbot Web API starting... 2026-06-05 18:05:37,450 [INFO] Runtime pid=95368 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-05 18:05:37,450 [INFO] Provider: groq 2026-06-05 18:05:37,450 [INFO] HTTPS enforcement: False 2026-06-05 18:05:37,451 [INFO] Loading FAISS index... 2026-06-05 18:05:37,453 [INFO] FAISS index loaded: 134 vectors 2026-06-05 18:05:37,453 [INFO] Loading chunk metadata... 2026-06-05 18:05:37,456 [INFO] Chunk metadata loaded: 134 chunks 2026-06-05 18:05:37,456 [INFO] Testing embedding API with 5 key(s)... 2026-06-05 18:05:38,004 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:05:38,029 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-05 18:05:38,029 [INFO] Vector store ready — 134 chunks 2026-06-05 18:05:38,029 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-05 18:05:38,029 [INFO] LLM gateway ready — active provider: groq 2026-06-05 18:05:38,029 [INFO] Server starting on http://0.0.0.0:5000 2026-06-05 18:05:38,031 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-05 18:05:38,031 [INFO] Press CTRL+C to quit 2026-06-05 18:06:01,616 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:01] "GET / HTTP/1.1" 304 - 2026-06-05 18:06:01,750 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:01] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-05 18:06:01,755 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:01] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-05 18:06:01,965 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:01] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:06:02,250 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:02,739 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:02] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:06:10,882 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:12,666 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:06:13,591 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:13] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:06:14,161 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:14,642 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:14] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:06:20,102 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:21,912 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:06:22,299 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:22] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:06:23,008 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:23,489 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:23] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:06:32,087 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:32] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:06:34,265 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:36,139 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:06:36,702 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:36] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:06:37,294 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:37,780 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:37] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:06:47,032 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:48,877 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:06:49,330 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:49] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:06:50,759 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:06:51,239 [INFO] 212.252.116.251 - - [05/Jun/2026 18:06:51] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:07:02,093 [INFO] 212.252.116.251 - - [05/Jun/2026 18:07:02] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:07:13,221 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:07:15,096 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:07:15,527 [INFO] 212.252.116.251 - - [05/Jun/2026 18:07:15] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:07:16,223 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:07:16,702 [INFO] 212.252.116.251 - - [05/Jun/2026 18:07:16] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:07:32,099 [INFO] 212.252.116.251 - - [05/Jun/2026 18:07:32] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:07:38,928 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:07:40,816 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:07:41,223 [INFO] 212.252.116.251 - - [05/Jun/2026 18:07:41] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:07:42,676 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:07:43,158 [INFO] 212.252.116.251 - - [05/Jun/2026 18:07:43] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:08:00,713 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:08:02,426 [INFO] 212.252.116.251 - - [05/Jun/2026 18:08:02] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:08:02,537 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:08:03,308 [INFO] 212.252.116.251 - - [05/Jun/2026 18:08:03] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:08:03,893 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:08:04,379 [INFO] 212.252.116.251 - - [05/Jun/2026 18:08:04] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:08:17,451 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:08:19,219 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 429 Too Many Requests" 2026-06-05 18:08:19,221 [WARNING] Embedding failed with key 1: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.', 'status': 'RESOURCE_EXHAUSTED'}} 2026-06-05 18:08:19,753 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:08:20,135 [INFO] 212.252.116.251 - - [05/Jun/2026 18:08:20] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:08:21,483 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:08:21,975 [INFO] 212.252.116.251 - - [05/Jun/2026 18:08:21] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:08:32,127 [INFO] 212.252.116.251 - - [05/Jun/2026 18:08:32] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:08:38,229 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:08:39,950 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 429 Too Many Requests" 2026-06-05 18:08:39,952 [WARNING] Embedding failed with key 1: 429 RESOURCE_EXHAUSTED. {'error': {'code': 429, 'message': 'Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.', 'status': 'RESOURCE_EXHAUSTED'}} 2026-06-05 18:08:40,589 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:08:41,094 [INFO] 212.252.116.251 - - [05/Jun/2026 18:08:41] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:08:41,668 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:08:42,152 [INFO] 212.252.116.251 - - [05/Jun/2026 18:08:42] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:09:02,603 [INFO] 212.252.116.251 - - [05/Jun/2026 18:09:02] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:09:32,603 [INFO] 212.252.116.251 - - [05/Jun/2026 18:09:32] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:10:02,602 [INFO] 212.252.116.251 - - [05/Jun/2026 18:10:02] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:10:32,734 [INFO] 212.252.116.251 - - [05/Jun/2026 18:10:32] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:10:50,430 [INFO] BAL Chatbot Web API starting... 2026-06-05 18:10:50,430 [INFO] Runtime pid=97940 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-05 18:10:50,431 [INFO] Provider: groq 2026-06-05 18:10:50,431 [INFO] HTTPS enforcement: False 2026-06-05 18:10:50,431 [INFO] Loading FAISS index... 2026-06-05 18:10:50,434 [INFO] FAISS index loaded: 134 vectors 2026-06-05 18:10:50,434 [INFO] Loading chunk metadata... 2026-06-05 18:10:50,437 [INFO] Chunk metadata loaded: 134 chunks 2026-06-05 18:10:50,437 [INFO] Testing embedding API with 5 key(s)... 2026-06-05 18:10:51,054 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:10:51,084 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-05 18:10:51,085 [INFO] Vector store ready — 134 chunks 2026-06-05 18:10:51,085 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-05 18:10:51,085 [INFO] LLM gateway ready — active provider: groq 2026-06-05 18:10:51,085 [INFO] Server starting on http://0.0.0.0:5000 2026-06-05 18:10:51,091 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-05 18:10:51,091 [INFO] Press CTRL+C to quit 2026-06-05 18:11:02,886 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:02] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:11:06,272 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:06] "GET / HTTP/1.1" 304 - 2026-06-05 18:11:06,471 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:06] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-05 18:11:06,525 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:06] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-05 18:11:06,673 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:06] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:11:07,013 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:11:07,476 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:07] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:11:36,861 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:36] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:11:52,692 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:11:54,459 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:11:55,185 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:55] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:11:55,758 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:11:56,212 [INFO] 212.252.116.251 - - [05/Jun/2026 18:11:56] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:12:06,860 [INFO] 212.252.116.251 - - [05/Jun/2026 18:12:06] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:12:36,853 [INFO] 212.252.116.251 - - [05/Jun/2026 18:12:36] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:13:06,855 [INFO] 212.252.116.251 - - [05/Jun/2026 18:13:06] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:13:21,963 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:13:23,817 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:13:24,222 [INFO] 212.252.116.251 - - [05/Jun/2026 18:13:24] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:13:24,759 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:13:25,212 [INFO] 212.252.116.251 - - [05/Jun/2026 18:13:25] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:13:35,446 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:13:36,899 [INFO] 212.252.116.251 - - [05/Jun/2026 18:13:36] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:13:37,237 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:13:37,409 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '676', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '990', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '14m24s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ktc5hkjsfa3te2s71p03fh4x'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:13:37,430 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-05 18:13:37,576 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ktc5hkqyfeavp59g0ezvg4rp'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:13:37,578 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-05 18:13:38,043 [INFO] 212.252.116.251 - - [05/Jun/2026 18:13:38] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:13:39,507 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-05 18:13:40,036 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:13:40,490 [INFO] 212.252.116.251 - - [05/Jun/2026 18:13:40] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:14:06,894 [INFO] 212.252.116.251 - - [05/Jun/2026 18:14:06] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:14:21,071 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:14:22,864 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:14:23,040 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '335', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '990', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '14m24s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ktc5k04pfs29z8862352429h'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:14:23,042 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-05 18:14:23,179 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ktc5k096fjgvf2xts8nmknyq'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:14:23,181 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-05 18:14:24,214 [INFO] 212.252.116.251 - - [05/Jun/2026 18:14:24] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:14:25,901 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-05 18:14:26,457 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:14:26,911 [INFO] 212.252.116.251 - - [05/Jun/2026 18:14:26] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:14:36,905 [INFO] 212.252.116.251 - - [05/Jun/2026 18:14:36] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:14:43,734 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:14:45,481 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:14:45,686 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1953', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '990', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '14m24s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ktc5kp8dfpmshy4vv05gdcnb'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:14:45,688 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-05 18:14:45,847 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ktc5kpdhe7ctpwb1rctj2x5h'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:14:45,848 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-05 18:14:46,010 [ERROR] Groq API HTTP error status=429 model=qwen/qwen3-32b rate_headers={'retry-after': '1', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '6000', 'x-ratelimit-remaining-requests': '998', 'x-ratelimit-remaining-tokens': '5340', 'x-ratelimit-reset-requests': '2m52.8s', 'x-ratelimit-reset-tokens': '6.6s', 'x-request-id': 'req_01ktc5kpjbfxp8rrpkw2vrknze'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:14:46,011 [WARNING] Groq fallback switching key_index=1 from_model=qwen/qwen3-32b to_model=meta-llama/llama-4-scout-17b-16e-instruct reason=http_429 2026-06-05 18:14:46,970 [INFO] 212.252.116.251 - - [05/Jun/2026 18:14:46] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:14:47,078 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=meta-llama/llama-4-scout-17b-16e-instruct 2026-06-05 18:14:47,604 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:14:48,059 [INFO] 212.252.116.251 - - [05/Jun/2026 18:14:48] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:15:07,094 [INFO] 212.252.116.251 - - [05/Jun/2026 18:15:07] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:15:19,049 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:15:20,810 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:15:20,996 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1824', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '991', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '12m57.599s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ktc5mrqxfyba8dpfpj7b1t50'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:15:20,998 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-05 18:15:21,151 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ktc5mrwsfynb1qa449nk3mjw'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:15:21,152 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-05 18:15:21,768 [INFO] 212.252.116.251 - - [05/Jun/2026 18:15:21] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:15:23,099 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-05 18:15:23,620 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:15:24,077 [INFO] 212.252.116.251 - - [05/Jun/2026 18:15:24] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:15:37,098 [INFO] 212.252.116.251 - - [05/Jun/2026 18:15:37] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:15:46,178 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:15:47,901 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:15:48,090 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1702', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '991', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '12m57.599s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ktc5nk6pek6v1wfetzjt7k1c'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:15:48,091 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-05 18:15:48,226 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ktc5nkaweakrhar6w3bzx1b1'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:15:48,227 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-05 18:15:48,384 [ERROR] Groq API HTTP error status=429 model=qwen/qwen3-32b rate_headers={'retry-after': '24', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '6000', 'x-ratelimit-remaining-requests': '997', 'x-ratelimit-remaining-tokens': '2803', 'x-ratelimit-reset-requests': '4m19.2s', 'x-ratelimit-reset-tokens': '31.97s', 'x-request-id': 'req_01ktc5nkfnevwtg0s1zex315k1'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:15:48,386 [WARNING] Groq fallback switching key_index=1 from_model=qwen/qwen3-32b to_model=meta-llama/llama-4-scout-17b-16e-instruct reason=http_429 2026-06-05 18:15:49,182 [INFO] 212.252.116.251 - - [05/Jun/2026 18:15:49] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:15:49,242 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=meta-llama/llama-4-scout-17b-16e-instruct 2026-06-05 18:15:49,779 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:15:50,237 [INFO] 212.252.116.251 - - [05/Jun/2026 18:15:50] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:16:04,411 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:16:06,141 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-05 18:16:06,319 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '353', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '991', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '12m57.599s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01ktc5p506ererz9vxqmk09t6p'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:16:06,321 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-05 18:16:06,464 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01ktc5p54verhtxdve53h8yknr'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 744, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-05 18:16:06,465 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-05 18:16:07,150 [INFO] 212.252.116.251 - - [05/Jun/2026 18:16:07] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:16:08,070 [INFO] 212.252.116.251 - - [05/Jun/2026 18:16:08] "POST /api/chat HTTP/1.1" 200 - 2026-06-05 18:16:09,784 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-05 18:16:10,303 [INFO] Found existing user id=34 for fingerprint 2026-06-05 18:16:10,760 [INFO] 212.252.116.251 - - [05/Jun/2026 18:16:10] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-05 18:16:37,386 [INFO] 212.252.116.251 - - [05/Jun/2026 18:16:37] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:17:07,388 [INFO] 212.252.116.251 - - [05/Jun/2026 18:17:07] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:17:37,391 [INFO] 212.252.116.251 - - [05/Jun/2026 18:17:37] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:18:07,384 [INFO] 212.252.116.251 - - [05/Jun/2026 18:18:07] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:18:37,696 [INFO] 212.252.116.251 - - [05/Jun/2026 18:18:37] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:19:07,719 [INFO] 212.252.116.251 - - [05/Jun/2026 18:19:07] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:19:37,695 [INFO] 212.252.116.251 - - [05/Jun/2026 18:19:37] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:20:07,701 [INFO] 212.252.116.251 - - [05/Jun/2026 18:20:07] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:20:37,936 [INFO] 212.252.116.251 - - [05/Jun/2026 18:20:37] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:21:08,773 [INFO] 212.252.116.251 - - [05/Jun/2026 18:21:08] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:21:39,087 [INFO] 212.252.116.251 - - [05/Jun/2026 18:21:39] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:22:09,836 [INFO] 212.252.116.251 - - [05/Jun/2026 18:22:09] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:22:40,153 [INFO] 212.252.116.251 - - [05/Jun/2026 18:22:40] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:23:10,321 [INFO] 212.252.116.251 - - [05/Jun/2026 18:23:10] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:23:40,461 [INFO] 212.252.116.251 - - [05/Jun/2026 18:23:40] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:24:10,719 [INFO] 212.252.116.251 - - [05/Jun/2026 18:24:10] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:24:41,044 [INFO] 212.252.116.251 - - [05/Jun/2026 18:24:41] "GET /api/health HTTP/1.1" 200 - 2026-06-05 18:25:11,837 [INFO] 212.252.116.251 - - [05/Jun/2026 18:25:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:34:09,597 [INFO] BAL Chatbot Web API starting... 2026-06-07 11:34:09,680 [INFO] Runtime pid=50296 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 11:34:09,680 [INFO] Provider: groq 2026-06-07 11:34:09,680 [INFO] HTTPS enforcement: False 2026-06-07 11:34:09,680 [INFO] Loading FAISS index... 2026-06-07 11:34:09,708 [INFO] FAISS index loaded: 134 vectors 2026-06-07 11:34:09,708 [INFO] Loading chunk metadata... 2026-06-07 11:34:09,711 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 11:34:09,711 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 11:34:10,331 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:34:10,361 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 11:34:10,363 [INFO] Vector store ready — 134 chunks 2026-06-07 11:34:10,363 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 11:34:10,364 [INFO] LLM gateway ready — active provider: groq 2026-06-07 11:34:10,364 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 11:34:10,385 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 11:34:10,385 [INFO] Press CTRL+C to quit 2026-06-07 11:35:37,641 [INFO] 212.252.116.251 - - [07/Jun/2026 11:35:37] "GET / HTTP/1.1" 304 - 2026-06-07 11:35:37,868 [INFO] 212.252.116.251 - - [07/Jun/2026 11:35:37] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 11:35:38,004 [INFO] 212.252.116.251 - - [07/Jun/2026 11:35:38] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 11:35:38,239 [INFO] 212.252.116.251 - - [07/Jun/2026 11:35:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:35:38,541 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:35:39,052 [INFO] 212.252.116.251 - - [07/Jun/2026 11:35:39] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:35:49,799 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:35:51,627 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:35:52,035 [INFO] 212.252.116.251 - - [07/Jun/2026 11:35:52] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:35:52,844 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:35:53,342 [INFO] 212.252.116.251 - - [07/Jun/2026 11:35:53] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:36:08,195 [INFO] 212.252.116.251 - - [07/Jun/2026 11:36:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:36:16,373 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:36:18,242 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:36:18,619 [INFO] 212.252.116.251 - - [07/Jun/2026 11:36:18] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:36:19,460 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:36:19,957 [INFO] 212.252.116.251 - - [07/Jun/2026 11:36:19] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:36:38,206 [INFO] 212.252.116.251 - - [07/Jun/2026 11:36:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:37:08,207 [INFO] 212.252.116.251 - - [07/Jun/2026 11:37:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:37:38,486 [INFO] 212.252.116.251 - - [07/Jun/2026 11:37:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:38:08,486 [INFO] 212.252.116.251 - - [07/Jun/2026 11:38:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:38:38,486 [INFO] 212.252.116.251 - - [07/Jun/2026 11:38:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:38:53,854 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:38:55,657 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:38:56,016 [INFO] 212.252.116.251 - - [07/Jun/2026 11:38:56] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:38:56,928 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:38:57,427 [INFO] 212.252.116.251 - - [07/Jun/2026 11:38:57] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:39:08,487 [INFO] 212.252.116.251 - - [07/Jun/2026 11:39:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:39:15,864 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:39:17,653 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:39:18,076 [INFO] 212.252.116.251 - - [07/Jun/2026 11:39:18] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:39:19,747 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:39:20,244 [INFO] 212.252.116.251 - - [07/Jun/2026 11:39:20] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:39:38,549 [INFO] 212.252.116.251 - - [07/Jun/2026 11:39:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:40:08,550 [INFO] 212.252.116.251 - - [07/Jun/2026 11:40:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:40:38,556 [INFO] 212.252.116.251 - - [07/Jun/2026 11:40:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:41:08,554 [INFO] 212.252.116.251 - - [07/Jun/2026 11:41:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:41:29,171 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:41:31,079 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:41:31,593 [INFO] 212.252.116.251 - - [07/Jun/2026 11:41:31] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:41:32,271 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:41:32,769 [INFO] 212.252.116.251 - - [07/Jun/2026 11:41:32] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:41:38,553 [INFO] 212.252.116.251 - - [07/Jun/2026 11:41:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:41:40,125 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:41:41,995 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:41:42,335 [INFO] 212.252.116.251 - - [07/Jun/2026 11:41:42] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:41:43,549 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:41:44,047 [INFO] 212.252.116.251 - - [07/Jun/2026 11:41:44] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:42:04,418 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:42:06,416 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:42:06,871 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:06] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:42:07,523 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:42:08,020 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:08] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:42:08,552 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:42:20,419 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:42:22,331 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:42:22,884 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:22] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:42:24,127 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:42:24,624 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:24] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:42:34,575 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:42:36,467 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:42:36,887 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:36] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:42:38,068 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:42:38,563 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:38] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:42:39,240 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:39] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:42:45,715 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:42:47,451 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:42:47,862 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:47] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:42:48,717 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:42:49,187 [INFO] 212.252.116.251 - - [07/Jun/2026 11:42:49] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:42:58,627 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:43:00,365 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:43:00,824 [INFO] 212.252.116.251 - - [07/Jun/2026 11:43:00] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:43:01,535 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:43:02,009 [INFO] 212.252.116.251 - - [07/Jun/2026 11:43:02] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:43:08,668 [INFO] 212.252.116.251 - - [07/Jun/2026 11:43:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:43:38,648 [INFO] 212.252.116.251 - - [07/Jun/2026 11:43:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:44:08,672 [INFO] 212.252.116.251 - - [07/Jun/2026 11:44:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:44:38,650 [INFO] 212.252.116.251 - - [07/Jun/2026 11:44:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:45:08,672 [INFO] 212.252.116.251 - - [07/Jun/2026 11:45:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:45:38,650 [INFO] 212.252.116.251 - - [07/Jun/2026 11:45:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:46:08,673 [INFO] 212.252.116.251 - - [07/Jun/2026 11:46:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:46:34,039 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:46:35,821 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:46:36,378 [INFO] 212.252.116.251 - - [07/Jun/2026 11:46:36] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:46:36,979 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:46:37,456 [INFO] 212.252.116.251 - - [07/Jun/2026 11:46:37] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:46:38,885 [INFO] 212.252.116.251 - - [07/Jun/2026 11:46:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:46:48,256 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:46:49,970 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:46:50,397 [INFO] 212.252.116.251 - - [07/Jun/2026 11:46:50] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:46:50,950 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:46:51,418 [INFO] 212.252.116.251 - - [07/Jun/2026 11:46:51] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:47:08,915 [INFO] 212.252.116.251 - - [07/Jun/2026 11:47:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:47:38,886 [INFO] 212.252.116.251 - - [07/Jun/2026 11:47:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:47:50,179 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:47:51,926 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:47:52,610 [INFO] 212.252.116.251 - - [07/Jun/2026 11:47:52] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:47:53,181 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:47:53,653 [INFO] 212.252.116.251 - - [07/Jun/2026 11:47:53] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:48:15,257 [INFO] BAL Chatbot Web API starting... 2026-06-07 11:48:15,257 [INFO] Runtime pid=58371 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 11:48:15,258 [INFO] Provider: groq 2026-06-07 11:48:15,258 [INFO] HTTPS enforcement: False 2026-06-07 11:48:15,258 [INFO] Loading FAISS index... 2026-06-07 11:48:15,261 [INFO] FAISS index loaded: 134 vectors 2026-06-07 11:48:15,261 [INFO] Loading chunk metadata... 2026-06-07 11:48:15,264 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 11:48:15,264 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 11:48:15,763 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:48:15,797 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 11:48:15,797 [INFO] Vector store ready — 134 chunks 2026-06-07 11:48:15,797 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 11:48:15,797 [INFO] LLM gateway ready — active provider: groq 2026-06-07 11:48:15,797 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 11:48:15,803 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 11:48:15,803 [INFO] Press CTRL+C to quit 2026-06-07 11:48:29,906 [INFO] 212.252.116.251 - - [07/Jun/2026 11:48:29] "GET / HTTP/1.1" 304 - 2026-06-07 11:48:30,060 [INFO] 212.252.116.251 - - [07/Jun/2026 11:48:30] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 11:48:30,090 [INFO] 212.252.116.251 - - [07/Jun/2026 11:48:30] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 11:48:30,313 [INFO] 212.252.116.251 - - [07/Jun/2026 11:48:30] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:48:30,540 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:48:31,016 [INFO] 212.252.116.251 - - [07/Jun/2026 11:48:31] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:48:38,975 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:48:40,726 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:48:41,104 [INFO] 212.252.116.251 - - [07/Jun/2026 11:48:41] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:48:41,693 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:48:42,162 [INFO] 212.252.116.251 - - [07/Jun/2026 11:48:42] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:48:58,064 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:48:59,903 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:49:00,294 [INFO] 212.252.116.251 - - [07/Jun/2026 11:49:00] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:49:00,298 [INFO] 212.252.116.251 - - [07/Jun/2026 11:49:00] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:49:00,851 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:49:01,321 [INFO] 212.252.116.251 - - [07/Jun/2026 11:49:01] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:49:05,636 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:49:07,386 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:49:07,721 [INFO] 212.252.116.251 - - [07/Jun/2026 11:49:07] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:49:08,525 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:49:08,996 [INFO] 212.252.116.251 - - [07/Jun/2026 11:49:08] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:50:13,937 [INFO] BAL Chatbot Web API starting... 2026-06-07 11:50:13,937 [INFO] Runtime pid=59426 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 11:50:13,938 [INFO] Provider: groq 2026-06-07 11:50:13,938 [INFO] HTTPS enforcement: False 2026-06-07 11:50:13,938 [INFO] Loading FAISS index... 2026-06-07 11:50:13,941 [INFO] FAISS index loaded: 134 vectors 2026-06-07 11:50:13,941 [INFO] Loading chunk metadata... 2026-06-07 11:50:13,943 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 11:50:13,944 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 11:50:14,591 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:50:14,626 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 11:50:14,626 [INFO] Vector store ready — 134 chunks 2026-06-07 11:50:14,627 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 11:50:14,627 [INFO] LLM gateway ready — active provider: groq 2026-06-07 11:50:14,627 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 11:50:14,633 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 11:50:14,633 [INFO] Press CTRL+C to quit 2026-06-07 11:50:27,168 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:27] "GET / HTTP/1.1" 304 - 2026-06-07 11:50:27,304 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:27] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 11:50:27,310 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:27] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 11:50:27,511 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:27] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:50:27,782 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:50:28,250 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:28] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:50:40,704 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:50:42,439 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:50:42,774 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:42] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:50:43,325 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:50:43,786 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:43] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:50:49,678 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:50:51,424 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:50:51,740 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:51] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:50:52,270 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:50:52,730 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:52] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:50:57,672 [INFO] 212.252.116.251 - - [07/Jun/2026 11:50:57] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:51:05,775 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:51:07,511 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:51:08,110 [INFO] 212.252.116.251 - - [07/Jun/2026 11:51:08] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:51:08,676 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:51:09,139 [INFO] 212.252.116.251 - - [07/Jun/2026 11:51:09] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:51:20,254 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:51:22,031 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:51:22,594 [INFO] 212.252.116.251 - - [07/Jun/2026 11:51:22] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:51:24,512 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:51:24,972 [INFO] 212.252.116.251 - - [07/Jun/2026 11:51:24] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:51:27,730 [INFO] 212.252.116.251 - - [07/Jun/2026 11:51:27] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:51:56,444 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:51:58,083 [INFO] 212.252.116.251 - - [07/Jun/2026 11:51:58] "GET /api/health HTTP/1.1" 200 - 2026-06-07 11:51:58,183 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:51:58,652 [INFO] 212.252.116.251 - - [07/Jun/2026 11:51:58] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:51:59,182 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:51:59,643 [INFO] 212.252.116.251 - - [07/Jun/2026 11:51:59] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 11:52:03,579 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:52:05,353 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 11:52:05,674 [INFO] 212.252.116.251 - - [07/Jun/2026 11:52:05] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 11:52:06,225 [INFO] Found existing user id=34 for fingerprint 2026-06-07 11:52:06,684 [INFO] 212.252.116.251 - - [07/Jun/2026 11:52:06] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:10:15,689 [INFO] 212.252.116.251 - - [07/Jun/2026 12:10:15] "GET / HTTP/1.1" 304 - 2026-06-07 12:10:15,843 [INFO] 212.252.116.251 - - [07/Jun/2026 12:10:15] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 12:10:15,892 [INFO] 212.252.116.251 - - [07/Jun/2026 12:10:15] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 12:10:17,279 [INFO] 212.252.116.251 - - [07/Jun/2026 12:10:17] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:10:17,281 [INFO] Found existing user id=34 for fingerprint 2026-06-07 12:10:17,751 [INFO] 212.252.116.251 - - [07/Jun/2026 12:10:17] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:10:46,152 [INFO] 212.252.116.251 - - [07/Jun/2026 12:10:46] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:16:32,563 [INFO] BAL Chatbot Web API starting... 2026-06-07 12:16:32,564 [INFO] Runtime pid=72368 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 12:16:32,564 [INFO] Provider: groq 2026-06-07 12:16:32,564 [INFO] HTTPS enforcement: False 2026-06-07 12:16:32,564 [INFO] Loading FAISS index... 2026-06-07 12:16:32,567 [INFO] FAISS index loaded: 134 vectors 2026-06-07 12:16:32,567 [INFO] Loading chunk metadata... 2026-06-07 12:16:32,569 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 12:16:32,569 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 12:16:33,081 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:16:33,108 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 12:16:33,110 [INFO] Vector store ready — 134 chunks 2026-06-07 12:16:33,110 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 12:16:33,110 [INFO] LLM gateway ready — active provider: groq 2026-06-07 12:16:33,111 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 12:16:33,117 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 12:16:33,117 [INFO] Press CTRL+C to quit 2026-06-07 12:16:41,254 [INFO] 212.252.116.251 - - [07/Jun/2026 12:16:41] "GET / HTTP/1.1" 200 - 2026-06-07 12:16:41,467 [INFO] 212.252.116.251 - - [07/Jun/2026 12:16:41] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 12:16:41,475 [INFO] 212.252.116.251 - - [07/Jun/2026 12:16:41] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 12:16:41,694 [INFO] 212.252.116.251 - - [07/Jun/2026 12:16:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:16:41,998 [INFO] Found existing user id=34 for fingerprint 2026-06-07 12:16:42,518 [INFO] 212.252.116.251 - - [07/Jun/2026 12:16:42] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:17:11,855 [INFO] 212.252.116.251 - - [07/Jun/2026 12:17:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:17:30,081 [INFO] 212.252.116.251 - - [07/Jun/2026 12:17:30] "GET / HTTP/1.1" 200 - 2026-06-07 12:17:30,336 [INFO] 212.252.116.251 - - [07/Jun/2026 12:17:30] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-07 12:17:30,552 [INFO] 212.252.116.251 - - [07/Jun/2026 12:17:30] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-07 12:17:30,774 [INFO] 212.252.116.251 - - [07/Jun/2026 12:17:30] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:17:31,551 [INFO] Found existing user id=35 for fingerprint 2026-06-07 12:17:32,047 [INFO] 212.252.116.251 - - [07/Jun/2026 12:17:32] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:17:41,858 [INFO] 212.252.116.251 - - [07/Jun/2026 12:17:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:29:41,237 [INFO] BAL Chatbot Web API starting... 2026-06-07 12:29:41,237 [INFO] Runtime pid=81649 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 12:29:41,238 [INFO] Provider: groq 2026-06-07 12:29:41,238 [INFO] HTTPS enforcement: False 2026-06-07 12:29:41,238 [INFO] Loading FAISS index... 2026-06-07 12:29:41,241 [INFO] FAISS index loaded: 134 vectors 2026-06-07 12:29:41,241 [INFO] Loading chunk metadata... 2026-06-07 12:29:41,244 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 12:29:41,245 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 12:29:41,742 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:29:41,770 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 12:29:41,772 [INFO] Vector store ready — 134 chunks 2026-06-07 12:29:41,772 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 12:29:41,772 [INFO] LLM gateway ready — active provider: groq 2026-06-07 12:29:41,772 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 12:29:41,778 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 12:29:41,778 [INFO] Press CTRL+C to quit 2026-06-07 12:29:55,176 [INFO] 212.252.116.251 - - [07/Jun/2026 12:29:55] "GET / HTTP/1.1" 200 - 2026-06-07 12:29:55,343 [INFO] 212.252.116.251 - - [07/Jun/2026 12:29:55] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 12:29:55,392 [INFO] 212.252.116.251 - - [07/Jun/2026 12:29:55] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 12:29:55,593 [INFO] 212.252.116.251 - - [07/Jun/2026 12:29:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:29:55,824 [INFO] Found existing user id=34 for fingerprint 2026-06-07 12:29:56,293 [INFO] 212.252.116.251 - - [07/Jun/2026 12:29:56] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:30:07,951 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:07] "GET / HTTP/1.1" 200 - 2026-06-07 12:30:08,279 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:08] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 12:30:08,326 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:08] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 12:30:08,541 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:30:08,862 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:30:09,159 [INFO] Found existing user id=35 for fingerprint 2026-06-07 12:30:09,637 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:09] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:30:25,752 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:30:27,750 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:27] "GET / HTTP/1.1" 206 - 2026-06-07 12:30:28,034 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:28] "GET /favicon.ico HTTP/1.1" 404 - 2026-06-07 12:30:55,733 [INFO] 212.252.116.251 - - [07/Jun/2026 12:30:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:31:25,753 [INFO] 212.252.116.251 - - [07/Jun/2026 12:31:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:31:55,735 [INFO] 212.252.116.251 - - [07/Jun/2026 12:31:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:32:13,281 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:13] "GET / HTTP/1.1" 206 - 2026-06-07 12:32:13,517 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:13] "GET /favicon.ico HTTP/1.1" 404 - 2026-06-07 12:32:25,753 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:32:29,079 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:29] "GET / HTTP/1.1" 200 - 2026-06-07 12:32:29,257 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:29] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-07 12:32:29,436 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:29] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-07 12:32:29,641 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:29] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:32:31,001 [INFO] No existing user with fingerprint found: 85bd810b227325f13e3cd6b5e198046a 2026-06-07 12:32:31,277 [INFO] Created visitor user id=39 fingerprint=85bd810b227325f13e3cd6b5e198046a 2026-06-07 12:32:31,754 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:31] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:32:55,751 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:32:59,653 [INFO] 212.252.116.251 - - [07/Jun/2026 12:32:59] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:33:09,538 [INFO] Found existing user id=39 for fingerprint 2026-06-07 12:33:11,339 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:33:11,838 [INFO] 212.252.116.251 - - [07/Jun/2026 12:33:11] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 12:33:12,644 [INFO] Found existing user id=39 for fingerprint 2026-06-07 12:33:13,120 [INFO] 212.252.116.251 - - [07/Jun/2026 12:33:13] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:33:25,752 [INFO] 212.252.116.251 - - [07/Jun/2026 12:33:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:33:29,656 [INFO] 212.252.116.251 - - [07/Jun/2026 12:33:29] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:33:32,760 [INFO] Found existing user id=39 for fingerprint 2026-06-07 12:33:34,522 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:33:34,842 [INFO] 212.252.116.251 - - [07/Jun/2026 12:33:34] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 12:33:36,159 [INFO] Found existing user id=39 for fingerprint 2026-06-07 12:33:36,634 [INFO] 212.252.116.251 - - [07/Jun/2026 12:33:36] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:33:55,755 [INFO] 212.252.116.251 - - [07/Jun/2026 12:33:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:33:59,659 [INFO] 212.252.116.251 - - [07/Jun/2026 12:33:59] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:34:18,940 [INFO] Found existing user id=39 for fingerprint 2026-06-07 12:34:20,772 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:34:21,239 [INFO] 212.252.116.251 - - [07/Jun/2026 12:34:21] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 12:34:21,878 [INFO] Found existing user id=39 for fingerprint 2026-06-07 12:34:22,358 [INFO] 212.252.116.251 - - [07/Jun/2026 12:34:22] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:34:25,755 [INFO] 212.252.116.251 - - [07/Jun/2026 12:34:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:34:29,661 [INFO] 212.252.116.251 - - [07/Jun/2026 12:34:29] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:34:55,754 [INFO] 212.252.116.251 - - [07/Jun/2026 12:34:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:34:59,662 [INFO] 212.252.116.251 - - [07/Jun/2026 12:34:59] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:35:09,941 [INFO] Found existing user id=39 for fingerprint 2026-06-07 12:35:11,673 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:35:12,075 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:12] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 12:35:12,685 [INFO] Found existing user id=39 for fingerprint 2026-06-07 12:35:13,161 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:13] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:35:25,754 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:35:29,664 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:29] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:35:43,873 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:43] "GET / HTTP/1.1" 200 - 2026-06-07 12:35:44,134 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:44] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-07 12:35:44,384 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:44] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-07 12:35:44,606 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:44] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:35:46,611 [INFO] No existing user with fingerprint found: edb88f2c8b17974d98b617e628b99ca8 2026-06-07 12:35:46,881 [INFO] Created visitor user id=40 fingerprint=edb88f2c8b17974d98b617e628b99ca8 2026-06-07 12:35:47,364 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:47] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:35:55,737 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:35:57,762 [INFO] Found existing user id=40 for fingerprint 2026-06-07 12:35:59,490 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:35:59,861 [INFO] 212.252.116.251 - - [07/Jun/2026 12:35:59] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 12:36:00,678 [INFO] Found existing user id=40 for fingerprint 2026-06-07 12:36:01,154 [INFO] 212.252.116.251 - - [07/Jun/2026 12:36:01] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:36:12,227 [INFO] Found existing user id=40 for fingerprint 2026-06-07 12:36:13,959 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:36:14,366 [INFO] 212.252.116.251 - - [07/Jun/2026 12:36:14] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 12:36:14,616 [INFO] 212.252.116.251 - - [07/Jun/2026 12:36:14] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:36:15,081 [INFO] Found existing user id=40 for fingerprint 2026-06-07 12:36:15,562 [INFO] 212.252.116.251 - - [07/Jun/2026 12:36:15] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:36:25,738 [INFO] 212.252.116.251 - - [07/Jun/2026 12:36:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:36:44,616 [INFO] 212.252.116.251 - - [07/Jun/2026 12:36:44] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:36:55,737 [INFO] 212.252.116.251 - - [07/Jun/2026 12:36:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:37:06,090 [INFO] Found existing user id=40 for fingerprint 2026-06-07 12:37:07,804 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:37:08,199 [INFO] 212.252.116.251 - - [07/Jun/2026 12:37:08] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 12:37:09,052 [INFO] Found existing user id=40 for fingerprint 2026-06-07 12:37:09,528 [INFO] 212.252.116.251 - - [07/Jun/2026 12:37:09] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 12:37:14,620 [INFO] 212.252.116.251 - - [07/Jun/2026 12:37:14] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:37:25,736 [INFO] 212.252.116.251 - - [07/Jun/2026 12:37:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:37:55,784 [INFO] 212.252.116.251 - - [07/Jun/2026 12:37:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:38:25,740 [INFO] 212.252.116.251 - - [07/Jun/2026 12:38:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:38:55,759 [INFO] 212.252.116.251 - - [07/Jun/2026 12:38:55] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:39:25,739 [INFO] 212.252.116.251 - - [07/Jun/2026 12:39:25] "GET /api/health HTTP/1.1" 200 - 2026-06-07 12:39:35,074 [INFO] Found existing user id=34 for fingerprint 2026-06-07 12:39:36,904 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 12:39:37,373 [INFO] 212.252.116.251 - - [07/Jun/2026 12:39:37] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 12:39:38,086 [INFO] Found existing user id=34 for fingerprint 2026-06-07 12:39:38,561 [INFO] 212.252.116.251 - - [07/Jun/2026 12:39:38] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:20:56,091 [INFO] BAL Chatbot Web API starting... 2026-06-07 18:20:56,092 [INFO] Runtime pid=30451 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 18:20:56,092 [INFO] Provider: groq 2026-06-07 18:20:56,092 [INFO] HTTPS enforcement: False 2026-06-07 18:20:56,092 [INFO] Loading FAISS index... 2026-06-07 18:20:56,120 [INFO] FAISS index loaded: 134 vectors 2026-06-07 18:20:56,120 [INFO] Loading chunk metadata... 2026-06-07 18:20:56,123 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 18:20:56,123 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 18:20:56,866 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:20:56,897 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 18:20:56,898 [INFO] Vector store ready — 134 chunks 2026-06-07 18:20:56,899 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 18:20:56,899 [INFO] LLM gateway ready — active provider: groq 2026-06-07 18:20:56,899 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 18:20:57,005 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 18:20:57,006 [INFO] Press CTRL+C to quit 2026-06-07 18:21:08,109 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:08] "GET / HTTP/1.1" 200 - 2026-06-07 18:21:08,407 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:08] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 18:21:08,463 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:08] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 18:21:08,687 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:21:08,901 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:09,375 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:09] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:21:11,565 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:13,296 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:21:13,679 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:13] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 18:21:14,327 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:14,789 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:14] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:21:22,899 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:24,642 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:21:25,147 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:25] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 18:21:25,681 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:26,140 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:26] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:21:38,643 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:21:44,356 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:46,043 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:21:46,501 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:46] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 18:21:47,038 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:47,503 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:47] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:21:56,595 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:58,278 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:21:58,674 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:58] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 18:21:59,229 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:21:59,706 [INFO] 212.252.116.251 - - [07/Jun/2026 18:21:59] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:22:08,734 [INFO] 212.252.116.251 - - [07/Jun/2026 18:22:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:22:19,837 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:22:21,528 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:22:21,962 [INFO] 212.252.116.251 - - [07/Jun/2026 18:22:21] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 18:22:22,595 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:22:23,057 [INFO] 212.252.116.251 - - [07/Jun/2026 18:22:23] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:22:34,048 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:22:35,741 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:22:36,175 [INFO] 212.252.116.251 - - [07/Jun/2026 18:22:36] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 18:22:36,703 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:22:37,170 [INFO] 212.252.116.251 - - [07/Jun/2026 18:22:37] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:22:38,756 [INFO] 212.252.116.251 - - [07/Jun/2026 18:22:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:23:01,778 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:23:03,493 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:23:03,901 [INFO] 212.252.116.251 - - [07/Jun/2026 18:23:03] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 18:23:04,423 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:23:04,882 [INFO] 212.252.116.251 - - [07/Jun/2026 18:23:04] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:23:08,754 [INFO] 212.252.116.251 - - [07/Jun/2026 18:23:08] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:23:21,009 [INFO] Session cleared: session_vp8sosk 2026-06-07 18:23:21,010 [INFO] 212.252.116.251 - - [07/Jun/2026 18:23:21] "POST /api/clear HTTP/1.1" 200 - 2026-06-07 18:23:25,775 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:23:27,405 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:23:27,586 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '1511', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '993', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '10m4.8s', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kthax1y3expbq56ggd0a9kxw'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 760, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-07 18:23:27,603 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-07 18:23:27,757 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kthax23cexx9cs2mm1yd9xnr'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 760, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-07 18:23:27,759 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-07 18:23:28,155 [INFO] 212.252.116.251 - - [07/Jun/2026 18:23:28] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 18:23:29,212 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-07 18:23:29,729 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:23:30,189 [INFO] 212.252.116.251 - - [07/Jun/2026 18:23:30] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:23:38,753 [INFO] 212.252.116.251 - - [07/Jun/2026 18:23:38] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:24:09,372 [INFO] 212.252.116.251 - - [07/Jun/2026 18:24:09] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:24:39,372 [INFO] 212.252.116.251 - - [07/Jun/2026 18:24:39] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:25:10,985 [INFO] 212.252.116.251 - - [07/Jun/2026 18:25:10] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:25:41,306 [INFO] 212.252.116.251 - - [07/Jun/2026 18:25:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:26:11,306 [INFO] 212.252.116.251 - - [07/Jun/2026 18:26:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:26:41,307 [INFO] 212.252.116.251 - - [07/Jun/2026 18:26:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:27:11,308 [INFO] 212.252.116.251 - - [07/Jun/2026 18:27:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:27:41,308 [INFO] 212.252.116.251 - - [07/Jun/2026 18:27:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:28:11,316 [INFO] 212.252.116.251 - - [07/Jun/2026 18:28:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:28:41,308 [INFO] 212.252.116.251 - - [07/Jun/2026 18:28:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:29:11,310 [INFO] 212.252.116.251 - - [07/Jun/2026 18:29:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:29:41,311 [INFO] 212.252.116.251 - - [07/Jun/2026 18:29:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:30:11,310 [INFO] 212.252.116.251 - - [07/Jun/2026 18:30:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:30:41,311 [INFO] 212.252.116.251 - - [07/Jun/2026 18:30:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:31:11,610 [INFO] 212.252.116.251 - - [07/Jun/2026 18:31:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:31:41,610 [INFO] 212.252.116.251 - - [07/Jun/2026 18:31:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:32:11,611 [INFO] 212.252.116.251 - - [07/Jun/2026 18:32:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:32:41,610 [INFO] 212.252.116.251 - - [07/Jun/2026 18:32:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:33:11,614 [INFO] 212.252.116.251 - - [07/Jun/2026 18:33:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:33:41,612 [INFO] 212.252.116.251 - - [07/Jun/2026 18:33:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:34:11,612 [INFO] 212.252.116.251 - - [07/Jun/2026 18:34:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:34:41,614 [INFO] 212.252.116.251 - - [07/Jun/2026 18:34:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:35:11,613 [INFO] 212.252.116.251 - - [07/Jun/2026 18:35:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:35:41,614 [INFO] 212.252.116.251 - - [07/Jun/2026 18:35:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:36:11,615 [INFO] 212.252.116.251 - - [07/Jun/2026 18:36:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:36:41,617 [INFO] 212.252.116.251 - - [07/Jun/2026 18:36:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:37:11,704 [INFO] 212.252.116.251 - - [07/Jun/2026 18:37:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:37:41,705 [INFO] 212.252.116.251 - - [07/Jun/2026 18:37:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:38:11,705 [INFO] 212.252.116.251 - - [07/Jun/2026 18:38:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:38:41,712 [INFO] 212.252.116.251 - - [07/Jun/2026 18:38:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:39:11,705 [INFO] 212.252.116.251 - - [07/Jun/2026 18:39:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:39:41,706 [INFO] 212.252.116.251 - - [07/Jun/2026 18:39:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:40:11,707 [INFO] 212.252.116.251 - - [07/Jun/2026 18:40:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:40:41,713 [INFO] 212.252.116.251 - - [07/Jun/2026 18:40:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:41:11,709 [INFO] 212.252.116.251 - - [07/Jun/2026 18:41:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:41:41,710 [INFO] 212.252.116.251 - - [07/Jun/2026 18:41:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:42:11,709 [INFO] 212.252.116.251 - - [07/Jun/2026 18:42:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:42:41,710 [INFO] 212.252.116.251 - - [07/Jun/2026 18:42:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:43:11,710 [INFO] 212.252.116.251 - - [07/Jun/2026 18:43:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:43:41,706 [INFO] 212.252.116.251 - - [07/Jun/2026 18:43:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:44:11,711 [INFO] 212.252.116.251 - - [07/Jun/2026 18:44:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:44:41,713 [INFO] 212.252.116.251 - - [07/Jun/2026 18:44:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:45:11,714 [INFO] 212.252.116.251 - - [07/Jun/2026 18:45:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:45:41,713 [INFO] 212.252.116.251 - - [07/Jun/2026 18:45:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:46:11,710 [INFO] 212.252.116.251 - - [07/Jun/2026 18:46:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:46:41,713 [INFO] 212.252.116.251 - - [07/Jun/2026 18:46:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:47:11,711 [INFO] 212.252.116.251 - - [07/Jun/2026 18:47:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:47:41,715 [INFO] 212.252.116.251 - - [07/Jun/2026 18:47:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:48:11,713 [INFO] 212.252.116.251 - - [07/Jun/2026 18:48:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:48:41,714 [INFO] 212.252.116.251 - - [07/Jun/2026 18:48:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:49:11,714 [INFO] 212.252.116.251 - - [07/Jun/2026 18:49:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:49:41,715 [INFO] 212.252.116.251 - - [07/Jun/2026 18:49:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:50:11,719 [INFO] 212.252.116.251 - - [07/Jun/2026 18:50:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:50:41,718 [INFO] 212.252.116.251 - - [07/Jun/2026 18:50:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:51:11,716 [INFO] 212.252.116.251 - - [07/Jun/2026 18:51:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:51:41,717 [INFO] 212.252.116.251 - - [07/Jun/2026 18:51:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:52:11,718 [INFO] 212.252.116.251 - - [07/Jun/2026 18:52:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:52:41,718 [INFO] 212.252.116.251 - - [07/Jun/2026 18:52:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:53:11,719 [INFO] 212.252.116.251 - - [07/Jun/2026 18:53:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:53:41,719 [INFO] 212.252.116.251 - - [07/Jun/2026 18:53:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:54:11,721 [INFO] 212.252.116.251 - - [07/Jun/2026 18:54:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:54:41,720 [INFO] 212.252.116.251 - - [07/Jun/2026 18:54:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:55:11,722 [INFO] 212.252.116.251 - - [07/Jun/2026 18:55:11] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:55:41,723 [INFO] 212.252.116.251 - - [07/Jun/2026 18:55:41] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:55:59,158 [INFO] BAL Chatbot Web API starting... 2026-06-07 18:55:59,159 [INFO] Runtime pid=51167 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 18:55:59,159 [INFO] Provider: groq 2026-06-07 18:55:59,159 [INFO] HTTPS enforcement: False 2026-06-07 18:55:59,159 [INFO] Loading FAISS index... 2026-06-07 18:55:59,162 [INFO] FAISS index loaded: 134 vectors 2026-06-07 18:55:59,162 [INFO] Loading chunk metadata... 2026-06-07 18:55:59,165 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 18:55:59,166 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 18:55:59,732 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:55:59,764 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 18:55:59,764 [INFO] Vector store ready — 134 chunks 2026-06-07 18:55:59,764 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 18:55:59,764 [INFO] LLM gateway ready — active provider: groq 2026-06-07 18:55:59,764 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 18:55:59,770 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 18:55:59,770 [INFO] Press CTRL+C to quit 2026-06-07 18:56:09,642 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:09] "GET / HTTP/1.1" 200 - 2026-06-07 18:56:09,925 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:09] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 18:56:09,976 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:09] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 18:56:10,154 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:10] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:56:10,434 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:56:10,908 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:10] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:56:41,808 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:41] "GET / HTTP/1.1" 304 - 2026-06-07 18:56:41,957 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:41] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 18:56:42,006 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:42] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 18:56:42,222 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:42] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:56:42,442 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:56:42,908 [INFO] 212.252.116.251 - - [07/Jun/2026 18:56:42] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:58:04,377 [INFO] BAL Chatbot Web API starting... 2026-06-07 18:58:04,378 [INFO] Runtime pid=52839 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 18:58:04,378 [INFO] Provider: groq 2026-06-07 18:58:04,378 [INFO] HTTPS enforcement: False 2026-06-07 18:58:04,378 [INFO] Loading FAISS index... 2026-06-07 18:58:04,381 [INFO] FAISS index loaded: 134 vectors 2026-06-07 18:58:04,381 [INFO] Loading chunk metadata... 2026-06-07 18:58:04,384 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 18:58:04,384 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 18:58:04,847 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 18:58:04,879 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 18:58:04,879 [INFO] Vector store ready — 134 chunks 2026-06-07 18:58:04,879 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 18:58:04,879 [INFO] LLM gateway ready — active provider: groq 2026-06-07 18:58:04,879 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 18:58:04,880 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 18:58:04,880 [INFO] Press CTRL+C to quit 2026-06-07 18:58:16,549 [INFO] 212.252.116.251 - - [07/Jun/2026 18:58:16] "GET / HTTP/1.1" 200 - 2026-06-07 18:58:16,818 [INFO] 212.252.116.251 - - [07/Jun/2026 18:58:16] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 18:58:16,872 [INFO] 212.252.116.251 - - [07/Jun/2026 18:58:16] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 18:58:17,071 [INFO] 212.252.116.251 - - [07/Jun/2026 18:58:17] "GET /api/health HTTP/1.1" 200 - 2026-06-07 18:58:17,345 [INFO] Found existing user id=34 for fingerprint 2026-06-07 18:58:17,807 [INFO] 212.252.116.251 - - [07/Jun/2026 18:58:17] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 18:58:47,206 [INFO] 212.252.116.251 - - [07/Jun/2026 18:58:47] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:00:19,995 [INFO] BAL Chatbot Web API starting... 2026-06-07 19:00:19,996 [INFO] Runtime pid=54232 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 19:00:19,996 [INFO] Provider: groq 2026-06-07 19:00:19,996 [INFO] HTTPS enforcement: False 2026-06-07 19:00:19,997 [INFO] Loading FAISS index... 2026-06-07 19:00:19,999 [INFO] FAISS index loaded: 134 vectors 2026-06-07 19:00:19,999 [INFO] Loading chunk metadata... 2026-06-07 19:00:20,001 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 19:00:20,001 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 19:00:20,485 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 19:00:20,516 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 19:00:20,516 [INFO] Vector store ready — 134 chunks 2026-06-07 19:00:20,517 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 19:00:20,517 [INFO] LLM gateway ready — active provider: groq 2026-06-07 19:00:20,517 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 19:00:20,526 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 19:00:20,526 [INFO] Press CTRL+C to quit 2026-06-07 19:00:28,998 [INFO] 212.252.116.251 - - [07/Jun/2026 19:00:28] "GET / HTTP/1.1" 200 - 2026-06-07 19:00:29,252 [INFO] 212.252.116.251 - - [07/Jun/2026 19:00:29] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 19:00:29,315 [INFO] 212.252.116.251 - - [07/Jun/2026 19:00:29] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 19:00:29,529 [INFO] 212.252.116.251 - - [07/Jun/2026 19:00:29] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:00:29,785 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:00:30,255 [INFO] 212.252.116.251 - - [07/Jun/2026 19:00:30] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:02:33,110 [INFO] BAL Chatbot Web API starting... 2026-06-07 19:02:33,110 [INFO] Runtime pid=55620 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 19:02:33,111 [INFO] Provider: groq 2026-06-07 19:02:33,111 [INFO] HTTPS enforcement: False 2026-06-07 19:02:33,111 [INFO] Loading FAISS index... 2026-06-07 19:02:33,114 [INFO] FAISS index loaded: 134 vectors 2026-06-07 19:02:33,114 [INFO] Loading chunk metadata... 2026-06-07 19:02:33,117 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 19:02:33,117 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 19:02:33,637 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 19:02:33,668 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 19:02:33,669 [INFO] Vector store ready — 134 chunks 2026-06-07 19:02:33,669 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 19:02:33,669 [INFO] LLM gateway ready — active provider: groq 2026-06-07 19:02:33,669 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 19:02:33,675 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 19:02:33,676 [INFO] Press CTRL+C to quit 2026-06-07 19:02:44,437 [INFO] 212.252.116.251 - - [07/Jun/2026 19:02:44] "GET / HTTP/1.1" 200 - 2026-06-07 19:02:44,683 [INFO] 212.252.116.251 - - [07/Jun/2026 19:02:44] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 19:02:44,729 [INFO] 212.252.116.251 - - [07/Jun/2026 19:02:44] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 19:02:44,922 [INFO] 212.252.116.251 - - [07/Jun/2026 19:02:44] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:02:45,186 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:02:45,629 [INFO] 212.252.116.251 - - [07/Jun/2026 19:02:45] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:03:15,039 [INFO] 212.252.116.251 - - [07/Jun/2026 19:03:15] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:04:01,352 [INFO] BAL Chatbot Web API starting... 2026-06-07 19:04:01,352 [INFO] Runtime pid=56970 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 19:04:01,353 [INFO] Provider: groq 2026-06-07 19:04:01,353 [INFO] HTTPS enforcement: False 2026-06-07 19:04:01,353 [INFO] Loading FAISS index... 2026-06-07 19:04:01,357 [INFO] FAISS index loaded: 134 vectors 2026-06-07 19:04:01,357 [INFO] Loading chunk metadata... 2026-06-07 19:04:01,358 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 19:04:01,358 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 19:04:01,868 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 19:04:01,898 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 19:04:01,899 [INFO] Vector store ready — 134 chunks 2026-06-07 19:04:01,899 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 19:04:01,899 [INFO] LLM gateway ready — active provider: groq 2026-06-07 19:04:01,899 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 19:04:01,901 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 19:04:01,901 [INFO] Press CTRL+C to quit 2026-06-07 19:04:06,559 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:06] "GET / HTTP/1.1" 200 - 2026-06-07 19:04:06,838 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:06] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 19:04:06,891 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:06] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 19:04:07,103 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:07] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:04:07,351 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:04:07,842 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:07] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:04:16,931 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:04:18,716 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 19:04:19,117 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:19] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 19:04:20,020 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:04:20,501 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:20] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:04:57,775 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:57] "GET / HTTP/1.1" 200 - 2026-06-07 19:04:58,019 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:58] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-07 19:04:58,185 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:58] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-07 19:04:58,402 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:58] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:04:59,492 [INFO] Found existing user id=38 for fingerprint 2026-06-07 19:04:59,973 [INFO] 212.252.116.251 - - [07/Jun/2026 19:04:59] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:08:35,962 [INFO] BAL Chatbot Web API starting... 2026-06-07 19:08:35,963 [INFO] Runtime pid=59635 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-07 19:08:35,963 [INFO] Provider: groq 2026-06-07 19:08:35,963 [INFO] HTTPS enforcement: False 2026-06-07 19:08:35,963 [INFO] Loading FAISS index... 2026-06-07 19:08:35,966 [INFO] FAISS index loaded: 134 vectors 2026-06-07 19:08:35,966 [INFO] Loading chunk metadata... 2026-06-07 19:08:35,968 [INFO] Chunk metadata loaded: 134 chunks 2026-06-07 19:08:35,968 [INFO] Testing embedding API with 5 key(s)... 2026-06-07 19:08:36,562 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 19:08:36,597 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-07 19:08:36,599 [INFO] Vector store ready — 134 chunks 2026-06-07 19:08:36,599 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-07 19:08:36,599 [INFO] LLM gateway ready — active provider: groq 2026-06-07 19:08:36,599 [INFO] Server starting on http://0.0.0.0:5000 2026-06-07 19:08:36,605 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-07 19:08:36,606 [INFO] Press CTRL+C to quit 2026-06-07 19:08:41,762 [INFO] 212.252.116.251 - - [07/Jun/2026 19:08:41] "GET / HTTP/1.1" 200 - 2026-06-07 19:08:42,027 [INFO] 212.252.116.251 - - [07/Jun/2026 19:08:42] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 19:08:42,072 [INFO] 212.252.116.251 - - [07/Jun/2026 19:08:42] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 19:08:42,414 [INFO] 212.252.116.251 - - [07/Jun/2026 19:08:42] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:08:42,767 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:08:43,247 [INFO] 212.252.116.251 - - [07/Jun/2026 19:08:43] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:09:04,179 [INFO] 212.252.116.251 - - [07/Jun/2026 19:09:04] "GET / HTTP/1.1" 200 - 2026-06-07 19:09:04,384 [INFO] 212.252.116.251 - - [07/Jun/2026 19:09:04] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:09:04,597 [INFO] 212.252.116.251 - - [07/Jun/2026 19:09:04] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 19:09:04,624 [INFO] 212.252.116.251 - - [07/Jun/2026 19:09:04] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 19:09:04,822 [INFO] 212.252.116.251 - - [07/Jun/2026 19:09:04] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:09:05,580 [INFO] Found existing user id=38 for fingerprint 2026-06-07 19:09:06,051 [INFO] 212.252.116.251 - - [07/Jun/2026 19:09:06] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:10:06,604 [INFO] 212.252.116.251 - - [07/Jun/2026 19:10:06] "GET / HTTP/1.1" 304 - 2026-06-07 19:10:06,759 [INFO] 212.252.116.251 - - [07/Jun/2026 19:10:06] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 19:10:06,806 [INFO] 212.252.116.251 - - [07/Jun/2026 19:10:06] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 19:10:07,137 [INFO] 212.252.116.251 - - [07/Jun/2026 19:10:07] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:10:07,303 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:10:07,777 [INFO] 212.252.116.251 - - [07/Jun/2026 19:10:07] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:10:37,892 [INFO] 212.252.116.251 - - [07/Jun/2026 19:10:37] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:11:07,893 [INFO] 212.252.116.251 - - [07/Jun/2026 19:11:07] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:11:20,737 [INFO] 212.252.116.251 - - [07/Jun/2026 19:11:20] "GET / HTTP/1.1" 304 - 2026-06-07 19:11:20,867 [INFO] 212.252.116.251 - - [07/Jun/2026 19:11:20] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 19:11:20,871 [INFO] 212.252.116.251 - - [07/Jun/2026 19:11:20] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 19:11:21,215 [INFO] 212.252.116.251 - - [07/Jun/2026 19:11:21] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:11:21,414 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:11:21,884 [INFO] 212.252.116.251 - - [07/Jun/2026 19:11:21] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:31:16,005 [INFO] 212.252.116.251 - - [07/Jun/2026 19:31:16] "GET / HTTP/1.1" 304 - 2026-06-07 19:31:16,137 [INFO] 212.252.116.251 - - [07/Jun/2026 19:31:16] "GET /BAL_Logo.png HTTP/1.1" 304 - 2026-06-07 19:31:16,185 [INFO] 212.252.116.251 - - [07/Jun/2026 19:31:16] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 304 - 2026-06-07 19:31:17,995 [INFO] 212.252.116.251 - - [07/Jun/2026 19:31:17] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:31:18,045 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:31:18,516 [INFO] 212.252.116.251 - - [07/Jun/2026 19:31:18] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:31:46,384 [INFO] 212.252.116.251 - - [07/Jun/2026 19:31:46] "GET /api/health HTTP/1.1" 200 - 2026-06-07 19:31:57,467 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:31:59,238 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-07 19:31:59,497 [ERROR] Groq API HTTP error status=429 model=llama-3.3-70b-versatile rate_headers={'retry-after': '736', 'x-ratelimit-limit-requests': '1000', 'x-ratelimit-limit-tokens': '12000', 'x-ratelimit-remaining-requests': '1000', 'x-ratelimit-remaining-tokens': '12000', 'x-ratelimit-reset-requests': '1ms', 'x-ratelimit-reset-tokens': '1ms', 'x-request-id': 'req_01kthethf7fgqbsbhctp2rwzg0'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 760, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: https://api.groq.com/openai/v1/chat/completions 2026-06-07 19:31:59,500 [WARNING] Groq fallback switching key_index=1 from_model=llama-3.3-70b-versatile to_model=meta-llama/llama-4-maverick-17b-128e-instruct reason=http_429 2026-06-07 19:31:59,653 [ERROR] Groq API HTTP error status=404 model=meta-llama/llama-4-maverick-17b-128e-instruct rate_headers={'x-request-id': 'req_01kthethm6fgqan5rjzeje88b3'} body= Traceback (most recent call last): File "/home/burak/Masaüstü/ChatbotBAL/web/app.py", line 760, in stream_groq_model resp.raise_for_status() File "/home/burak/venv/lib/python3.12/site-packages/requests/models.py", line 1026, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://api.groq.com/openai/v1/chat/completions 2026-06-07 19:31:59,655 [WARNING] Groq fallback switching key_index=1 from_model=meta-llama/llama-4-maverick-17b-128e-instruct to_model=qwen/qwen3-32b reason=http_404 2026-06-07 19:32:00,257 [INFO] 212.252.116.251 - - [07/Jun/2026 19:32:00] "POST /api/chat HTTP/1.1" 200 - 2026-06-07 19:32:02,171 [WARNING] Groq fallback succeeded key_index=1 original_model=llama-3.3-70b-versatile active_model=qwen/qwen3-32b 2026-06-07 19:32:02,723 [INFO] Found existing user id=34 for fingerprint 2026-06-07 19:32:03,184 [INFO] 212.252.116.251 - - [07/Jun/2026 19:32:03] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-07 19:32:16,492 [INFO] 212.252.116.251 - - [07/Jun/2026 19:32:16] "GET /api/health HTTP/1.1" 200 - 2026-06-08 07:10:20,898 [INFO] BAL Chatbot Web API starting... 2026-06-08 07:10:20,922 [INFO] Runtime pid=8719 cwd=/home/burak/Masaüstü/ChatbotBAL/web log_file=/home/burak/Masaüstü/ChatbotBAL/logs/web.log 2026-06-08 07:10:20,922 [INFO] Provider: groq 2026-06-08 07:10:20,922 [INFO] HTTPS enforcement: False 2026-06-08 07:10:20,922 [INFO] Loading FAISS index... 2026-06-08 07:10:20,942 [INFO] FAISS index loaded: 134 vectors 2026-06-08 07:10:20,943 [INFO] Loading chunk metadata... 2026-06-08 07:10:20,953 [INFO] Chunk metadata loaded: 134 chunks 2026-06-08 07:10:20,953 [INFO] Testing embedding API with 5 key(s)... 2026-06-08 07:10:21,611 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 07:10:21,642 [INFO] ✓ Embedding API test successful (dim=(1, 3072)) 2026-06-08 07:10:21,642 [INFO] Vector store ready — 134 chunks 2026-06-08 07:10:21,643 [INFO] Groq configured — key_count=2 primary_model=llama-3.3-70b-versatile 2026-06-08 07:10:21,643 [INFO] LLM gateway ready — active provider: groq 2026-06-08 07:10:21,643 [INFO] Server starting on http://0.0.0.0:5000 2026-06-08 07:10:21,674 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on all addresses (0.0.0.0) * Running on http://127.0.0.1:5000 * Running on http://192.168.1.2:5000 2026-06-08 07:10:21,674 [INFO] Press CTRL+C to quit 2026-06-08 08:39:51,241 [INFO] 5.24.176.5 - - [08/Jun/2026 08:39:51] "GET / HTTP/1.1" 200 - 2026-06-08 08:39:51,561 [INFO] 5.24.176.5 - - [08/Jun/2026 08:39:51] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-08 08:39:51,845 [INFO] 5.24.176.5 - - [08/Jun/2026 08:39:51] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-08 08:39:53,001 [INFO] 5.24.176.5 - - [08/Jun/2026 08:39:53] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:39:53,324 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:39:53,846 [INFO] 5.24.176.5 - - [08/Jun/2026 08:39:53] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:40:22,096 [INFO] 5.24.176.5 - - [08/Jun/2026 08:40:22] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:40:52,106 [INFO] 5.24.176.5 - - [08/Jun/2026 08:40:52] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:41:15,610 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:41:17,459 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:41:17,853 [INFO] 5.24.176.5 - - [08/Jun/2026 08:41:17] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:41:18,689 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:41:19,200 [INFO] 5.24.176.5 - - [08/Jun/2026 08:41:19] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:41:22,083 [INFO] 5.24.176.5 - - [08/Jun/2026 08:41:22] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:41:47,090 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:41:48,914 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:41:49,406 [INFO] 5.24.176.5 - - [08/Jun/2026 08:41:49] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:41:50,109 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:41:50,619 [INFO] 5.24.176.5 - - [08/Jun/2026 08:41:50] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:41:52,092 [INFO] 5.24.176.5 - - [08/Jun/2026 08:41:52] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:41:56,769 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:41:58,616 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:41:58,989 [INFO] 5.24.176.5 - - [08/Jun/2026 08:41:58] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:41:59,597 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:42:00,110 [INFO] 5.24.176.5 - - [08/Jun/2026 08:42:00] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:42:22,125 [INFO] 5.24.176.5 - - [08/Jun/2026 08:42:22] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:42:27,117 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:42:28,979 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:42:29,259 [INFO] 5.24.176.5 - - [08/Jun/2026 08:42:29] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:42:30,356 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:42:30,867 [INFO] 5.24.176.5 - - [08/Jun/2026 08:42:30] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:42:52,102 [INFO] 5.24.176.5 - - [08/Jun/2026 08:42:52] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:43:00,292 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:43:02,093 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:43:02,416 [INFO] 5.24.176.5 - - [08/Jun/2026 08:43:02] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:43:03,747 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:43:04,257 [INFO] 5.24.176.5 - - [08/Jun/2026 08:43:04] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:43:22,082 [INFO] 5.24.176.5 - - [08/Jun/2026 08:43:22] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:43:41,110 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:43:42,904 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:43:43,268 [INFO] 5.24.176.5 - - [08/Jun/2026 08:43:43] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:43:44,003 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:43:44,511 [INFO] 5.24.176.5 - - [08/Jun/2026 08:43:44] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:43:52,133 [INFO] 5.24.176.5 - - [08/Jun/2026 08:43:52] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:43:53,286 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:43:55,064 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:43:55,464 [INFO] 5.24.176.5 - - [08/Jun/2026 08:43:55] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:43:56,268 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:43:56,800 [INFO] 5.24.176.5 - - [08/Jun/2026 08:43:56] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:44:15,189 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:44:16,987 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:44:17,361 [INFO] 5.24.176.5 - - [08/Jun/2026 08:44:17] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:44:18,280 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:44:18,789 [INFO] 5.24.176.5 - - [08/Jun/2026 08:44:18] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:44:22,096 [INFO] 5.24.176.5 - - [08/Jun/2026 08:44:22] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:44:52,118 [INFO] 5.24.176.5 - - [08/Jun/2026 08:44:52] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:45:01,673 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:45:03,559 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:45:04,080 [INFO] 5.24.176.5 - - [08/Jun/2026 08:45:04] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:45:04,788 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:45:05,303 [INFO] 5.24.176.5 - - [08/Jun/2026 08:45:05] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:45:22,248 [INFO] 5.24.176.5 - - [08/Jun/2026 08:45:22] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:45:25,224 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:45:27,005 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:45:27,823 [INFO] 5.24.176.5 - - [08/Jun/2026 08:45:27] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:45:28,843 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:45:29,351 [INFO] 5.24.176.5 - - [08/Jun/2026 08:45:29] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:45:52,123 [INFO] 5.24.176.5 - - [08/Jun/2026 08:45:52] "GET /api/health HTTP/1.1" 200 - 2026-06-08 08:45:53,909 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:45:55,690 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 08:45:56,131 [INFO] 5.24.176.5 - - [08/Jun/2026 08:45:56] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 08:45:56,804 [INFO] Found existing user id=35 for fingerprint 2026-06-08 08:45:57,313 [INFO] 5.24.176.5 - - [08/Jun/2026 08:45:57] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 08:49:58,324 [INFO] 5.24.176.5 - - [08/Jun/2026 08:49:58] "GET /api/health HTTP/1.1" 200 - 2026-06-08 09:05:56,890 [INFO] 5.24.176.5 - - [08/Jun/2026 09:05:56] "GET / HTTP/1.1" 200 - 2026-06-08 09:05:57,209 [INFO] 5.24.176.5 - - [08/Jun/2026 09:05:57] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-08 09:05:57,838 [INFO] 5.24.176.5 - - [08/Jun/2026 09:05:57] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-08 09:05:59,681 [INFO] 5.24.176.5 - - [08/Jun/2026 09:05:59] "GET /api/health HTTP/1.1" 200 - 2026-06-08 09:05:59,720 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:06:00,224 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:00] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 09:06:10,453 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:06:12,196 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 09:06:12,563 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:12] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 09:06:13,311 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:06:13,795 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:13] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 09:06:24,875 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:06:26,641 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 09:06:27,068 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:27] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 09:06:27,953 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:06:28,045 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:28] "GET /api/health HTTP/1.1" 200 - 2026-06-08 09:06:28,437 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:28] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 09:06:50,760 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:06:52,500 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 09:06:52,887 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:52] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 09:06:53,555 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:06:54,044 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:54] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 09:06:58,083 [INFO] 5.24.176.5 - - [08/Jun/2026 09:06:58] "GET /api/health HTTP/1.1" 200 - 2026-06-08 09:07:06,537 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:07:08,269 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 09:07:08,757 [INFO] 5.24.176.5 - - [08/Jun/2026 09:07:08] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 09:07:09,358 [INFO] Found existing user id=35 for fingerprint 2026-06-08 09:07:09,841 [INFO] 5.24.176.5 - - [08/Jun/2026 09:07:09] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 14:20:29,470 [INFO] 5.24.176.5 - - [08/Jun/2026 14:20:29] "GET / HTTP/1.1" 200 - 2026-06-08 14:20:29,813 [INFO] 5.24.176.5 - - [08/Jun/2026 14:20:29] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-08 14:20:30,290 [INFO] 5.24.176.5 - - [08/Jun/2026 14:20:30] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-08 14:20:31,718 [INFO] 5.24.176.5 - - [08/Jun/2026 14:20:31] "GET /api/health HTTP/1.1" 200 - 2026-06-08 14:20:33,399 [INFO] No existing user with fingerprint found: be4731a536b63b690514d4c216d99ba2 2026-06-08 14:20:33,680 [INFO] Created visitor user id=41 fingerprint=be4731a536b63b690514d4c216d99ba2 2026-06-08 14:20:34,165 [INFO] 5.24.176.5 - - [08/Jun/2026 14:20:34] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 14:21:10,820 [INFO] 5.24.176.5 - - [08/Jun/2026 14:21:10] "GET /api/health HTTP/1.1" 200 - 2026-06-08 14:21:13,738 [INFO] Found existing user id=41 for fingerprint 2026-06-08 14:21:15,550 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 14:21:15,981 [INFO] 5.24.176.5 - - [08/Jun/2026 14:21:15] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 14:21:18,160 [INFO] Found existing user id=41 for fingerprint 2026-06-08 14:21:18,630 [INFO] 5.24.176.5 - - [08/Jun/2026 14:21:18] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 14:21:40,640 [INFO] 5.24.176.5 - - [08/Jun/2026 14:21:40] "GET /api/health HTTP/1.1" 200 - 2026-06-08 16:05:50,273 [INFO] 5.24.176.5 - - [08/Jun/2026 16:05:50] "GET / HTTP/1.1" 200 - 2026-06-08 16:05:50,739 [INFO] 5.24.176.5 - - [08/Jun/2026 16:05:50] "GET /BAL_Logo.png HTTP/1.1" 200 - 2026-06-08 16:05:51,462 [INFO] 5.24.176.5 - - [08/Jun/2026 16:05:51] "GET /vendor/fingerprintjs/fp.esm.js HTTP/1.1" 200 - 2026-06-08 16:05:53,925 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:05:54,388 [INFO] 5.24.176.5 - - [08/Jun/2026 16:05:54] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 16:05:54,654 [INFO] 5.24.176.5 - - [08/Jun/2026 16:05:54] "GET /api/health HTTP/1.1" 200 - 2026-06-08 16:06:21,676 [INFO] 5.24.176.5 - - [08/Jun/2026 16:06:21] "GET /api/health HTTP/1.1" 200 - 2026-06-08 16:06:47,530 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:06:49,239 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 16:06:49,624 [INFO] 5.24.176.5 - - [08/Jun/2026 16:06:49] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 16:06:50,348 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:06:50,798 [INFO] 5.24.176.5 - - [08/Jun/2026 16:06:50] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 16:06:51,686 [INFO] 5.24.176.5 - - [08/Jun/2026 16:06:51] "GET /api/health HTTP/1.1" 200 - 2026-06-08 16:07:21,697 [INFO] 5.24.176.5 - - [08/Jun/2026 16:07:21] "GET /api/health HTTP/1.1" 200 - 2026-06-08 16:07:39,778 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:07:41,441 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 16:07:41,956 [INFO] 5.24.176.5 - - [08/Jun/2026 16:07:41] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 16:07:42,650 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:07:43,099 [INFO] 5.24.176.5 - - [08/Jun/2026 16:07:43] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 16:07:51,708 [INFO] 5.24.176.5 - - [08/Jun/2026 16:07:51] "GET /api/health HTTP/1.1" 200 - 2026-06-08 16:07:55,281 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:07:56,898 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 16:07:57,332 [INFO] 5.24.176.5 - - [08/Jun/2026 16:07:57] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 16:07:58,254 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:07:58,703 [INFO] 5.24.176.5 - - [08/Jun/2026 16:07:58] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 16:08:21,791 [INFO] 5.24.176.5 - - [08/Jun/2026 16:08:21] "GET /api/health HTTP/1.1" 200 - 2026-06-08 16:08:27,506 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:08:31,411 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 16:08:33,631 [INFO] 5.24.176.5 - - [08/Jun/2026 16:08:33] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 16:08:34,193 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:08:34,644 [INFO] 5.24.176.5 - - [08/Jun/2026 16:08:34] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 16:08:44,466 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:08:46,149 [INFO] HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:batchEmbedContents "HTTP/1.1 200 OK" 2026-06-08 16:08:46,604 [INFO] 5.24.176.5 - - [08/Jun/2026 16:08:46] "POST /api/chat HTTP/1.1" 200 - 2026-06-08 16:08:47,262 [INFO] Found existing user id=35 for fingerprint 2026-06-08 16:08:47,711 [INFO] 5.24.176.5 - - [08/Jun/2026 16:08:47] "GET /api/auth/status HTTP/1.1" 200 - 2026-06-08 16:08:51,674 [INFO] 5.24.176.5 - - [08/Jun/2026 16:08:51] "GET /api/health HTTP/1.1" 200 -