Upload 2 files

start.sh

@@ -33,7 +33,7 @@ echo "Ollama is ready."
 echo "API is running on: http://0.0.0.0:7860"
 
 # Start FastAPI in the background
-uvicorn app:app --host 0.0.0.0 --port 8000 --workers 4 --limit-concurrency 20 &
+uvicorn app:app --host 0.0.0.0 --port 8000 --workers 1 --limit-concurrency 20 &
 
 # Start Streamlit for UI
 streamlit run streamlit_app.py --server.port 7860 --server.address 0.0.0.0

streamlit_app.py

@@ -14,7 +14,7 @@ def query_ai(question):
     url = "http://127.0.0.1:8000/query/"
     params = {"input_text": question}
     
-    with requests.get(url, params=params, stream=True) as response:
+    with requests.get(url, params=params, stream=True,timeout=120) as response:
         if response.status_code == 200:
             full_response = ""
             for chunk in response.iter_content(chunk_size=1024):