updated llm

core_logic.py

@@ -10,12 +10,12 @@ from huggingface_hub import InferenceClient
 from tools import web_search, parse_file
 from groq import Groq
 
-#client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+client = Groq(api_key=os.getenv("GROQ_API_KEY"))
 
 # Recommended: Qwen2.5-Coder-32B or Llama-3.1-70B-Instruct
 #client = InferenceClient("deepseek-ai/DeepSeek-V4-Pro", token=os.getenv("HF_TOKEN"))
 #client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct", token=os.getenv("HF_TOKEN"))
-client = InferenceClient("Qwen/Qwen2.5-Coder-7B-Instruct", token=os.getenv("HF_TOKEN"))
+#client = InferenceClient("Qwen/Qwen2.5-Coder-7B-Instruct", token=os.getenv("HF_TOKEN"))
 #client = InferenceClient("llama-3.1-8b-instant", token=os.getenv("HF_TOKEN")) "llama-3.1-70b-versatile" -> GROQ API
 #client = InferenceClient("meta-llama/Llama-3.1-8B-Instruct", token=os.getenv("HF_TOKEN")) # Or "Qwen/Qwen2.5-72B-Instruct"
 
@@ -67,9 +67,9 @@ def chat_function(message, history):
 
     response_text = ""
     try:
-        for chunk in client.chat_completion(messages, max_tokens=2048, stream=True, temperature=0.2):
+        #for chunk in client.chat_completion(messages, max_tokens=2048, stream=True, temperature=0.2):
         # --- Uncomment below for GROQ
-        #for chunk in client.chat.completions.create(model="llama-3.1-70b-versatile", messages=messages, max_tokens=2048, stream=True, temperature=0.2): # Or model="llama-3.1-8b-instant"
+        for chunk in client.chat.completions.create(model="llama-3.1-70b-versatile", messages=messages, max_tokens=2048, stream=True, temperature=0.2): # Or model="llama-3.1-8b-instant"
             # FIX: Check if choices exists and is not empty
             if hasattr(chunk, 'choices') and len(chunk.choices) > 0:
                 token = chunk.choices[0].delta.content