Update main.py

main.py

@@ -105,11 +105,11 @@ def chat_with_llama_stream(messages, model="gpt-3.5-turbo", max_llm_history=4, m
         )
         
         full_response = ""
-        for chunk in response:
-            if chunk.choices[0].delta.content is not None:
-                content = chunk.choices[0].delta.content
-                full_response += content
-                yield content
+        for event in openai_stream:
+            if "content" in event["choices"][0].delta:
+                current_response = event["choices"][0].delta.content
+                full_response +=current_response
+                yield current_response
         
         # After streaming, add the full response to the conversation history
         messages.append({"role": "assistant", "content": full_response})
@@ -260,9 +260,9 @@ async def news_assistant(query: NewsQueryModel, api_key: str = Depends(verify_ap
         raise HTTPException(status_code=500, detail="Failed to fetch news data")
         
     def process_response():
-        for content in chat_with_llama_stream(messages, model="google/gemini-pro-1.5"):
+        for content in chat_with_llama_stream(messages, model="meta-llama/llama-3-70b-instruct"):
             yield content
-
+#meta-llama/llama-3-70b-instruct  google/gemini-pro-1.5
     return StreamingResponse(process_response(), media_type="text/event-stream")
 
 if __name__ == "__main__":