delete docs

main.py

@@ -141,13 +141,21 @@ import asyncio
 
 GENERATION_TIMEOUT_SEC = 60
 
-async def stream_generator(response,prompt):
+async def stream_generator(response, prompt):
+    buffer = ''  # Buffer to accumulate chunks
     async with async_timeout.timeout(GENERATION_TIMEOUT_SEC):
         try:
             async for chunk in response:
-                yield json.dumps({"prompt": prompt, "content": chunk})
+                buffer += chunk
+                try:
+                    data = json.loads(buffer)  # Try to parse the accumulated buffer
+                    yield json.dumps({"prompt": prompt, "content": data})
+                    buffer = ''  # Clear the buffer after successful parsing
+                except json.JSONDecodeError:
+                    continue  # Continue accumulating data if JSON is incomplete
         except asyncio.TimeoutError:
             raise HTTPException(status_code=504, detail="Stream timed out")
+
     
 
 @app.post("/generate-answer/")

rag.py

@@ -107,7 +107,7 @@ def generate_response_via_langchain(query: str, stream: bool = False, model: str
     prompt = PromptTemplate.from_template(template)
     
     # Initialize the OpenAI LLM with the specified model
-    llm = ChatOpenAI(model=model)
+    llm = ChatOpenAI(model=model,temperature=0)
     
     # Create an LLM chain with the prompt and the LLM
     llm_chain = prompt | llm | StrOutputParser()