Update app.py

app.py

@@ -64,6 +64,7 @@ llm_pipeline = pipeline(
     generation_config=generation_config,
     device=model.device.index if model.device.type == "cuda" else -1
 )
+
 llm = HuggingFacePipeline(pipeline=llm_pipeline)
 
 retriever = vector_store.as_retriever(search_kwargs={"k": 3})
@@ -78,7 +79,6 @@ qa_chain = RetrievalQA.from_chain_type(
 # FastAPI setup
 app = FastAPI(title="Apollo RAG Medical Chatbot")
 
-
 class Query(BaseModel):
     question: str = Field(..., example="ما هي اسباب تساقط الشعر ؟", min_length=3)
 
@@ -155,18 +155,17 @@ async def ask(query: Query):
         timeout_callback = TimeoutCallback(timeout_seconds=60)
 
 
-        docs = retriever.get_relevant_documents(query.question)
-        if not docs:
-            logger.warning("No documents retrieved from Qdrant for the question.")
-        else:
-            logger.debug(f"Retrieved documents: {[doc.page_content for doc in docs[:1]]}")
-
+        # docs = retriever.get_relevant_documents(query.question)
+        # if not docs:
+        #     logger.warning("No documents retrieved from Qdrant for the question.")
+        # else:
+        #     logger.debug(f"Retrieved documents: {[doc.page_content for doc in docs[:1]]}")
 
         loop = asyncio.get_event_loop()
         
         answer = await asyncio.wait_for(
             # qa_chain.run(prompt, callbacks=[timeout_callback]),
-            loop.run_in_executor(None, qa_chain.run, prompt),
+            loop.run_in_executor(None, qa_chain.run, query.question),
             timeout=360
         )