streaming

app.py

@@ -4,6 +4,7 @@ from pydantic import BaseModel
 from langchain_ollama import ChatOllama
 from langchain.schema import StrOutputParser
 from langchain.prompts import ChatPromptTemplate
+from fastapi.responses import StreamingResponse
 import logging
 from functools import lru_cache
 
@@ -43,6 +44,22 @@ async def ask_question(question: Question):
     except Exception as e:
         logger.error(f"Error in /ask endpoint: {str(e)}")
         raise HTTPException(status_code=500, detail=str(e))
+    
+@app.post("/ask_stream")
+async def ask_question_stream(question: Question):
+    try:
+        logger.info(f"Received question for streaming: {question.text}")
+        chain = get_chain()
+        
+        async def generate():
+            async for chunk in chain.astream({"question": question.text}):
+                yield chunk + "\n"
+        
+        return StreamingResponse(generate(), media_type="text/plain")
+    except Exception as e:
+        logger.error(f"Error in /ask_stream endpoint: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
 
 @app.on_event("startup")
 async def startup_event():