Update main.py

main.py

@@ -2,9 +2,8 @@ import fastapi
 import json
 import markdown
 import uvicorn
-from fastapi.responses import HTMLResponse
+from fastapi.responses import StreamingResponse, HTMLResponse
 from fastapi.middleware.cors import CORSMiddleware
-from sse_starlette.sse import EventSourceResponse
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 from ctransformers import AutoModelForCausalLM
 from pydantic import BaseModel
@@ -37,10 +36,10 @@ async def chat(prompt = "Once upon a time there was a "):
     completion = llm(prompt)
     async def server_sent_events(chat_chunks):
         for chat_chunk in chat_chunks:
-            yield dict(data=json.dumps(chat_chunk))
-        yield dict(data="[DONE]")
+            yield chat_chunk
+        yield "[DONE]"
 
-    return EventSourceResponse(server_sent_events(completion))
+    return StreamingResponse(server_sent_events(completion))
 
 @app.post("/v1/chat/completions")
 async def chat(request: ChatCompletionRequest, response_mode=None):
@@ -48,10 +47,10 @@ async def chat(request: ChatCompletionRequest, response_mode=None):
     async def server_sent_events(chat_chunks):
         for chat_chunk in chat_chunks:
             print(chat_chunk)
-            yield dict(data=json.dumps(chat_chunk))
-        yield dict(data="[DONE]")
+            yield chat_chunk
+        yield "[DONE]"
 
-    return EventSourceResponse(server_sent_events(completion))
+    return StreamingResponse(server_sent_events(completion))
 
 if __name__ == "__main__":
   uvicorn.run(app, host="0.0.0.0", port=8000)