Update main.py

main.py

@@ -36,12 +36,12 @@ class ChatCompletionRequest(BaseModel):
 
 @app.post("/v1/chat/completions")
 async def chat(request: ChatCompletionRequest, response_mode=None):
-    tokens = llm.tokenize(request.messages)
-    async def server_sent_events(chat_chunks):
+    tokens = llm.tokenize(request.prompt)
+    async def server_sent_events(chat_chunks, llm):
         for token in llm.generate(chat_chunks):
             yield llm.detokenize(token)
 
-    return EventSourceResponse(server_sent_events(tokens))
+    return EventSourceResponse(server_sent_events(tokens, llm))
 
 if __name__ == "__main__":
   uvicorn.run(app, host="0.0.0.0", port=8000)