Update main.py

main.py

@@ -32,7 +32,7 @@ class ChatCompletionRequest(BaseModel):
 
 @app.post("/v1/chat/completions")
 async def chat(request: ChatCompletionRequest, response_mode=None):
-    tokens = llm.tokenize(prompt)
+    tokens = llm.tokenize(request.prompt)
     async def server_sent_events(chat_chunks, llm):
         yield prompt
         for chat_chunk in llm.generate(chat_chunks):