Update main.py

main.py

@@ -68,11 +68,11 @@ async def chat(prompt = "I want to download a dataset from GCS"):
 
 
 class ChatCompletionRequest(BaseModel):
-    prompt: str
+    messages: str
 
 @app.post("/v1/chat/completions")
 async def chat(request: ChatCompletionRequest, response_mode=None):
-    tokens = llm.tokenize(request.prompt)
+    tokens = llm.tokenize(request.messages.join(' '))
     async def server_sent_events(chat_chunks, llm):
         for chat_chunk in llm.generate(chat_chunks):
             yield llm.detokenize(chat_chunk)