update oai

qwen_agent/llm/qwen_oai.py

@@ -326,7 +326,7 @@ def create_chat_completion(request: ChatCompletionRequest):
         if request.functions:
             raise Exception("Invalid request: Function calling is not yet implemented for stream mode.")
         generate = predict(query, history, request.model, stop_words, gen_kwargs)
-        return generate
+        return json.loads(generate)
         # return EventSourceResponse(generate, media_type="text/event-stream")
 
     stop_words_ids = [tokenizer.encode(s) for s in stop_words] if stop_words else None