解决Open WebU无法显示基于OpenAI API接口的推理内容的问题

解决方案

把reasoning content的东西移到content中来 并在reasoning时，手动加上标签。具体做法是截获第三方api返回的stream，并修改其中的内容，再移交给open webUI处理。

在backend\open_webui\routers\openai.py中 找到 generate_chat_completion 这个函数
在

r = Nonesession = Nonestreaming = Falseresponse = None

下方 增加截获函数 这个方案适用于 火山 百炼 vLLM我没试过，但是思路是一样的，根据vLLM返回的chunk内容，把reasoning的部分贴到content中去就能正常显示了。

async def modify_stream_content(original_stream):start_reasoning = Trueend_reasoning = True# 逐块处理流式内容async for chunk in original_stream:# 示例：修改 chunk 内容（假设 chunk 是 JSON 字符串）try:# 1. 解码字节流为字符串decoded_chunk = chunk.decode('utf-8').lstrip('data: ').strip()# 2. 解析 JSON（根据实际格式调整）chunk_data = json.loads(decoded_chunk)# 3. 修改内容if "choices" in chunk_data and len(chunk_data["choices"]) > 0:delta = chunk_data["choices"][0].get("delta", {})# print(delta)if delta["content"] == None:delta["content"] = ""if "reasoning_content" in delta and delta["reasoning_content"] == None:delta["reasoning_content"] = ""if delta["content"] == "":if start_reasoning:delta["content"] = "<think>" + delta["content"] + delta["reasoning_content"]start_reasoning = Falseelse:delta["content"] = delta["content"] + delta["reasoning_content"]else:if end_reasoning:delta["content"] = "</think>" + delta["content"]end_reasoning = False# print(delta)# 4. 重新编码为字节流modified_chunk = f"data: {json.dumps(chunk_data)}\n\n".encode('utf-8')except (json.JSONDecodeError, KeyError) as e:# 处理错误（可选：记录日志或跳过）modified_chunk = chunk  # 保留原始数据# 5. 返回修改后的 chunkyield modified_chunk

在下方，if "text/event-stream" in r.headers.get("Content-Type", ""): 分支里。调用截获函数并返回

 # Check if response is SSEif "text/event-stream" in r.headers.get("Content-Type", ""):streaming = True# 调用截获函数modified_stream = modify_stream_content(r.content)return StreamingResponse(# r.content,modified_stream,status_code=r.status,headers=dict(r.headers),background=BackgroundTask(cleanup_response, response=r, session=session),)