学编程的小虎: 报错信息为： Traceback (most recent call last): File "/data/workspace/ollama-python-serve/1.py", line 34, in for chunk in response: File "/data/apps/anaconda/2024.02-1/lib/python3.11/site-packages/langchain_core/runnables/base.py", line 4748, in stream yield from self.bound.stream( File "/data/apps/anaconda/2024.02-1/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 265, in stream raise e File "/data/apps/anaconda/2024.02-1/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 245, in stream for chunk in self._stream(messages, stop=stop, **kwargs): File "/data/apps/anaconda/2024.02-1/lib/python3.11/site-packages/langchain_community/chat_models/ollama.py", line 344, in _stream for stream_resp in self._create_chat_stream(messages, stop, **kwargs): File "/data/apps/anaconda/2024.02-1/lib/python3.11/site-packages/langchain_community/c

旭日跑马踏云飞: 报错信息是啥。不过stream这个调用在这里并没有function call，回头我再研究一下。我看你使用的qwen，也可以参考这篇https://blog.csdn.net/tirestay/article/details/140050280#t2 通过qwen-agent来调用，跟openai的调用方式一致，通过参数stream就支持流式输出。

学编程的小虎: 如果是用invoke就可以

学编程的小虎: 一样的代码，我这里报错： from langchain_experimental.llms.ollama_functions import OllamaFunctions # 第一步：获取大模型 client = OllamaFunctions(model='qwen:32b', base_url='http://localhost:11434', format='json') # 第二步，定义业务函数 get_current_weather = { 'name': 'get_current_weather', 'description': 'Get the current weather in a given location', 'parameters': { 'type': 'object', 'properties': { 'city': { 'type': 'string', 'description': 'The city and state, e.g. San Francisco, CA', } }, 'required': ['city'], } } tools = [get_current_weather] # 第三步,通过业务处理函数描述，把业务函数绑定到大模型上 client_with_tool = client.bind_tools( tools=tools ) # 第四步，发起交互 message = "What's the weather like in San Francisco?" response = client_with_tool.stream(message) print(response) for chunk in response: print(chunk.content, end="", flush=True)

旭日跑马踏云飞: 也可以查看https://blog.csdn.net/tirestay/article/details/140050280 这篇，讲述了三种场景。