Traceback (most recent call last):
  File "d:\my_code\llm_learning\Langchain_RAG\t4_llamaindex_local_rag.py", line 281, in <module>
    main()
  File "d:\my_code\llm_learning\Langchain_RAG\t4_llamaindex_local_rag.py", line 269, in main
    answer = rag.query(question)
  File "d:\my_code\llm_learning\Langchain_RAG\t4_llamaindex_local_rag.py", line 174, in query
    response = query_engine.query(question)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index_instrumentation\dispatcher.py", line 335, in wrapper
    result = func(*args, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\base\base_query_engine.py", line 44, in query
    query_result = self._query(str_or_query_bundle)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index_instrumentation\dispatcher.py", line 335, in wrapper
    result = func(*args, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\query_engine\retriever_query_engine.py", line 197, in _query       
    response = self._response_synthesizer.synthesize(
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index_instrumentation\dispatcher.py", line 335, in wrapper
    result = func(*args, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\response_synthesizers\base.py", line 235, in synthesize
    response_str = self.get_response(
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index_instrumentation\dispatcher.py", line 335, in wrapper
    result = func(*args, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\response_synthesizers\compact_and_refine.py", line 43, in get_response
    return super().get_response(
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index_instrumentation\dispatcher.py", line 335, in wrapper
    result = func(*args, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\response_synthesizers\refine.py", line 179, in get_response        
    response = self._give_response_single(
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\response_synthesizers\refine.py", line 241, in _give_response_single
    program(
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index_instrumentation\dispatcher.py", line 335, in wrapper
    result = func(*args, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\response_synthesizers\refine.py", line 85, in __call__
    answer = self._llm.predict(
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index_instrumentation\dispatcher.py", line 335, in wrapper
    result = func(*args, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\llms\llm.py", line 623, in predict
    chat_response = self.chat(messages)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index_instrumentation\dispatcher.py", line 335, in wrapper
    result = func(*args, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\core\llms\callbacks.py", line 175, in wrapped_llm_chat
    f_return_val = f(_self, messages, **kwargs)
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\llama_index\llms\ollama\base.py", line 394, in chat
    response = self.client.chat(
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\ollama\_client.py", line 351, in chat
    return self._request(
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\ollama\_client.py", line 189, in _request
    return cls(**self._request_raw(*args, **kwargs).json())
  File "D:\envs\miniconda\envs\vis2\lib\site-packages\ollama\_client.py", line 133, in _request_raw
    raise ResponseError(e.response.text, e.response.status_code) from None
ollama._types.ResponseError: llama runner process has terminated: exit status 2 (status code: 500)

使用LlamaIndex + 本地LLM实现本地RAG的时候报上面的错误，一直以为是ollama端口占用报错。后面发现是llama3.1:8b太大报的错。但奇怪的是使用langchain+llm+faiss用的也是llama3.1:8b模型，跑起来没啥问题，才占了6G（显卡12G)