frostmiku/chatglm-langchain

ChatGLM 6B 的模型与UI，通过 LangChain 与向量匹配实现本地知识库问答，支持流式输出

Hi there 👋

chatglm-langchain's Issues

运行问题

请问出现下面错误是为什么呢？
no sentence-transformers model found with name /home/hc/.cache/torch/sentence_transformers/GanymedeNil_text2vec-large-chinese. Creating a new one with MEAN pooling.
demo.md 未能成功加载
2023-05-21 16:39:31.580 Uncaught app exception
Traceback (most recent call last):
File "/home/hc/anaconda3/envs/zwtpy39/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 565, in _run_script
exec(code, module.dict)
File "/home/hc/zwt/qa/ChatGLM-LangChain-main/ui.py", line 47, in
st.session_state.vecdb = init_knowledge_vector_store(
File "/home/hc/zwt/qa/ChatGLM-LangChain-main/utils.py", line 48, in init_knowledge_vector_store
vector_store = FAISS.from_documents(docs, embeddings)
File "/home/hc/anaconda3/envs/zwtpy39/lib/python3.10/site-packages/langchain/vectorstores/base.py", line 218, in from_documents
return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)
File "/home/hc/anaconda3/envs/zwtpy39/lib/python3.10/site-packages/langchain/vectorstores/faiss.py", line 368, in from_texts
return cls.__from(
File "/home/hc/anaconda3/envs/zwtpy39/lib/python3.10/site-packages/langchain/vectorstores/faiss.py", line 330, in __from
index = faiss.IndexFlatL2(len(embeddings[0]))
IndexError: list index out of range

启动后总报内存不足，但是明明有剩余6G可用

算了下 134217728 bytes只合约128M内存，辛苦大佬帮忙看下

(langc) PS G:\files\dev\ChatGLM-LangChain> streamlit run ui.py --browser.gatherUsageStats False

  You can now view your Streamlit app in your browser.

  Local URL: http://localhost:8501
  Network URL: http://10.168.78.14:8501

Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Symbol cudaLaunchKernel not found in C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common\cudart64_65.dll
2023-07-18 10:18:44.397 Uncaught app exception
Traceback (most recent call last):
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 263, in _get_or_create_cached_value
    cached_result = cache.read_result(value_key)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\caching\cache_resource_api.py", line 500, in read_result
    raise CacheKeyNotFoundError()
streamlit.runtime.caching.cache_errors.CacheKeyNotFoundError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 311, in _handle_cache_miss
    cached_result = cache.read_result(value_key)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\caching\cache_resource_api.py", line 500, in read_result
    raise CacheKeyNotFoundError()
streamlit.runtime.caching.cache_errors.CacheKeyNotFoundError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 552, in _run_script
    exec(code, module.__dict__)
  File "G:\files\dev\ChatGLM-LangChain\ui.py", line 41, in <module>
    tokenizer, model, embeddings = get_model()
                                   ^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 211, in wrapper
    return cached_func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 240, in __call__
    return self._get_or_create_cached_value(args, kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 266, in _get_or_create_cached_value
    return self._handle_cache_miss(cache, value_key, func_args, func_kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 320, in _handle_cache_miss
    computed_value = self._info.func(*func_args, **func_kwargs)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "G:\files\dev\ChatGLM-LangChain\ui.py", line 24, in get_model
    model = AutoModel.from_pretrained(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\transformers\models\auto\auto_factory.py", line 459, in from_pretrained
    return model_class.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\transformers\modeling_utils.py", line 2362, in from_pretrained
    model = cls(config, *model_args, **model_kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\will/.cache\huggingface\modules\transformers_modules\silver\chatglm-6b-int4-slim\c9ec05795cbcdd8be88b1c7b4e6a53db24477bc5\modeling_chatglm.py", line 1019, in __init__
    self.transformer = ChatGLMModel(config)
                       ^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\will/.cache\huggingface\modules\transformers_modules\silver\chatglm-6b-int4-slim\c9ec05795cbcdd8be88b1c7b4e6a53db24477bc5\modeling_chatglm.py", line 825, in __init__
    [get_layer(layer_id) for layer_id in range(self.num_layers)]
  File "C:\Users\will/.cache\huggingface\modules\transformers_modules\silver\chatglm-6b-int4-slim\c9ec05795cbcdd8be88b1c7b4e6a53db24477bc5\modeling_chatglm.py", line 825, in <listcomp>
    [get_layer(layer_id) for layer_id in range(self.num_layers)]
     ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\will/.cache\huggingface\modules\transformers_modules\silver\chatglm-6b-int4-slim\c9ec05795cbcdd8be88b1c7b4e6a53db24477bc5\modeling_chatglm.py", line 811, in get_layer
    return GLMBlock(
           ^^^^^^^^^
  File "C:\Users\will/.cache\huggingface\modules\transformers_modules\silver\chatglm-6b-int4-slim\c9ec05795cbcdd8be88b1c7b4e6a53db24477bc5\modeling_chatglm.py", line 586, in __init__
    self.mlp = GLU(
               ^^^^
  File "C:\Users\will/.cache\huggingface\modules\transformers_modules\silver\chatglm-6b-int4-slim\c9ec05795cbcdd8be88b1c7b4e6a53db24477bc5\modeling_chatglm.py", line 521, in __init__
    self.dense_4h_to_h = skip_init(
                         ^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\torch\nn\utils\init.py", line 52, in skip_init
    return module_cls(*args, **kwargs).to_empty(device=final_device)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\torch\nn\modules\module.py", line 1024, in to_empty
    return self._apply(lambda t: torch.empty_like(t, device=device))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\torch\nn\modules\module.py", line 820, in _apply
    param_applied = fn(param)
                    ^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\torch\nn\modules\module.py", line 1024, in <lambda>
    return self._apply(lambda t: torch.empty_like(t, device=device))
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\anaconda3\envs\langc\Lib\site-packages\torch\_refs\__init__.py", line 4254, in empty_like
    return torch.empty_strided(
           ^^^^^^^^^^^^^^^^^^^^
RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 134217728 bytes.

windows utf-8乱码

疑似是UnstructuredFileLoader这个方法的问题