[Python] langchain / Chroma Process finished with exit code -1073741819 (0xC0000005) with

Discussão em 'Python' iniciado por Stack, Janeiro 24, 2025.

  1. Stack

    Stack Membro Participativo

    I am stumped with this problem

    chunks = []
    for path in file_paths: # path is a string filepath to a csv
    chunks.extend(self.chunk_data(path))
    chunks = filter_complex_metadata(chunks)
    # add all relevant documents to chunks
    # creates a unique cache for this dataset
    cache_dir_name = "local_cache"
    if not os.path.exists(cache_dir_name):
    os.makedirs(cache_dir_name)
    self.vector_store = Chroma.from_documents(documents=chunks,
    embedding=FastEmbedEmbeddings(model_name="BAAI/bge-small-en",
    cache_dir=cache_dir_name)) # crashes here


    When it gets to the end it throws the following error:


    Fetching 5 files: 0%| | 0/5 [00:00<?, ?it/s]C:\Users\...\venv\Lib\site-packages\huggingface_hub\file_download.py:140: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\Users\...\cache\models--Qdrant--bge-small-en. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
    To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
    warnings.warn(message)
    Fetching 5 files: 100%|██████████| 5/5 [00:05<00:00, 1.18s/it]

    Process finished with exit code -1073741819 (0xC0000005)


    The weird thing is this code was working fine before. Then I cloned a new repo, reinstalled all dependencies, and now it is not. I am afraid it might be for some reason external to the codebase, however it is at the Chroma.from_documents where it fails.

    The issue is exit code 0xC0000005 is an access violation, as far as I can tell, and this is really hard to debug..

    Update: I activated developer mode in windows, now it still says Process finished with exit code -1073741819 (0xC0000005) at the same point but with no warnings...

    Continue reading...

Compartilhe esta Página