unstructured icon indicating copy to clipboard operation
unstructured copied to clipboard

File Not Found Error nlp/english-words.txt

Open taaha3244 opened this issue 10 months ago • 1 comments

Hello Everyone!!, I am trying to setup unstructured on google colab

I am facing a "FileNotFoundError: [Errno 2] No such file or directory: '/usr/local/lib/python3.10/dist-packages/unstructured/nlp/english-words.txt'"

**Code is as below ! pip install -U langchain openai qdrant-client langchain_openai langchain-experimental ! pip install "unstructured[all-docs]" pillow pydantic lxml pillow matplotlib tiktoken numpy !pip install popper utils tesseract-ocr
!pip install "detectron2@git+https://github.com/facebookresearch/[email protected]#egg=detectron2"

from langchain_text_splitters import CharacterTextSplitter from unstructured.partition.auto import partition

image

Will appreciate help

taaha3244 avatar Apr 05 '24 07:04 taaha3244

This was an issue with unstructured==0.13.1 but should be fixed as of 0.13.2 , initially tracked here: https://github.com/Unstructured-IO/unstructured/issues/2855 .

cragwolfe avatar Apr 05 '24 07:04 cragwolfe