How to install Unstructured for Langchain Document loaders. Langchain Unstructured tutorial

These installation steps for unstructured enables document loader to work with all regular files like txt, md, py and most importantly PDFs. You can also extract text out of images which is super cool. Also reads text our of any given list of URLs.

#langchain #langchaintutorial #langchainhowto

[echohive]

I hope you will find this video helpful.

[jaysonp]

I've been all over youtube and going back and forth with Chat GPT to get this installed. Your tutorial was the only one I've found that works. Thank you so much! PS: You have a new patreon sub :)

[goldengrapeorg]

Very helpful, I wanted to try chat your data before and got stuck in installing Unstructured for Langchain Document loaders at the beginning.

[ravisawhney]

Hi, how can I load in ms xlsx and doc files? struggling with the libreoffice process. Txs

[himanshushrivastava]

Thanks for the tutorial dude! By understandinng your tutorial, I was able to develop QA bot that can provide answers from a given document. However, this chatbot is limited to the document’s information only. I want to create a chatbot that can integrate its own data with the document’s data. How can I achieve this?

[luiscarlospxr]

After following every step on the video, I obtained this eror once and once again:

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for pycocotools
Failed to build pycocotools
ERROR: Could not build wheels for pycocotools, which is required to install pyproject.toml-based projects



PLEASE HELP <3

[OscarFonsecaQ]

I suggest you to try with PaddleOCR instead of tesseract

[danquixote]

I wish I had found this video before wasting 2 hours. New to coding and my one main gripe is how user 'unfriendly' all the set up steps are. Google colab seems like the best option at the moment. On the plus side, we have amazing coding communities that seem happy to offer advice and support along the way. Thanks.

[juliusgiron]

Echohive, looking to sub. Do you have examples of how to connect chatgpt to postgres?

[nuclear_AI]

sorry to be a pain but do you have any advice for the following?
Im coming across the below error whilst attempting to pip install unstructured[local-inference]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for pycocotools
Successfully built unstructured-inference python-docx python-pptx unstructured iopath antlr4-python3-runtime
Failed to build pycocotools
ERROR: Could not build wheels for pycocotools, which is required to install pyproject.toml-based projects

[BatBallBites]

i have downloaded different versions of poppler but there is not bin directory

[AIinIM]

I have an error: ERROR: Could not build wheels for pycocotools, which is required to install pyproject.toml-based projects. Trying everything what I can find on the Internet, but nothing seems to work. Tried with both Python 3.10 and 3.9 and still get this error.

[Alex-pybs]

I keep running into the error ModuleNotFoundError: No module named 'torch'

[lnt]

Unstructured langchain doc link is dead, unfortunately

[kevinkate]

Poppler site is closed! can you help me please