How could load with word, excel, ppt

[vecyang1]

No description provided.

[spacepirate0001]

Support for docs, csv, txt, json coming in PR #246

[ViniciusTheCoder]

Support for docs, csv, txt, json coming in PR #246

Just a question: to ingest the html I just have do paste the HTML inside the docs folder and run ingest?

[davideuler]

This project has support of docx, pptx, csv, txt, etc. With open source chromadb instread of Pinecone.
gpt4-pdf-chatbot-langchain-chromadb

[dosubot]

Hi, @vecyang1! I'm Dosu, and I'm helping the gpt4-pdf-chatbot-langchain team manage their backlog. I wanted to let you know that we are marking this issue as stale.

From what I understand, the issue is about finding a way to load files with the extensions .docx, .xlsx, and .pptx in a GitHub repository. It seems that support for these file types is coming in PR #246, as mentioned by spacepirate0001. There was also a question from ViniciusTheCoder about ingesting HTML files. Lastly, davideuler mentioned a project that has support for docx, pptx, csv, txt, etc. using open source chromadb instead of Pinecone.

Before we close this issue, we wanted to check with you if it is still relevant to the latest version of the gpt4-pdf-chatbot-langchain repository. If it is, please let us know by commenting on the issue. Otherwise, feel free to close the issue yourself or it will be automatically closed in 7 days.

Thank you for your understanding and contribution to the gpt4-pdf-chatbot-langchain repository!