I built an open source website that lets you upload large files, such as in-depth novels or academic papers, and ask ChatGPT questions based on your specific knowledge base. So far, I've tested it with long books like the Odyssey and random research papers that I like, and it works shockingly well.

• vault-ai

  80 3,225 5.7 JavaScript

  OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.

I deployed the code here if you want to play around with it: https://vault.pash.city. Feel free to upload any non-sensitive or non-personal documents and experiment with the site. That being said, I strongly recommend you run the code locally and use it at your own pace with no size/length limitations (though be careful with your OpenAI API usage!)

• vault-ai

  1 1 4.5 JavaScript

  OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, etc) using a simple React frontend. (by Skordio)

For anyone wanting to do this themselves, WSL(windows subsystem for Linux) is great for setting this up on a windows pc. There were a few things I needed to change in the config though - they’re on my fork

• SurveyJS

  surveyjs.io featured

  Open-Source JSON Form Builder to Create Dynamic Forms Right in Your App. With SurveyJS form UI libraries, you can build and style forms in a fully-integrated drag & drop form builder, render them in your JS app, and store form submission data in any backend, inc. PHP, ASP.NET Core, and Node.js.

  

• hnsqlite

  6 143 5.5 Python

  hnsqlite integrates hnswlib and sqlite for simple text embedding search

  

We are built on open core https://github.com/jiggy-ai. Our open source hnsqlite is light weight, easy to use. And best of all, we make it easy for you to get your data out of JiggyBase. You can download a sqlite file that contains your document text data, metadata, embedding vectors, and embedding index. This can be used directly in the open source hnsqlite package.

Suggest a related project