I've also been experimenting with generating embeddings from repos/docs, and even though embeddings are cheap, I find myself making sure I record every last one to disk so I don't have to hit the API again for that piece of content.

It strikes me as wasteful to potentially generate them multiple times for the same repo. Is it against TOS to publicly share generated embeddings and collaborate to build a database of codebase (and/or more) vectors? Is there anything like that yet?

Of course code changes over time, but they'd be useful for e.g. a stable release of a library. For big codebases, it'd also be more economical to re-embed only changed files (or functions/classes, more granularly).

Introducing our Q&A Chatbot Creator, a powerful tool that automates the process of creating a chatbot for your Github repositories. With just a few simple steps, you can create your own state-of-the-art Q&A chatbot with ease. Using LangChain and Gradio, the tool generates the FAISS embedding vector space for you, and provides a seamless integration with OpenAI API and Huggingface Tokens. The end result is a high-quality chatbot that you can use and customize to suit your needs. Give it a try today and experience the power of automation in chatbot creation!

Hi! I have a fee important questions before using this :)

Namely, is there some way to estimate how much it will cost in OpenAI credits.

My repo has a vendor folder with thousands of dependency files. Will each of these be sent off to OpenAI for embeddings?

Would you kindly provide any and all info, can’t wait to try this but I’m worried it’ll cost way more than I’m anticipating.