This repository has been archived by the owner on Jul 11, 2023. It is now read-only.
First draft: supabase(pg vector) and promptable example to chat with docs #49
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
mayooear
changed the title
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hey @cfortuner it's Mayo here. As discussed, here's the draft of the supabase x promptable example starter kit to "chat with docs." I haven't fully implemented the logic or frontend UI yet, but I've laid out the architecture and config for us to discuss as I make changes.
The current architecture requires first running two scripts
scrapeandembed, to extract text from a given url (docs website) then embed those docs into supabase usingpg vectors.Afterwards, when there is a question asked on the frontend, it is sent to
api/search-docswhere the user's request is embedded and then supabase performs a similarity search to retrieve similar docs.At this point we can either choose to display these similar docs or send them to openai as context to generate a final generated answer.
Let me know your thoughts on the example usecase, current layout and what role you'd like promptable to play in this process. For example, if you'd prefer we load existing docs on disk instead of scraping a website etc.