Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

CLI commands for creating OpenAI Assistants #359

Draft
wants to merge 5 commits into
base: main
Choose a base branch
from
Draft

Conversation

jlewi
Copy link
Owner

@jlewi jlewi commented Jan 2, 2025

We'd like to create a really good story for integrating with technical documentation. If you have technical documentation you'd like to "chat your docs". To experiment with that we can use OpenAI Assistants.

An OpenAI Assistant can answer queries using RAG using a bunch of files you uploaded. The advantage of using OpenAI Assistant is it automatically handles

  • Segmenting and chunking documents
  • VectorDatabase
  • RAG

This PR contains some CLI commands to

  • Create an Assistant from a YAML file
  • Create a Vector store from a YAML file
  • Sync the files in a directory to OpenAI

@jlewi jlewi marked this pull request as draft January 2, 2025 00:28
Copy link

netlify bot commented Jan 2, 2025

Deploy Preview for foyle canceled.

Name Link
🔨 Latest commit c2f04d3
🔍 Latest deploy log https://app.netlify.com/sites/foyle/deploys/6776c2fd167d2100080215a9

@jlewi
Copy link
Owner Author

jlewi commented Jan 2, 2025

Code is pretty rough in its current state.
It doesn't properly handle resyncing changes to OpenAI. This is partly due to limitations in the API. There's no way with the existing API to easily track what version of a file we have.
We also depend on a fork of the go-openai client
sashabaranov/go-openai#919

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant