https://github.com/supabase/embeddings-generator

GitHub Action to generate embeddings from the markdown files in your repository.
https://github.com/supabase/embeddings-generator

embeddings postgres postgresql supabase vector

Last synced: 3 months ago
JSON representation

GitHub Action to generate embeddings from the markdown files in your repository.

• Host: GitHub
• URL: https://github.com/supabase/embeddings-generator
• Owner: supabase
• License: mit
• Created: 2023-05-25T04:43:02.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-01T20:25:52.000Z (9 months ago)
• Last Synced: 2024-04-13T21:54:14.364Z (9 months ago)
• Topics: embeddings, postgres, postgresql, supabase, vector
• Language: TypeScript
• Homepage: https://github.com/marketplace/actions/supabase-embeddings-generator
• Size: 1.39 MB
• Stars: 76
• Watchers: 17
• Forks: 13
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Codeowners: CODEOWNERS

Awesome Lists containing this project

README

        
# Supabase Embeddings Generator

A GitHub Action that converts your markdown files into embeddings and stores them in your Postgres/Supabase database, allowing you to perform vector similarity search inside your documentation and website.

This action is a companion to the [`headless-vector-search`](https://github.com/supabase/headless-vector-search) repo, which is used to store and retrieve the embeddings using [OpenAI](https://openai.com) and [Supabase](https://supabase.com).

## Usage

You can find this action on the [GitHub Marketplace](https://github.com/marketplace/actions/supabase-embeddings-generator).

In your knowledge base repository, create a new action called `.github/workflows/generate_embeddings.yml` with the following content:

```yml

name: 'generate_embeddings'

on: # run on main branch changes

  push:

    branches:

      - main

jobs:

  generate:

    runs-on: ubuntu-latest

    steps:

      - uses: actions/checkout@v3

      - uses: supabase/[email protected] # Find the latest version in the Marketplace

        with:

          supabase-url: 'https://your-project-ref.supabase.co'

          supabase-service-role-key: ${{ secrets.SUPABASE_SERVICE_ROLE_KEY }}

          openai-key: ${{ secrets.OPENAI_KEY }}

          docs-root-path: 'docs' # the path to the root of your md(x) files

```

Make sure to set `SUPABASE_SERVICE_ROLE_KEY`, and `OPENAI_KEY` as repository secrets in your repo settings (settings > secrets > actions).

See the instructions in the [`headless-vector-search`](https://github.com/supabase/headless-vector-search) for more information on how to query your database from your website.

## Developers

See details in [MAINTAINERS.md](https://github.com/supabase/embeddings-generator/blob/main/MAINTAINERS.md)

## License

[MIT](https://github.com/supabase/embeddings-generator/blob/main/LICENSE)