(copied from OP: #12054)

End-to-end POC for DocsGPT project.

Pre-reqs

Config/secrets

Updated your ./apps/docs/.env.local file with some keys (use .env.sample as a base):

NEXT_PUBLIC_SUPABASE_URL=http://localhost:54321
NEXT_PUBLIC_SUPABASE_ANON_KEY=
OPENAI_KEY=

# TODO: merge META_SUPABASE_URL with NEXT_PUBLIC_SUPABASE_URL
# Currently separate in order to run edge function locally
# (runs in container with different network namespace)
META_SUPABASE_URL=http://supabase_kong_supabase:8000
META_SUPABASE_SERVICE_KEY=

To get the OpenAI key, you will need an OpenAI account and create a key here:
https://beta.openai.com/account/api-keys

Run local Supabase stack

We have extended ./supabase to include DB migrations required for DocsGPT. Be sure to run a local Supabase stack. From the project root:

$ supabase start

Generate embeddings (first time only)

The first time you will need to pre-generate embeddings for the documents (guide-only for now). Simply call the following script from ./apps/docs:

$ npm run build:embeddings

You can safely call this multiple times if you like - it uses a checksum to determine whether or not it has already generated an embedding for each document and will skip if its already there.

In the future this will most likely be called from a CI pipeline.

Note: This does have a (very small) cost every time you run. It queries OpenAI's embeddings endpoint to generate embeddings. If you find yourself constantly restarting your Postgres instance, you can use the following commands to quickly backup/restore without re-generating embeddings every time:

Backup:

pg_dump --column-inserts --data-only -h localhost -p 54322 -U postgres -t page -t page_section > backup.sql

Restore:

psql -h localhost -p 54322 -U postgres -q -f backup.sql

Run edge function

A server side edge function was built to handle DocGPT queries (search embeddings in Postgres, inject as context in prompt, send prompt request to OpenAI).

You will need to run this function locally and pass in the above environment variables. From the project root:

$ supabase functions serve clippy-search --env-file ./apps/docs/.env

Run docs project

Of course we will need to run the docs project to use the frontend. From ./apps/docs:

$ npm run dev