Skip to content

[DEV-15246] - add generate embeddings command - #4746

Open
zachflanders-frb wants to merge 1 commit into
ftr/dev-15246-embedding-mixinfrom
ftr/dev-15246-generate_embeddings_command
Open

[DEV-15246] - add generate embeddings command#4746
zachflanders-frb wants to merge 1 commit into
ftr/dev-15246-embedding-mixinfrom
ftr/dev-15246-generate_embeddings_command

Conversation

@zachflanders-frb

@zachflanders-frb zachflanders-frb commented Aug 18, 2026

Copy link
Copy Markdown
Contributor

Description:

This is PR 3/3 for this feature. The first PR added the pgvector extension to the app, the second PR adds the EmbeddingMixin and the fields on the models that should have embeddings generated. This PR adds the django management command to generate these embeddings.

Technical Details:

These embeddings will potentially take several hours to generate, but will only need to be generated once. The embeddings are auto generated on object save or creation. The existing loaders (e.g. load_naics) will generate embeddings for new records created with get_or_create, but updated or bulk_update records bypass the save method and will need to be manually regenerated. If the embedding fails the save will continue without an exception being raised, so it will still work in the legacy aws environment if bedrock is not available.

Requirements for PR Merge:

  1. Unit & integration tests updated
  2. Appropriate Operations ticket(s) created
  3. Jira Ticket(s)
    1. DEV-15246

Explain N/A in above checklist:

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