feat: build hosted embeddings and activate complete search generations - #1
Closed
salmonumbrella wants to merge 1 commit into
Closed
salmonumbrella wants to merge 1 commit into
salmonumbrella wants to merge 1 commit into
Conversation
7 tasks
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Superseded by kenn-io#1736, opened upstream at the same feature commit.
Hosted PostgreSQL can now build embeddings from projected sessions and serve semantic and hybrid search without a local SQLite archive. The server owns encoding, durable retries, and current-source coverage. Unchanged chunks can reuse vector values after a raw append replaces their physical session IDs.
Operators provision a versioned generation with an owner connection, then enable its worker on the restricted runtime target. A rebuild keeps the previous generation serving until the replacement has complete coverage. Each search uses one generation and its matching encoder throughout the request. Usage-only mode clears derived embedding content; keyword search remains available when the active embedding profile cannot be used.
This implements item 5 of kenn-io#1352 and stacks on kenn-io#1730. The parent PR must land first. Generation storage, worker lifecycle, and configured-runtime acceptance tests are the main review areas. Retention and garbage collection remain part of roadmap item 6.