TAN-6354 Support live clustering for nested topics #13030
Draft
Conversation
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
Add a new method to classify multiple ideas in parallel, with LLM requests parallelized but database operations kept sequential. This avoids tenant/DB issues by pre-computing all prompts before spawning threads. Also fix Idea#input_topics association to use lft instead of ordering (since InputTopic now uses acts_as_nested_set). Co-Authored-By: Claude Opus 4.5 <[email protected]>
Update the job to process batches of ideas using the parallel classification method. The classify_all_inputs_in_background! method now batches ideas into groups of 24, and each job processes its batch in parallel. For single-idea classification (e.g., on idea create/update), the job is called with an array of one idea ID. Co-Authored-By: Claude Opus 4.5 <[email protected]>
Collaborator
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Changelog