fix: use per-call sessions for embeddings to prevent timeout on large collections#420
Open
debugerman wants to merge 1 commit intotobi:mainfrom
Open
fix: use per-call sessions for embeddings to prevent timeout on large collections#420debugerman wants to merge 1 commit intotobi:mainfrom
debugerman wants to merge 1 commit intotobi:mainfrom
Conversation
… collections The old design wrapped the entire embedding loop in a single LLM session with a 30-minute maxDuration cap. For collections exceeding ~39k chunks, the session timer would fire mid-loop and all remaining embeddings would fail with SessionReleasedError. Each embed/embedBatch call now gets its own short-lived session with the default 10-minute timeout, which is more than sufficient for a single batch of ≤32 texts. Closes tobi#410
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The old design wrapped the entire embedding loop in a single LLM session with a 30-minute maxDuration cap. For collections exceeding ~39k chunks, the session timer would fire mid-loop and all remaining embeddings would fail with SessionReleasedError.
Each embed/embedBatch call now gets its own short-lived session with the default 10-minute timeout, which is more than sufficient for a single batch of ≤32 texts.
Closes #410