Repository navigation
fix/import bank bounded batches - #5661
Merged
Merged
Conversation
…d batches (#5418) import-bank wrote every observation in one insert inside one transaction; on a large bank with 3072-dim embeddings that bind message passed PostgreSQL's 1 GB protocol limit and the connection was reset, leaving the target with facts and no observations. - Observations are embedded and inserted _OBSERVATION_BATCH_SIZE (500) at a time, one transaction per batch; the Postgres store now accumulates outcome.imported across calls instead of overwriting it. - Document batches also close at _FACT_BATCH_SIZE (2000) facts, so fifty fact-heavy documents can no longer outgrow the same limit. A single document still rides whole (its facts share one transaction). Closes #5418
…g comments - test_import_observations_in_bounded_batches counts via list_memory_units instead of a raw SELECT on memory_units. - _EMBED_BATCH_SIZE comment no longer says observations arrive as one list. - Note that a mid-import failure leaves earlier observation batches, and that the import-bank retry starts over.
This was referenced Oct 16, 2026
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
RECALL_STRATEGY_BOOSTS=temporal:*no longer helps dated queries — recall@10 0.807 → 0.501 (0.10.0 → 0.10.2) #4939) (fix(recall): don't decay the post-rerank temporal boost by rank (#4939) #5295)source_fact_idsmatch no batch fact, and stamps their facts consolidated #5273) (fix(consolidation): pin source_fact_ids to the batch and report actions that cite none (#5273) #5307)