docs: correct embedding preflight batch sizes from 1 and 4 to 1 and 8 - #200
Open
detail-app[bot] wants to merge 1 commit into
Open
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
Sign up for freeto 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The embedding preflight's largest probe batch was bumped from 4 to 8
in commit 0dba1d1, which also updated
docs/ingestion.md. Two sibling living docs still claimed '1 and 4',
claiming developers/agents would test their gateway against a stale
batch size and pass when they shouldn't, or miss a preflight that
their gateway cannot handle a batch of 8.
A developer following docs/configuration.md to validate a new gateway
endpoint would probe only batch sizes 1 and 4, never exercising the
batch-of-8 path that ingestion actually issues at startup; the preflight
would pass locally but ingestion could still fail on the larger batch.
Introduced by commit 0dba1d1 (@WilliamAGH)
Doc Drift PRs can be configured here.