fix(embedding): surface upstream errors instead of silent timeout#1910
Merged
Conversation
PR Reviewer Guide 🔍Here are some key observations to aid the review process:
|
PR Code Suggestions ✨No code suggestions found for the PR. |
The /ready endpoint checks AGFS, VectorDB, APIKeyManager, and Ollama but not the embedding provider. When the provider is down (500 or unreachable), ov find silently times out with a misleading "Network error" and neither ov health nor ov ready surfaces the real cause. Add an embedding probe (single-token embed with 10s timeout) so that ov ready reports a broken embedding backend before any search is attempted. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
10022e6 to
8163183
Compare
MaojiaSheng
approved these changes
May 15, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
ov findshows misleadingNetwork error: HTTP request failedbecause the Rust CLI times out (60s) before the Python server finishes retrying the embedding call (3+ minutes with SDK retries compounding on top of OV retries). Neitherov healthnorov readychecks embedding connectivity, so users have no way to detect a broken provider.max_retries=0) on the OpenAI embedding client — the server now fails fast enough for the CLI to receive the actual errorHierarchicalRetriever.retrieve()aroundembed_compat()with provider/model context in the error message, so users see exactly which backend is broken/readyendpoint (10s timeout) —ov readynow catches a broken embedding provider before any search is attemptedTest plan
ov readyshould reportembedding: error: ...ov findwith broken provider → should return specific error instead of "Network error"🤖 Generated with Claude Code