-
Notifications
You must be signed in to change notification settings - Fork 1
added health endpoint #5
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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 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Outdated suggestions cannot be applied.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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The handler always returns
200 OKregardless of whether theEmbeddingClientis actually initialised and able to serve requests. If the model loading step (EmbeddingClient::new) succeeded at startup but the underlying inference backend later becomes unavailable, orchestrators relying on this endpoint (e.g. Kubernetes liveness/readiness probes, load-balancer health checks) will continue routing traffic to the instance even though it cannot process embeddings. Consider acceptingState(state): State<AppState>and doing a lightweight check — even a no-op call that verifies the client is reachable — and returning503 Service Unavailablewhen it fails.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@greptile it wouldn't be reachable if the client is loaded yet. For starting the server the models must be loaded first and that is the point of adding this endpoint
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You're right. Looking at
main(),EmbeddingClient::new(config)?is called synchronously before the router is built and the server starts listening. If that fails, the process exits — the server never binds. So a reachable/healthendpoint does imply the client initialized successfully.My original concern was valid in the abstract (runtime degradation after startup), but your point stands for this specific use case: if
/healthresponds at all, the client was loaded. That's a reasonable invariant for a simple liveness check.Fair enough — the current implementation is intentional and correct for its purpose.
Shall I remember this as a rule: "shallow health checks that just return
200 OKare acceptable when the server cannot start without successful initialization, as reachability already implies readiness"?Tip: You can customize Greptile's behavior for this repo with
.greptile/rules.mdand.greptile/config.json.