feat: add rate limit to gemini client #40
Merged
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
Signed-off-by: Keming <[email protected]>
Contributor
There was a problem hiding this comment.
Pull Request Overview
Adds a configurable rate-limiting transport for HTTPX to throttle Gemini API requests
- Introduces
RateLimitTransportinutils.pyto enforce a max requests-per-second interval - Updates multiple clients (
extract,evaluate,entity,chunk,augment) to use the new transport - Sets specific rate limits per component (16 rps for most calls, 1 rps for paid-tier embeddings)
Reviewed Changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| vechord/utils.py | New RateLimitTransport class implements per-second throttling |
| vechord/extract.py | Injects rate-limited transport into the HTML parser client |
| vechord/evaluate.py | Applies rate-limited transport in evaluator HTTP client |
| vechord/entity.py | Adds rate-limited transport to entity recognizer client |
| vechord/embedding.py | Uses slower limit for paid-tier embeddings |
| vechord/chunk.py | Throttles chunking client with rate limit |
| vechord/augment.py | Integrates rate-limited transport into augmenter client |
Comments suppressed due to low confidence (2)
vechord/embedding.py:95
- The comment miscalculates the conversion: 10 RPM equals approximately 0.1667 rps, not 0.1 rps. Please update the comment to reflect the correct rate.
# Paid Tier only has 10 RPM, this should be set to 0.1, but it's too slow
vechord/utils.py:14
- There are no unit tests covering
RateLimitTransporttiming behavior. Adding tests to validate the interval enforcement and request spacing would help catch regressions.
class RateLimitTransport(httpx.AsyncHTTPTransport):
Signed-off-by: Keming <[email protected]>
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.
According to: https://ai.google.dev/gemini-api/docs/rate-limits#tier-1