feat: Add OpenAI Rate limiting #1805
Merged
Conversation
This file contains 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
|
Looks like this is adding rate limiting to both the OpenAI model and the Bedrock model. Why not add to all models? |
@axiomofjoy I checked the other models and we were not catching any kind of rate limiting error in their implementations so I think it's out of scope to try and add that functionality in this PR |
axiomofjoy
reviewed
Nov 27, 2023
axiomofjoy
approved these changes
Nov 29, 2023
mikeldking
pushed a commit
that referenced
this pull request
Dec 1, 2023
* Implement adaptive rate limiter for OpenAI * Add adaptive rate limiter to Bedrock model * Use a sensible default maximum request rate * Ruff 🐶 * Mark test as xfail after llama_index update * Do not retry on rate limit errors with tenacity * Remove xfail after llama_index version lock * Use events and locks instead of nesting asyncio.run * Ensure that events are always set after rate limit handling * Retry on httpx ReadTimeout errors * Update rate limiters with verbose generation info * Improve end of queue handling in AsyncExecutor * improve types to remove the need for casts (#1817) * Improve interrupt handling * Exit early from queue.join on termination events * Properly cancel running tasks * Add pytest-asyncio to hatch env * Do not await cancelled tasks * Improve task_done marking logic * Increase default concurrency --------- Co-authored-by: Xander Song <axiomofjoy@gmail.com>
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Outdated suggestions cannot be applied.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.
resolves #1663
Implements an adaptive rate limiter that will gradually increase the rate of submission until a rate limit error is encountered, it will then lower the rate limit and block until the rate limited request can be completed.