Add limit on concurrent requests for doc-qa #64
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
tholor
approved these changes
Apr 17, 2020
|
|
||
| resp_time = round(time.time() - t1, 2) | ||
| logger.info({"time": resp_time, "request": request.json(), "results": results}) | ||
| with doc_qa_limiter.run(): |
There was a problem hiding this comment.
It would be nicer to make a decorator out of this, but if this requires bigger changes we can do it later in a separate PR.
masci
pushed a commit
that referenced
this pull request
Nov 27, 2023
Remove Component's I/O type checks at run time
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Outdated suggestions cannot be applied.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.
This PR adds a
RequestLimiterclass to limit concurrent requests for a given endpoint.In the case of question answering on very large documents, the requests can take several seconds. With the default FastAPI/Uvicorn/Gunicorn deployment, the requests get processed concurrently on a GPU, slowing down all the requests. To provide consistent user experience, the API can respond with a server-busy error code if the in-process requests exceed the limit threshold.