-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
add vespa + embedding timeout env variables #2689
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
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.
PR Summary
This PR adds new environment variables VESPA_REQUEST_TIMEOUT and CLIENT_EMBEDDING_TIMEOUT to configure timeouts for Vespa requests and embedding clients. The changes are implemented in backend configuration files and Docker Compose files for development environments.
- Added VESPA_REQUEST_TIMEOUT in
backend/danswer/configs/app_configs.py
for Vespa request timeouts - Introduced CLIENT_EMBEDDING_TIMEOUT in
backend/danswer/configs/model_configs.py
for OpenAI and VoyageAI embedding timeouts - Applied VESPA_REQUEST_TIMEOUT to HTTP client instances in
backend/danswer/document_index/vespa/index.py
- Implemented CLIENT_EMBEDDING_TIMEOUT in
backend/model_server/encoders.py
for embedding clients - Added both new environment variables to
docker-compose.dev.yml
anddocker-compose.gpu-dev.yml
6 file(s) reviewed, 2 comment(s)
Edit PR Review Bot Settings
@@ -395,6 +395,8 @@ | |||
os.environ.get("CUSTOM_ANSWER_VALIDITY_CONDITIONS", "[]") | |||
) | |||
|
|||
VESPA_REQUEST_TIMEOUT = int(os.environ.get("VESPA_REQUEST_TIMEOUT", 0)) or None |
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.
style: Consider adding a comment explaining the purpose and usage of this new variable
# Only used for OpenAI and VoyageAI | ||
CLIENT_EMBEDDING_TIMEOUT = int(os.environ.get("CLIENT_EMBEDDING_TIMEOUT") or 0) or None |
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.
style: Add a comment explaining the purpose and expected format of CLIENT_EMBEDDING_TIMEOUT
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.
Let's just remove it from the deployment files, the rest is good
8ec7d0a
to
79751f7
Compare
249267c
to
454437f
Compare
Description
[Provide a brief description of the changes in this PR]
How Has This Been Tested?
[Describe the tests you ran to verify your changes]
Accepted Risk
[Any know risks or failure modes to point out to reviewers]
Related Issue(s)
[If applicable, link to the issue(s) this PR addresses]
Checklist: