Skip to content

Use Retry-After if present in header #459

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Use Retry-After if present in header #459

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 10 additions & 3 deletions async-openai/src/client.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
use std::pin::Pin;
use std::{pin::Pin, time::Duration};

use bytes::Bytes;
use futures::{stream::StreamExt, Stream};
Expand Down Expand Up @@ -360,6 +360,13 @@ impl<C: Config> Client<C> {
.map_err(OpenAIError::Reqwest)
.map_err(backoff::Error::Permanent)?;

let retry_after = response
.headers()
.get("retry-after")
Copy link
Owner

@64bit 64bit Nov 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not an official header

https://platform.openai.com/docs/guides/rate-limits#rate-limits-in-headers

.and_then(|h| h.to_str().ok())
.and_then(|s| s.parse::<u64>().ok())
.map(Duration::from_secs);

let status = response.status();

match read_response(response).await {
Expand All @@ -370,7 +377,7 @@ impl<C: Config> Client<C> {
if status.is_server_error() {
Err(backoff::Error::Transient {
err: OpenAIError::ApiError(api_error),
retry_after: None,
retry_after,
})
} else if status.as_u16() == 429
&& api_error.r#type != Some("insufficient_quota".to_string())
Expand All @@ -379,7 +386,7 @@ impl<C: Config> Client<C> {
tracing::warn!("Rate limited: {}", api_error.message);
Err(backoff::Error::Transient {
err: OpenAIError::ApiError(api_error),
retry_after: None,
retry_after,
})
} else {
Err(backoff::Error::Permanent(OpenAIError::ApiError(api_error)))
Expand Down
Loading