[AI gateway] Request timeouts for fallback providers #19391
+102
−6
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
kodster28
requested review from
kathayl,
G4brym,
mchenco,
daisyfaithauma and
a team
as code owners
![hyperlint-ai[bot]](https://avatars.githubusercontent.com/in/718456?s=60&v=4){kind=small}
kodster28
commented
Jan 23, 2025
| You can use the Universal endpoint to contact every provider. The payload is expecting an array of message, and each message is an object with the following parameters: | ||
|
|
||
| - `provider` : the name of the provider you would like to direct this message to. Can be OpenAI, workers-ai, or any of our supported providers. | ||
| - `endpoint`: the pathname of the provider API you’re trying to reach. For example, on OpenAI it can be `chat/completions`, and for Workers AI this might be [`@cf/meta/llama-3.1-8b-instruct`](/workers-ai/models/llama-3.1-8b-instruct/). See more in the sections that are specific to [each provider](/ai-gateway/providers/). | ||
| - `authorization`: the content of the Authorization HTTP Header that should be used when contacting this provider. This usually starts with “Token” or “Bearer”. | ||
| - `headers`: |
There was a problem hiding this comment.
@kathayl, I think this is accurate, but fact check me here :)
| - `query`: the payload as the provider expects it in their official API. | ||
|
|
||
| ## cURL example | ||
|
|
||
| The following example shows a simple setup with a primary model and a [fallback](/ai-gateway/configuration/fallbacks/) option. |
There was a problem hiding this comment.
Wanted to add more cross-links over to fallbacks page
| @@ -41,6 +41,10 @@ entries: | |||
| general_definition: |- | |||
| Header to [bypass caching for a specific request](/ai-gateway/configuration/caching/#skip-cache-cf-aig-skip-cache). | |||
| - term: cf-aig-request-timeout | |||
There was a problem hiding this comment.
Adds automatically to headers glossary page
|
|
||
| If that fails, then the gateway will timeout and move to the fallback `@cf/meta/llama-3.1-8b-instruct-fast` model. This model has 3000 milliseconds - determined by the request-level `cf-aig-request-timeout` value - to complete the request and provide an answer. | ||
|
|
||
| ```bash title="Request" collapse={36-50} {2,11,13-15} |
There was a problem hiding this comment.
If the collapsible bit here is distracting, happy to remove.
Also, switched the example a bit so it made sense to me... but I also could just be hallucinating stuff. Happy to flip it back to the original.
Co-authored-by: hyperlint-ai[bot] <154288675+hyperlint-ai[bot]@users.noreply.github.com>
github-actions
bot
added
product:ai-gateway
Deploying cloudflare-docs with
|
| Latest commit: |
771fedb
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://1647671e.cloudflare-docs-7ou.pages.dev |
| Branch Preview URL: | https://aig-request-timeout.cloudflare-docs-7ou.pages.dev |
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.
Summary
New feature, request timeouts for fallback providers.
Updated several pages in AI gateway docs + changelog entry.