Add OpenAI URL override and support for custom request headers #27
+9
−2
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
This commit introduces the configuration primitives necessary for semantic caching proxy services for OpenAI requests.Specifically, the ability to override the OpenAI root API URL path and the ability to add custom headers to the request payload in the form of a hash. This commit does not introduce tests, and should not be merged until a subsequent commit lands with proper testing.
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Outdated suggestions cannot be applied.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.
Relates to #9
Preface
Opening early to discuss whether this is a welcome addition, the architectural decisions, documentation implications, and whether expanding this URL config override to other LLMs within the gem's scope makes sense. I'm committed to maintaining the developer experience simplicity of the project's stated mission, so I'm on board with redoing the initial approach to fit in with longer-term priorities (or closing outright!).
Goal
This commit introduces the configuration primitives necessary for semantic caching proxy services for OpenAI requests. Specifically, the option to override the OpenAI root API URL path and the ability to add custom headers to the request payload in the form of a hash. I'm a Fastly employee, and I used our semantic caching product as a test implementation.
In-Progress Disclaimer
This branch does not yet introduce tests and should not be merged until a subsequent commit lands with proper testing.