Skip to content

Cache AI requests and responses

Jan Provaznik requested to merge jp-ai-cache into master

What does this MR do and why?

Related to https://gitlab.com/gitlab-org/gitlab/-/issues/410521

Cache AI requests and responses

  • Redis stream is used to cache AI requests/responses
  • because streams can't be updated, requests and responses are cached separately
  • response can be found by request's ID (which is same for both request and response)
  • when caching is called for responses, also response_body is stored. It's not clear at this point what data we will need to store for requests vs responses (we can extend this later), so at this point presence of response_body is the only difference between requests and responses.
  • This cache is not used yet (I plan to do this in a separate MR as this would be too big change)

Screenshots or screen recordings

Screenshots are required for UI changes, and strongly recommended for all other merge requests.

How to set up and validate locally

Numbered steps to set up and validate the change are strongly suggested.

MR acceptance checklist

This checklist encourages us to confirm any changes have been analyzed to reduce risks in quality, performance, reliability, security, and maintainability.

Edited by Jan Provaznik

Merge request reports