Skip to content
This repository was archived by the owner on Sep 30, 2024. It is now read-only.

feat(cody-gateway): add support for Gemini models with context cache#63413

Merged
abeatrix merged 1 commit into
mainfrom
bee/gemini-caching-models
Jul 3, 2024
Merged

feat(cody-gateway): add support for Gemini models with context cache#63413
abeatrix merged 1 commit into
mainfrom
bee/gemini-caching-models

Conversation

@abeatrix

@abeatrix abeatrix commented Jun 21, 2024

Copy link
Copy Markdown
Contributor

PART OF https://linear.app/sourcegraph/issue/CODY-2451
CLOSE https://linear.app/sourcegraph/issue/CODY-2513

  • Add Gemini 1.5 Flash 001 and Gemini 1.5 Pro 001 models to the config and allowed models lists
  • These fixed stable versions support context caching, as noted in the Google Gemini API docs

image

NEXT: Implement context caching in the codebase. Right now using the newly added models alone do not work with context caching.

Test plan

No feature changes. Adding new model to allow list.

Changelog

- Add Gemini 1.5 Flash 001 and Gemini 1.5 Pro 001 models to the config and allowed models lists
- These fixed stable versions support context caching, as noted in the Google Gemini API docs
@cla-bot cla-bot Bot added the cla-signed label Jun 21, 2024
@abeatrix abeatrix requested review from a team, sagtanih and valerybugakov June 21, 2024 00:11
@abeatrix abeatrix changed the title feat(cody-gateway): add support for Gemini 1.5 Flash and Pro 001 models feat(cody-gateway): add support for Gemini 1.5 Flash and Pro models with context cache Jun 21, 2024
@abeatrix abeatrix marked this pull request as draft June 21, 2024 02:20
@abeatrix abeatrix marked this pull request as ready for review June 21, 2024 17:05
@abeatrix abeatrix changed the title feat(cody-gateway): add support for Gemini 1.5 Flash and Pro models with context cache feat(cody-gateway): add support for Gemini models with context cache Jun 21, 2024

@chrsmith chrsmith left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

LGTM.

Do we want to "float" gemini-1.5-latest to use ...-001, ...-002 automatically? Or do we want to treat -latest as literally the model name "latest" and have N-different ...-XXX model names floating around?

It seems like this approach isn't going to scale particularly well.

@abeatrix abeatrix merged commit 806ff43 into main Jul 3, 2024
@abeatrix abeatrix deleted the bee/gemini-caching-models branch July 3, 2024 16:28
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants