Basic Bedrock LLM client. #931
Merged
Conversation
This file contains hidden or 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
baitsguy
reviewed
Oct 16, 2024
|
Thanks! Added integration test and addressed other comments. PTAL. |
|
Changes look good, open_ai integ test is failing tho |
baitsguy
reviewed
Oct 16, 2024
baitsguy
approved these changes
Oct 16, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This is a crude but serviceable LLM client that uses Bedrock. I have currently tested it only with Sonnet 3.5 and different models may have different requirements and parameters, but we can add those over time as needed.
Since there are so many different models with somewhat different formats, it's a little hard to test them all.
I lifted the cache logic into the
LLMbase class so it is reusable across subclasses, although the OpenAI variant needs to account for the response type in the cache key.