Refactor agent to accept agent config #3430
Merged
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
xingyaoww
approved these changes
Aug 17, 2024
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Outdated suggestions cannot be applied.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.
This PR proposes to start adapting agent config to use for each agent options, similarly as we do with LLM / LLMConfig.
Agent configs will likely have more attributes than today in the near future. I think that in a follow-up PR, we can move embeddings options from LLMConfig to a MemoryConfig, part of agent config (e.g. allow to enable/disable history summarization or caching per agent). Since those are not the same models, they don't quite belong with the completion LLM settings already. Also, LLMConfig is becoming quite large itself, it seems like we can break from it the stuff that is different after all.