Conversation
Collaborator
Author
|
Sample code (use different LLMs for different agents as well): Output: |
Collaborator
Author
|
Here's an example of the compiled responses that will then go to the internal evaluator agent for selection: |
This comment has been minimized.
This comment has been minimized.
Collaborator
Author
|
Closing for now. |
Codecov Report❌ Patch coverage is
... and 41 files with indirect coverage changes 🚀 New features to boost your workflow:
|
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why are these changes needed?
Representing an agent that's encapsulating the Redundant pattern where multiple agents are used to respond to a task and an evaluation agent chooses the best one.
Redundant pattern documentation.
This is a first draft of the approach, it uses a simple 4 step process internally. No swarm/group chat as it is very sequential. If we expand its utility then we can consider an internal swarm.
EvaluationAgent may not be the final name.
Here are the parameters of the EvaluationAgent.
It is currently running a nested chat asynchronously internally, so the agents are all responding at the same time.
Related issue number
Closes #1351
Checks