feat: prompting O1 #1891
Merged
feat: prompting O1 #1891
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
…ent.inner_step() ie the single step version
Closed
sarahwooders
approved these changes
Oct 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Outdated suggestions cannot be applied.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.
Please describe the purpose of this pull request.
Create a new agent type O1Agent, that uses prompting to get the agent to "think" more at inference time before responding by calling a think function repeatedly before the final answer function.
How to test
How can we test your PR during review? What commands should we run? What outcomes should we expect?
Added a simple test in test_o1_agent that creates an O1 agent and asks it to compare which two numbers are larger. With got-4o-mini, it improves accuracy from 0->80%. The test just checks that 3 steps to respond.
Have you tested this PR?
Have you tested the latest commit on the PR? If so please provide outputs from your tests.
Related issues or PRs
Please link any related GitHub issues or PRs.
This is based on the refactor to make
Agentmulti-step in #1884.