Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[WIP ] New planner and plan following for Gaia #99

Closed
wants to merge 65 commits into from
Closed

Conversation

ollmer
Copy link
Collaborator

@ollmer ollmer commented Nov 14, 2024

  1. New node for plain text answers
  2. New node for formalization of plain text into expected class
  3. Planner agent for detailed plans.
  4. Survey facts first, then plan, like magentic
  5. Explicit links to previous plan steps, plan as DAG.
  6. ... to be continued

@ollmer ollmer linked an issue Nov 15, 2024 that may be closed by this pull request
examples/gaia_agent/v2.py Outdated Show resolved Hide resolved
examples/gaia_agent/v2.py Outdated Show resolved Hide resolved
return super().create(llm, nodes=nodes, subagents=subagents, max_iterations=2)


class GaiaExecutor(Agent):
Copy link
Collaborator

Choose a reason for hiding this comment

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

so that's like a jack-of-all-trades that has all the tools worker, I suppose?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Yes, executor without specialization, just like our previous Gaia agent.

@ollmer
Copy link
Collaborator Author

ollmer commented Jan 14, 2025

@rizar I'm going to close this as we not intend to merge it in a main in its current form. Some code from this branch will be moved to the new standard node separately.
Do you agree?

@ollmer ollmer closed this Jan 21, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Add subagent calling to mononode
2 participants