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

A new example application to OmAgent #107

Open
Xxxxxsun opened this issue Dec 5, 2024 · 0 comments
Open

A new example application to OmAgent #107

Xxxxxsun opened this issue Dec 5, 2024 · 0 comments

Comments

@Xxxxxsun
Copy link

Xxxxxsun commented Dec 5, 2024

I have reproduced the COT algorithm using OmAgent and reorganized the entire codebase to align with the structure outlined in CONTRIBUTING.md(New Features, Sec. 2). The current directory structure for COT is as follows:

examples/cotprompt
├── agent
│   └── cot_agent
│       ├── cot_conclude.py
│       ├── cot_input_interface.py
│       ├── cot_reasoning.py
│       └── __init__.py
│       
├── compile_container.py
├── configs
│   ├── llms
│   │   ├── gpt4o.yml
│   │   ├── json_res.yml
│   │   └── text_res.yml
│   ├── tools
│   │   └── all_tools.yml
│   └── workers
│       ├── cot_conclude.yml
│       ├── cot_input_interface.yml
│       └── cot_reasoning.yaml
├── container.yaml
└── run_cli.py

The main approach involves implementing three workers:

  1. cot_input_interface: Responsible for receiving user questions.
  2. cot_reasoning: Dedicated to generating the reasoning path without producing the final answer.
  3. cot_conclude: Takes the user question and the reasoning path generated by the ReasonWorker to produce the final answer.
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

No branches or pull requests

1 participant