https://github.com/wpuricz/multiagent
A proof of concept for multi agent AI interaction
https://github.com/wpuricz/multiagent
Last synced: 27 days ago
JSON representation
A proof of concept for multi agent AI interaction
- Host: GitHub
- URL: https://github.com/wpuricz/multiagent
- Owner: wpuricz
- Created: 2024-02-04T21:54:57.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2024-03-12T21:37:00.000Z (almost 2 years ago)
- Last Synced: 2024-12-29T04:33:57.622Z (about 1 year ago)
- Language: Jupyter Notebook
- Size: 27.5 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Multi Agent POC
This is a proof of concept for a multi agent architecture. It simulates a developer(gpt-3.5-turbo) and code reviewer(gpt-3.5-turbo-0125) working together. The input box allows you to input code into the textbox. The developer will write the code and the code reviewer will suggest improvements and the iteration will continue.
### Running the application
Requires Python, preferably 3.10 or higher
1. Create a python virtual environment with conda or venv (optional)
```bash
conda create -n multi-agent -y python=3.10 pip
conda activate multi-agent
```
2. Add your openai key to the streamlit secrets
Create the .streamlit folder and a file called secrets.toml, and add the key
```bash
mkdir .streamlit
touch .streamlit/secrets.toml
```
In the secrets.toml file put a line
```OPENAI_API_KEY = "api key goes here"```
3. Install Requirements
```bash
pip install -r requirements.txt
```
4. Run it
With logging to a file
```bash
streamlit run multi_agent.py --logger.level=info 2>'app.log'
```
or log to terminal
```bash
streamlit run multi_agent.py
```
### Example Conversations
- [React Form](./example_conversations/multi_agent%20·%20Streamlit%20Form.pdf)
- [Python Data](./example_conversations/multi_agent%20·%20Python%20data.pdf)
### Screenshot
