Skip to content

Conversational Health Agents: A Personalized LLM-powered Agent Framework

License

Notifications You must be signed in to change notification settings

cloudrumbles/CHA

 
 

Repository files navigation

Quick Start

To use CHA in a safe and stable way, ensure you have Python 3.10 or higher installed. First, create a virtual environment:

# Create the virtual environment
python -m venv /path/to/new/virtual/environment

# Activate the virtual environment
source /path/to/new/virtual/environment/bin/activate

Now, install the CHA package.

pip install openCHA
playwright install

Manual Installation

git clone https://github.com/Institute4FutureHealth/CHA.git
cd CHA
pip install -e '.[all]'
playwright install

To simplify installation with minimum requirements and be ready to go, you can use the following command. This installs OpenAI, React Planner, as well as SerpAPI (search) and Playwright (browser) tasks:

pip install -e '.[minimum]'

If you want to install all requirements for all tasks and other components, use the following command:

pip install -e '.[all]'

Running openCHA

After installing the package, based on what tasks you want to use, you may need to acquire some api_keys. For example, to get started using openAI GPT3.5 model as LLM in CHA, you need to signup in their website and get the api_key. Then you should add openAI api_key as environment vairable in your terminal:

export OPENAI_API_KEY="your api_key"

The same goes for using tasks like SerpAPI:

export SERPAPI_API_KEY="your api_key"

Finally, you can start running our framework with the following simple code:

from openCHA import openCHA

cha = openCHA()
cha.run_with_interface()

This code will run the default interface, and you can access it at the following URL:

http://127.0.0.1:7860

For more examples, visit the Examples page.

Alt Text

About

Conversational Health Agents: A Personalized LLM-powered Agent Framework

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.9%
  • Dockerfile 0.1%