5 Minute Version

This is a '5-minute version', if you just want to run IntellAgent quickly on example data. If you want more in-depth information, go to the Installation Guide.

Step 1 - Download and install

git clone git@github.com:plurai-ai/intellagent.git
cd intellagent

You can use Conda or pip to install the dependencies.

Using pip:

pip install -r requirements.txt

Step 2 - Set your LLM API Key

Edit the config/llm_env.yml file to set up your LLM configuration:

openai:
  OPENAI_API_KEY: "your-api-key-here"

To change the default LLM provider or model for either the IntellAgent system or the chatbot, you can easily update the configuration file. For instance, modify the config/config_edcation.yml file:

llm_intellagent:
    type: 'azure'

llm_chat:
    type: 'azure'

To change the number of samples in the database you should modify the num_samples in the config file:

dataset:
    num_samples: 30

Step 3 - Run the Simulator

If you're utilizing Azure OpenAI services for user_llm, ensure you disable the default jailbreak filter before running the simulator.

For fast simple environment without a database, run the following command:

python run.py --output_path results/education --config_path ./config/config_education.yml 

For more complex (slower) environment with a database, run the following command:

python run.py --output_path results/airline --config_path ./config/config_airline.yml 

Troubleshooting
- Rate limit messages → Decrease num_workers variables in the config_default file.
- Frequent timeout errors → Increase the timeout values in the config_default file.

Explore all the Customization options to configure the simulation for your environment. or delve into the examples we provide to learn more about its capabilities.

Step 4 - See the Results

To understand all the simulator generated artifacts, see the Results section.

To visualize the simulation results using streamlit, run:

streamlit run simulator/visualization/Simulator_Visualizer.py

This will launch a Streamlit dashboard showing detailed analytics and visualizations of your simulation results.