cacarvuai/human-ai-collab repository overview

⁠Human_AI_Collab

A Streamlit-based application for evaluating Human-AI collaboration in policing. This project uses survey data to generate insights through interactive dashboards and provides evaluation support powered by advanced language models llama3.2:3b and mistral.

⁠Features

• Survey Responses Dashboard: Analyze survey data using charts, maps, and word clouds.
• AI-Powered Evaluation: Gain insights from survey responses with advanced language models.
• Streamlit App: Simple and user-friendly web interface.

⁠Quick Start

⁠Method 1: Using Docker

1. Install Docker: Download Docker⁠.
2. Login to Docker Hub:

   docker login

1. Pull the Image:

   docker pull cacarvuai/human-ai-collab:latest

1. Run the Container:

   docker run -p 8501:8501 --rm -it cacarvuai/human-ai-collab:latest

1. Access the App:
   Open your browser and navigate to http://localhost:8501.

⁠Method 2: Running Locally

⁠Prerequisites

• Python 3.11+
• Virtual environment tools (venv or virtualenv)

⁠Steps

1. Clone the Repository:

   git clone https://github.com/WSvanTienen/Human-AI-Collab
   cd Human-AI-Collab

1. Set Up Virtual Environment:

   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\\Scripts\\activate

1. Install Dependencies:

   pip install -r requirements.txt

1. Run the Application:

   streamlit run application.py

1. Access the App:
   Open your browser and navigate to http://localhost:8501.

⁠Running with Dockerfile

To build and run the Docker image manually:

1. Build the Docker Image:

   docker build -t human-ai-collab:latest .

1. Run the Docker Container:

   docker run -p 8501:8501 human-ai-collab:latest

1. Access the App:
   Open your browser and navigate to http://localhost:8501.

⁠Notes for Running Locally

⁠Activating the Virtual Environment on Windows

If PowerShell shows an error about the execution policy, run this command:

Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass

Then activate the environment:

.venv\\Scripts\\activate

⁠Dependencies

• Streamlit: For creating interactive web apps.
• Altair: For data visualization.
• Folium: For interactive maps.
• WordCloud: For generating word clouds.
• SQLite3: For database storage and management.
• Ollama: For advanced language model interactions.

⁠Ollama Models Used

• llama3.2:3b: For generating embeddings and refining survey questions.
• mistral: For evaluation insights based on survey responses.

⁠File Structure

• application.py: Main application file.
• Dockerfile: Docker configuration file for containerizing the app.
• Evaluation_LLM.py: Provides evaluation support powered by language models.
• images: Directory containing images used in the application.
• main_survey.py: Handles survey logic and embedding generation.
• README.md: Project documentation.
• requirements.txt: List of Python dependencies.
• responses.db: SQLite database for storing survey responses.
• survey_final.json: JSON file containing the survey questions and configurations.
• survey_results.db: SQLite database for storing survey results.
• visuals_db_test.py: Generates the survey dashboard.

⁠Contributing

1. Fork the repository.
2. Create a feature branch:

   git checkout -b feature-name
   

   Copy
3. Commit your changes:

   git commit -m "Add new feature"
   

   Copy
4. Push to the branch:

   git push origin feature-name
   

   Copy
5. Open a Pull Request.