Skip to content

federicodip/AI-Agora

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

AI Agora: Fostering Democratic Knowledge via Augmented Retrieval

agora

AI Agora is an innovative application at the intersection of learning and social justice, designed to empower scholars, social researchers, and citizens to explore publicly available Congressional Records in a meaningful and efficient way. By leveraging state-of-the-art Augmented Retrieval techniques, this project aims to democratize access to critical legislative information, fostering transparency and participation in the democratic process.


🚀 Features

1. Customizable Information Pipelines

  • Users can build tailored pipelines to browse and retrieve relevant data from the vast repository of Congressional Records hosted on Congress.gov.
  • Flexibility to focus on specific topics, keywords, or debates.

2. For Scholars and Citizens Alike

  • Scholars: Access structured tools for in-depth analysis of legislative language, trends, and social justice issues.
  • Citizens: Stay informed and engaged with the democratic process by querying debates, bills, and amendments.

3. Augmented Retrieval

  • Combines natural language processing (NLP) with retrieval-augmented generation (RAG) to offer precise and contextual results, even from complex legislative texts.

4. Transparent and Participatory

  • Enhances public participation by breaking down barriers to understanding legislative language.
  • Promotes equitable access to legislative data for underserved communities.

💡 Why AI Agora?

At the Intersection of Learning and Social Justice

The democratic process should be accessible to everyone. Yet, vast and complex legislative records often make it difficult for citizens and scholars to engage. AI Agora bridges this gap by providing tools to:

  • Analyze legislative trends.
  • Identify key discussions relevant to social justice and public policy.
  • Build knowledge pipelines that suit diverse needs, whether for academic research or civic activism.

🛠️ How It Works

  1. Data Retrieval: Pulls records from Congressional Records, including bills, debates, and legislative amendments.
  2. Text Splitting and Embedding:
    • Processes legislative texts into manageable chunks.
    • Embeds them into a vector database for fast and accurate retrieval.
  3. Pipeline Customization:
    • Users can define their search parameters, such as topics, timeframes, or speakers.
  4. Interactive Querying:
    • Input natural language questions or topics of interest.
    • AI Agora retrieves, analyzes, and presents concise and contextualized answers with source references.
  5. Visualization and Insights:
    • Optional data visualization to uncover trends in legislative discourse.

📚 Example Queries

  • Legislative Insights: "What were the main arguments in the debate over the 2024 budget bill?"
  • Social Justice Focus: "How has Congress discussed climate change in the past year?"
  • Trends Analysis: "What topics did Representative John Smith discuss most frequently in 2023?"

📊 Technologies Used

  • LangChain: To manage the retrieval-augmented pipeline.
  • OpenAI GPT-4: For advanced natural language understanding and generation.
  • Chroma: Vector storage for efficient information retrieval.
  • Gradio: For a clean and user-friendly interface.
  • Congressional Records API: To access up-to-date legislative data.

🌍 Impact and Vision

AI Agora is more than just a tool—it's a step toward a more informed and engaged citizenry. By enhancing access to legislative records, it:

  • Encourages participation in democratic processes.
  • Reduces barriers to understanding complex legislative texts.
  • Empowers communities to advocate for social justice by staying informed.

🛠️ Contributing

We welcome contributions from the community! Here’s how you can help:

  1. Fork the repository.
  2. Create a branch for your feature or bugfix.
  3. Commit your changes and push to your fork.
  4. Open a pull request to the main repository.

🙏 Acknowledgments

  • Congress.gov: For making public records accessible.
  • OpenAI: For enabling advanced NLP capabilities.
  • Gradio: For providing a robust framework for the user interface.

📬 Contact

If you have any questions or suggestions, feel free to reach out via fed.dipasqua@stud.uniroma3.it


Let’s make democracy more accessible, one query at a time!

About

AI Agora: Fostering Democratic Knowledge via Augmented Retrieval

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages