Heritage Square Foundation AI Agent

This is the Organized Folder for Problem 2
This is the Unorganized Folder (Current) for Problem 2

Inspiration The inspiration for this project is to create a powerful RAG (Retrieval-Augmented Generation) application that allows users to chat with their files in Google Drive directly.

What it does The Heritage Square Foundation Agent is an AI assistant that helps with:

Grant document preparation
Answering questions about Foundation documents
Providing information from Google Drive files

How we built it The project is built using Streamlit for the UI and integrates with a chat engine to handle user prompts and responses. It leverages Google Drive for document storage and retrieval, and uses a vector client for efficient data handling. The environment is set up using Docker.

Challenges we ran into Some challenges faced during the development include:

Setting up the Google Service account for accessing Google Drive
Managing session states and ensuring data consistency
Handling errors and edge cases in the chat engine responses

Accomplishments that we're proud of We are proud of creating a seamless and interactive chatbot that can directly interact with documents stored in Google Drive. The integration with LlamaIndex and Pathway vector store has made the application robust and efficient.

What we learned We learned how to effectively use Streamlit for building interactive UIs, how to integrate with Google Drive using a service account, and how to manage session states in a web application. Additionally, we gained insights into using vector stores for efficient data retrieval.

Future plans for the Heritage Square Foundation Agent include: