Introduction

Index

• Quickstart
• LLM Settings
• Index Settings
• System Messages
• Glossary

About

Faith Copilot helps you chat with your RAG data using various types of language models.

In this documentation, we’ll guide you in the process of creating your own Embeddings, Upserting them to a Vector Store, and much more.

Visit the Glossary if you run into a term you’re not familiar with.

Notebooks

Faith Copilot has a series of Notebooks made with Google Colab so you don’t have to write code from scratch. These notebooks include:

• 📙 FaithCopilot Context Pipeline (Google Colab Notebook)

What can you do with Faith Copilot?

• Hybrid search your documents (by keywords and semantically)
• Chat with your documents and ask it questions
• Fine tune your LLM

The Basic Pipeline

1. Upload text file to Faith Copilot and get back the IDs
2. Get the Embeddings for those files
3. Push the embeddings to the Vector Store using the Faith Copilot ID as the index record’s ID
4. Add the namespace to Faith Copilot

Check out our Quickstart and start creating your RAG system.