Welcome to Lexy

Lexy is a data platform for building AI-powered applications. You can use Lexy to:

• Build Retrieval Augmented Generation (RAG) applications.
• Provide relevant context for AI agents.
• Add long-term memory to chat-based applications.
• Extract structured data from unstructured documents.

Features

• REST API for storing, embedding, and retrieving documents.
• Pipeline-based document processing using your own Python functions.
• Change data capture for real-time updates.
• Secure file storage using Amazon S3 or Google Cloud Storage.
• Open source Apache 2.0 license.

Installation

Follow the steps in the installation guide to install Lexy.

Quickstart

See the quickstart guide to get started with Lexy.

Tutorials

Review the following tutorials for a step-by-step guide on how to use Lexy.

• Getting started for an overview of Lexy's core concepts.
• Retrieval Augmented Generation (RAG) for how to implement RAG using Lexy.
• Multimodal image search for how to use Lexy to build a multimodal search engine.
• Custom transformers for using your own functions as transformers.
• Document filters shows how to build pipelines for different types of documents.
• Structured data extraction for how to extract structured data from documents.

Reference

See the API reference for detailed documentation on Lexy's API.

The Python SDK is a Python client for Lexy, with detailed documentation.

Contributing

Check out the developer notes for guidance on contributing to the Lexy codebase.

FAQs

Any questions? Check out the FAQ for answers to common questions.

If you can't find the answer you're looking for, please contact us.