​
Welcome to LiquidIndex

LiquidIndex is a fully managed RAG (Retrieval Augmented Generation) engine designed with developer experience in mind. Inspired by Stripe’s simplicity, we’ve created a streamlined API that handles all the complexity of RAG implementations - from ingestion to retrieval pipelines - allowing you to focus on building great applications.

Multi-Tenant Implementation

Learn how to implement RAG for multiple users or organizations

Single-Tenant Setup

Build RAG for a single organization or dataset

Core Concepts

Understanding multi-tenant RAG, retrieval strategies, and best practices

Changelog

Stay updated with our latest features and improvements

​
Getting Started

Getting started with LiquidIndex is straightforward:

  1. Generate an API key in the dashboard
  2. Create your first project
  3. View the API docs to begin integrating

For detailed implementation guides, explore our documentation sections above.

​
What is RAG?

Retrieval Augmented Generation (RAG) is a technique that enhances AI models by providing them with relevant context from your data. Instead of relying solely on the model’s training data, RAG allows you to ground responses in your specific documents, knowledge base, or data.

LiquidIndex simplifies RAG implementation by managing:

  • Document ingestion and processing
  • Efficient vector storage and retrieval
  • Context optimization for AI models
  • Multi-tenant data isolation
  • Scalable infrastructure