RAG made

Simple

The Stripe Checkout of RAG. Simple setup, powerful results.

Spin up a scalable, multi-tenant RAG engine in three API calls. Create a customer, start a session, and query.

Built for speed, flexibility, and seamless integration. No hassle or complex infrastructure, just simple API calls that get the job done.

Multi-Tenant RAG in Just Three API Calls

Integrate powerful AI search for all your users with minimal code

Create a Customer

Each of your users becomes a "customer" in our system, with their own isolated data space. Perfect for SaaS applications where each user needs their own private RAG engine.

Create a Session

Just like Stripe Checkout, our session system handles the entire upload process with a secure, hosted interface. Your users get redirected to our page, upload their documents, and return to your app.

Query Data

Your users can query their own documents using natural language. Our system automatically routes queries to the right customer's data space, ensuring complete data isolation.

JavaScript

1// Create a new user in your multi-tenant RAG system
2// Each of your users gets their own isolated data space
3const response = await axios.post("https://api.liquidindex.dev/customer/create", {
4 project_id: "<project_id>", // Your project identifier
5 name: "<name>", // Your user's name or identifier
6}, {
7 headers: {
8 Authorization: "Bearer <YOUR_API_KEY>", // Your API key for authentication
9 }
10});

See It in Action: Multi-Tenant RAG in Just Minutes

Watch how quickly you can add AI document search for all your users

Multi-Tenant RAG Without the Headaches

We handle all the complex infrastructure so you can focus on building features your users love

1

User Uploads Documents

Your users upload their documents through our secure, hosted interface. You simply redirect them to our session page and we handle the rest.

2

We Process Everything

Documents are automatically processed, chunked, and prepared for retrieval. Each user's data is kept completely separate from others.

3

AI-Powered Embeddings

We convert each user's documents into high-dimensional vectors using state-of-the-art AI models, capturing the semantic meaning of their content.

4

Multi-Tenant Storage

Each user's data is stored in their own isolated vector space, ensuring complete data separation. Scale to thousands of users without managing complex infrastructure.

5

Intelligent Querying

Your application can query each user's documents with a simple API call. We automatically route the query to the right user's data and return the most relevant information.

Simple, Transparent Pricing

Choose the plan that fits your needs. Start with Basic and upgrade anytime.

Basic

Pay as you go
10MB file upload limit
Standard processing queue
Community support
Standard vector DB
Default embedding models
Popular

Pro

$25/month
100MB file upload limit
Priority processing
Direct developer support
Configurable vector DB
Extended embedding model selection
Access to SubPages

Add AI Search to Your Apps in Minutes

Let users search their data with AI using just three API calls. No infrastructure or complex integration required.

Multi-tenant by design
Stripe-like integration