Plug-and-Play RAG API
for developers

Production-ready retrieval in under 10 minutes. Upload your docs, query in natural language, ship AI features — not infrastructure.

Free tier includedNo credit cardTypeScript & Python SDKs
query.ts
import { RAGClient } from "@ragex/sdk";

const client = new RAGClient({ apiKey: process.env.RAG_API_KEY });

const { results } = await client.search("kb_01", {
  query: "What is our refund policy?",
});

// → "Enterprise customers may request a full refund
//    within 30 days of purchase..."

Trusted by engineering teams

NimbusArcturusVela LabsStratosKovaMeridian

Up and running in 3 steps

01

Create a knowledge base

Define a collection to hold your documents. One line of code.

const kb = await client.createKnowledgeBase({
  name: "support-docs",
});
02

Upload your documents

Upload PDFs, Markdown, HTML — we handle parsing, chunking, and embedding.

const doc = await client.uploadDocument(
  kb.id,
  pdfFile,
  { filename: "refund-policy.pdf" },
);
03

Query with natural language

Ask questions in plain English. Get ranked, relevant results.

const { results } = await client.search(kb.id, {
  query: "What is our refund policy?",
});

// → "Enterprise customers may request a full refund
//    within 30 days of purchase..."

Everything you need. Nothing you don't.

A complete retrieval pipeline so you can focus on your product, not your infrastructure.

Universal file parsing

PDF, DOCX, PPTX, HTML, Markdown, and 11 more formats — parsed and chunked automatically.

Hybrid search

Vector, keyword, or combined search modes with tunable fusion for maximum relevance.

Intelligent reranking

Every query is re-scored with a cross-encoder model to push the best results to the top.

Metadata filtering

Filter results by custom document metadata using operators like $eq, $in, $gt, and more.

First-class SDKs

TypeScript and Python SDKs with full type safety and autocompletion.

Multi-tenant ready

Isolate knowledge bases per customer. Built for SaaS from day one.

Usage tracking

Monitor queries, pages processed, and API requests. Rate limits enforced per plan.

OpenAPI specification

Machine-readable API spec. Generate clients in any language, explore with Swagger.

Graceful degradation

If reranking times out, results still return. Your search never fails silently.

Built for developers who read the docs

Clean APIs, typed SDKs, and documentation that respects your time.

  • RESTful API with predictable resource-oriented URLs
  • Comprehensive TypeScript and Python SDKs
  • Detailed error codes with actionable messages
  • OpenAPI spec available for code generation
  • Rate limits designed for production workloads
  • Full request logging and usage tracking
terminal
$ npm install @ragex/sdk
+ @ragex/sdk@1.0.0
added 2 packages in 0.8s
Zero dependencies
Full TypeScript definitions
Ready to import

What developers are saying

We went from 3 weeks of building RAG infrastructure to shipping in an afternoon. The search quality is genuinely better than what we had in-house.

SC

Sarah Chen

Staff Engineer, Nimbus

The API is exactly what I wanted to build but didn't have time to. Clean, fast, and the docs are actually good. Rare combo.

MR

Marcus Rodriguez

CTO, Vela Labs

We handle 2M+ queries/month through Ragex. Sub-200ms p95 latency, zero downtime. It just works.

JP

James Park

Lead Engineer, Stratos

Replaced our entire Pinecone + LangChain pipeline with a single API call. Our team can focus on the product again.

PS

Priya Sharma

Engineering Manager, Arcturus

What developers are building

From customer-facing chatbots to internal tooling — one API handles them all.

Customer support bots

Ground LLM responses in your actual support docs and knowledge base articles.

Internal Q&A

Let employees search company wikis, handbooks, and Confluence in natural language.

Documentation search

Semantic search across your docs — better than keyword matching, zero training required.

Legal & compliance

Search contracts, policies, and regulatory documents with cited sources.

Product copilots

Build in-app AI assistants that answer questions about your product data.

Research tools

Help analysts search and synthesize information across large document collections.

Simple, transparent pricing

Every plan starts with a 7-day free trial. No credit card required.

Starter

For side projects and small apps.

$29/month
Start Free Trial
  • 500 pages/month
  • 5,000 queries/month
  • 3 knowledge bases
  • 50 documents
  • 500 MB storage
  • 10 req/s rate limit
  • TypeScript & Python SDKs
  • Email support

Business

For growing products at scale.

$229/month
Start Free Trial
  • 6,500 pages/month
  • 50,000 queries/month
  • 25 knowledge bases
  • 500 documents
  • 5 GB storage
  • 100 req/s rate limit
  • Usage overage billing
  • Priority support

Scale

For high-volume production workloads.

$499/month
Start Free Trial
  • 15,000 pages/month
  • 120,000 queries/month
  • 100 knowledge bases
  • 2,000 documents
  • 20 GB storage
  • 200 req/s rate limit
  • Usage overage billing
  • Priority support

Your RAG pipeline, ready in 10 minutes.

Stop building retrieval infrastructure. Start shipping AI features.