Document ingestion and vector search you can self-host
bigRAG is a complete RAG pipeline — upload documents, auto-chunk, embed, and search. One API for your entire retrieval-augmented generation stack. Deploy on your infrastructure in minutes.
Features
Everything you need for RAG
Any Document Format
PDF, DOCX, PPTX, HTML, Markdown, images with OCR, and more — powered by Docling for universal document parsing.
Any Embedding Model
OpenAI and Cohere embedding models with per-collection configuration. Mix providers across collections.
Hybrid Search
Semantic, keyword, or hybrid search with Reciprocal Rank Fusion. Optional Cohere reranking for top results.
Real-Time Progress
Stream document processing progress via Server-Sent Events. Track parsing, chunking, and embedding in real time.
Webhooks
HMAC-signed webhook payloads with automatic retries. Get notified when documents are processed or fail.
TypeScript SDK
Zero-dependency TypeScript client for Node.js, browsers, Deno, and Bun. Full type safety and automatic retries.
Simple integration
Upload, embed, and search in minutes
bigRAG handles the entire RAG pipeline. Upload any document format, and it automatically parses, chunks, embeds, and indexes for vector search. Use the TypeScript SDK or REST API.
import { BigRAG } from "@bigrag/client";
const client = new BigRAG({
apiSecret: "your-api-secret",
baseUrl: "http://localhost:6100",
});
// Upload, embed, and search — all in one platform
const { results } = await client.query("knowledge_base", {
query: "What is the PTO policy?",
top_k: 5,
});15+
Document formats
PDF, DOCX, images, and more
6
Embedding models
OpenAI and Cohere
5 min
To deploy
Docker Compose
Deploy on your infrastructure
Your documents, embeddings, and search data never leave your servers. One command to get started.
$ curl -O https://raw.githubusercontent.com/bigint/bigrag/main/docker-compose.yml
$ docker compose up -d