@yoginth: today i'm launching http://rag.computer an open source RAG platform built on top of @turbopuffer fast ingestion, fast r…

X AI KOLs Timeline Tools

Summary

bigRAG is an open-source RAG platform built on top of Turbopuffer for fast ingestion and retrieval, supporting multiple document formats and embedding models.

today i'm launching https://t.co/lG6DqJOfZN an open source RAG platform built on top of @turbopuffer fast ingestion, fast retrieval, clean developer experience. one of the few AI infra products that genuinely feels modern. more soon 👀 https://t.co/nLxNYOnr0F
Original Article
View Cached Full Text

Cached at: 05/22/26, 07:57 PM

today i’m launching https://t.co/lG6DqJOfZN

an open source RAG platform built on top of @turbopuffer

fast ingestion, fast retrieval, clean developer experience.

one of the few AI infra products that genuinely feels modern.

more soon 👀 https://t.co/nLxNYOnr0F


Turbopuffer-backed RAG for your documents

Source: https://rag.computer/ Open-source · Self-hosted control plane · Turbopuffer search

Upload documents, parse with Docling, embed with your provider, and use Turbopuffer for semantic, keyword, and hybrid retrieval through one API.

Get StartedStar on GitHub

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, Cohere, Voyage, and OpenAI-compatible models with per-collection configuration. Mix providers across collections.### Turbopuffer Search Turbopuffer powers semantic, keyword, and hybrid search from the same chunk store, with Reciprocal Rank Fusion for mixed queries.### Namespace Isolation Each collection maps to a Turbopuffer namespace, keeping vector writes, keyword indexes, exports, and deletes scoped.### Webhooks HMAC-signed webhook payloads with automatic retries for document, collection, connector, and backup events.### 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 in Turbopuffer for vector and full-text search. Use the TypeScript SDK or REST API.

TypeScript SDK with zero dependencies and full type safety

Turbopuffer stores vectors, chunk text, metadata, and keyword indexes

Full API reference with Swagger docs at /docs

15+

Document formats

PDF, DOCX, images, and more

1

Search backend

Turbopuffer

12+

Embedding models

OpenAI, Cohere, Voyage

5 min

To deploy

Docker Compose

Deploy bigRAG with Turbopuffer search

Run the API, admin UI, Postgres, and Redis yourself, then connect Turbopuffer for managed vector and full-text retrieval.

Similar Articles

RAG-Anything: All-in-One RAG Framework

Papers with Code Trending

RAG-Anything is a new open-source framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.

HKUDS/RAG-Anything

GitHub Trending (daily)

HKUDS released RAG-Anything, an open-source all-in-one multimodal retrieval-augmented generation framework based on LightRAG.