OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

bigRAG

bigRAG is an open-source, self-hostable RAG application that ingests documents, automatically chunks and embeds them, and provides semantic, keyword and hybrid retrieval through a REST API. Its documented architecture uses a Python/FastAPI API, an ingestion worker, Postgres and Redis, with Turbopuffer as the search backend.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

bigRAG — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use bigRAG when you want to operate a self-hosted document-ingestion and retrieval service and connect it to an application through REST or the documented client options.

Who it is for

  • Developers building applications that need searchable document collections behind a REST API.
  • Teams seeking a self-hosted RAG backend with automatic document processing and multiple retrieval modes.

Documented uses

  • Ingest supported documents, including PDF, DOCX, PPTX, HTML, Markdown and images.
  • Create searchable collections using embeddings and Turbopuffer-backed vector, keyword or hybrid retrieval.
  • Query one or multiple collections through HTTP, TypeScript or Python client options.
  • Use the documented generated-chat playground for backend-grounded responses with streaming and citations.
Before you choose

Requirements & limits

The repository is public and identifies the project as open source under the MIT license. The README documents Docker Compose deployment and API-key authentication for HTTP clients.

  • Turbopuffer must be configured before ingesting or querying; it is the documented search backend.
  • Embedding-provider options listed are OpenAI, OpenAI-compatible gateways, Cohere and Voyage; Cohere is also listed for reranking.
  • The documented Compose setup starts the API, worker, admin UI, Postgres and Redis.
  • Document parsing is handled through Docling, and the README lists PDF, DOCX, PPTX, HTML, Markdown and images among supported formats.
  • The service can be accessed through REST, with TypeScript and Python SDKs and an MCP server also listed.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a local bigRAG instance and query a document

Use the documented Docker Compose and HTTP workflow to create a collection, upload a file and submit a retrieval query.

Before you start

  • Docker Compose
  • A configured Turbopuffer instance
  • An embedding-provider API key
  • curl; the example uses jq to extract an API key

Steps

  1. Run the command below to start the API, worker, admin UI, Postgres and Redis.

    Documented command
    docker compose up -d

  2. Configure Turbopuffer through onboarding before ingesting or querying collections.

  3. Create the first administrator through /v1/auth/setup, then mint an API key through /v1/admin/api-keys.

  4. Use the key to create a collection with an embedding API key, upload a document to that collection, and POST a query to its /query endpoint.

Expected outcome

A collection with an uploaded document and a REST query request, following the README's documented workflow.

Guide limitations

  • Turbopuffer must be configured before collection ingestion or queries.
  • The guide follows documented instructions and is not a report of an executed or tested deployment.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
bigRAGIngest supported documents, including PDF, DOCX, PPTX, HTML, Markdown and images.Cloud, Docker, Self-hosted, ServerThe repository is public and identifies the project as open source under the MIT license. The README documents Docker Compose deployment and API-key authentication for HTTP clients.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
bigint/rag.computer · Official homepage title · retained in its source language
How we review sourcesSuggest a correction