# langflow-ai/openrag

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

Repository: https://github.com/langflow-ai/openrag
Canonical: https://ross.abutalabs.com/products/openrag
Homepage: https://www.openr.ag
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T21:55:06+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 29
- inputs: {"age_days": 418, "days_push": 7, "days_rel": 23, "gap_med": 1.0, "n_releases_24m": 53}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4466, forks 465 (observed 2026-08-28T04:08:50.819332+00:00)

## What it is
OpenRAG is an open-source, pre-packaged Retrieval-Augmented Generation platform from IBM that combines Langflow, Docling, and OpenSearch into a single installable package. It provides document ingestion, hybrid semantic search, and an agentic chat interface for querying documents, deployable via Docker with a FastAPI backend and Next.js frontend.

## Use cases
- build a chatbot that answers questions over my documents
- search PDFs and office documents with semantic search
- set up a self-hosted RAG pipeline quickly
- ingest messy real-world documents into a searchable knowledge base
- customize RAG workflows with a visual drag-and-drop builder
- run enterprise document search with hybrid retrieval and re-ranking
- connect cloud storage like Google Drive or SharePoint to an AI search

## When to choose
- you want a batteries-included RAG stack without wiring components yourself
- you need document parsing of complex formats like PDFs via Docling
- you want OpenSearch-backed hybrid search at enterprise scale
- you want to customize retrieval flows visually with Langflow
- you prefer self-hosting with Docker and open-source licensing

## When to avoid
- you need a lightweight embeddable library rather than a full deployed application
- you want a fully managed cloud RAG service with no infrastructure
- your stack requires Elasticsearch or a vector database other than OpenSearch
- you cannot run Docker/Podman or WSL on Windows
- you need a minimal custom pipeline and prefer assembling components yourself

## Facets
- artifact type: application
- maturity: active
- function: rag, search-engine, chatbot, agent-framework, nlp, pdf, web-framework, chat-interface
- domain: large-language-models, artificial-intelligence, self-hosted, developer-tools
- platform: self-hosted, python, cross-platform, windows
- tags: agentic-rag, opensearch, langflow, docling, document-ingestion, semantic-search, enterprise-search, fastapi, nextjs, vector-search, retrieval-augmented-generation, search, ai-agents, docker, web-server, linux, macos

## Member repositories
- langflow-ai/openrag (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:50.819332+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:20:38.659056+00:00, confidence not recorded.
  - readme: https://github.com/langflow-ai/openrag (fetched 2026-08-28T04:08:50.819332+00:00, sha 400e09e2d496)
  - homepage: https://www.openr.ag (fetched 2026-08-29T09:07:17.158633+00:00, sha a0f361e785bc)
  - site_page: https://docs.openr.ag/quickstart (fetched 2026-08-29T09:07:17.162472+00:00, sha 95274f25f1f1)
  - site_page: https://docs.openr.ag/ (fetched 2026-08-29T09:07:17.165003+00:00, sha 820febb48dd3)
- Data as of 2026-08-30T08:39:29.467469+00:00.