Freeper month
$0/month
- 5 Apps, 1 team member, 0.1 GB dataset storage, 500 credits/month, API key not available
Finding your next stop…
Loading the latest directory information.
Loading the latest directory information.
Start here for the decision-making essentials: what RAGFlow does, who it is for, how it is accessed, and the first-party sources behind this profile.
$0/month
$29/month
$129/month
Open-source RAG engine delivering citation-backed question answering with an integrated agent platform combining RAG, tools, and MCPs. Features vector search, BM25, re-ranking, multi-format ingestion, Knowledge Compilation, GraphRAG, and multi-agent orchestration.
Read-only public captures of RAGFlow’s homepage. Screenshots are dated, never live embeds, and open full-screen.
Short answers to the questions buyers and builders commonly ask about RAGFlow. Each answer cites the shared ledger below, where every source is listed once.
Open-source RAG engine delivering grounded, citation-backed question answering and an inte · Combines vector search, BM25, and custom scoring with advanced re-ranking for retrieval, p · Knowledge Compilation Engine introduced in 0.27 as an intelligent agent data foundation · Agentic Retrieval framework upgraded in 0.27
Empower your AI agents through the leading open-source RAG engine, delivering reliable context and an integrated agent platform, built for enterprise.
Multi-agent orchestration use cases such as autonomous stock analysis (ticker identificati · Education: parse textbook and handout structure, map knowledge concepts, generate lesson s · Legal & Compliance: contract risk review, due diligence brief generation from public and i · Manufacturing: ingest SOPs, work instructions, equipment manuals, and work orders; respond
Enables advanced stock analysis through autonomous planning and multi-agent orchestration.
RAGFlow v0.27.0 is the last major version with Python as the backend language.
As the last major version with Python as the backend language
Free | $0/month | 5 Apps, 1 team member, 0.1 GB dataset storage, 500 credits / month, API · Starter | $29/month | 50 Apps, 5 team members, 5 GB dataset storage, 5,000 credits / month · Pro | $129/month | Unlimited Apps, 20 team members, 50 GB dataset storage, 20,000 credits
Free Start for free and explore essential features to get your project off the ground. - 5 Apps - 1 team members - 0.1 GB dataset storage - 500 credits / month - API key not available
Offers HTTP and Python APIs to integrate RAGFlow capabilities into external applications.
RAGFlow also offers HTTP and Python APIs for you to integrate RAGFlow's capabilities into your applications.
Supports ingestion of documents (PDF, DOC, DOCX, TXT, MD, MDX), tables (CSV, XLSX, XLS), p · RAGFlow integrates natively with mainstream financial data sources to support stock resear
File formats that RAGFlow supports include documents (PDF, DOC, DOCX, TXT, MD, MDX), tables (CSV, XLSX, XLS), pictures (JPEG, JPG, PNG, TIF, GIF), and slides (PPT, PPTX).
This profile connects the jobs RAGFlow is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.
Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.
HTTP 200 verified twice
RAGFlow
Open-source RAG (Retrieval-Augmented Generation) engine · Citation-backed question answering with integrated agent platform · Visual workflows combining RAG, tools, and MCPs
Open-source RAG engine delivering grounded, citation-backed question answering and an integrated agent platform with visual workflows combining RAG, tools, and MCPs.
Combines vector search, BM25, and custom scoring with advanced re-ranking for retrieval, plus a built-in ingestion pipeline that cleanses and structures multi-format data into rich semantic representations.
Multi-agent orchestration use cases such as autonomous stock analysis (ticker identification, external/internal insight aggregation, combined with financial metrics) and structured legal precedent analysis across case law.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine available for self-hosting.
Deployable via Docker on Linux, macOS, or Windows; officially supports x86 CPU and Nvidia GPU with ARM64 Docker images not maintained.
Enterprise deployment options include BYOC (Bring Your Own Cloud) and on-premises with dedicated support and custom SLA.
Latest release is RAGFlow v0.27.2 (stable), with a nightly unstable build also available; uses Elasticsearch or Infinity for multiple recall and integrates with mainstream LLMs (including Ollama, Xinference, LocalAI for local LLM deployment
Free | $0/month | 5 apps, 1 team member, 0.1 GB dataset storage, 500 credits/month, API key not available
Starter | $29/month | 50 Apps, 5 team members, 5 GB dataset storage, 5,000 credits/month, API key available
A concise view of the jobs, capabilities and integrations described in the recorded product sources.
Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.
A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.
Showing the newest updates and meaningful milestones. Open an entry for its summary and source.
Adds an Azure DevOps data source connector, You.com and Serply web search providers, a Synthorai model provider, missing DeepSeek models, and AWS Bedrock API key authentication; the retrieval API now exposes rerank_candidates_count, knn top_k, and num_candidat
View source [6]Major version introducing a brand new document experience (full details truncated in the supplied changelog excerpt); the dedicated blog announcement frames this release around Knowledge Compilation and Agentic Retrieval.
View source [6]Adds a language-aware Snowball stemmer covering 16 languages and ships bug fixes across MCP, OCR, and UI components.
View source [6]Adds Google BigQuery as a data source connector, two new MCP tools, the SoMark OCR parser, and exposes the Ingest documents API endpoint.
View source [6]Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.
These tools share a workflow, capability or audience with RAGFlow. They may complement it rather than replace it, and are not presented as integrations or endorsements.
Pro | $129/month | Unlimited Apps, 20 team members, 50 GB dataset storage, 20,000 credits/month, API key available
Supports ingestion of documents (PDF, DOC, DOCX, TXT, MD, MDX), tables (CSV, XLSX, XLS), pictures (JPEG, JPG, PNG, TIF, GIF), and slides (PPT, PPTX), plus data source connectors including Azure DevOps, Google BigQuery, WebDAV, Sitemap, Outl
Offers HTTP and Python APIs to integrate RAGFlow capabilities into external applications.
Implements reasonable technical and organizational measures to protect Personal Data, uses Standard Contractual Clauses or equivalent transfer mechanisms for international data transfers, and supports data subject rights including access, c
Education: parse textbook and handout structure, map knowledge concepts, generate lesson structure, board notes, and practice sets, and grade assignments with leveled personalized feedback
Legal & Compliance: contract risk review, due diligence brief generation from public and internal materials, evidence timeline and exhibit indexing, and clause template standardization
Manufacturing: ingest SOPs, work instructions, equipment manuals, and work orders; respond to alarm codes with cited checks; and draft corrective actions from defect data
RAGFlow is an open-source project recognized among GitHub's Fastest-Growing Open Source Projects
RAGFlow 0.27.0 (latest released version at time of evidence)
2026-08-24 (RAGFlow 0.27.0)
Knowledge Compilation Engine introduced in 0.27 as an intelligent agent data foundation
Agentic Retrieval framework upgraded in 0.27
Memory module and Memory API giving AI Agents lasting memory and task-relevant historical experience retrieval
Multi-Agent Deep Research introduced in RAGFlow 0.20.0
Command-line interface (CLI) for back-end management
GraphRAG for revealing hidden relationships across documents
RAGFlow introduces a Knowledge Compilation Engine that parses, chunks, and indexes documents, then identifies entities, relationships, concepts, temporal information, and hierarchical structures to produce reusable Knowledge Artifacts.
Advanced Stock Research solution cleanses and extracts multimodal data including reports, contracts, and recordings, with traceable source citations.
RAGFlow consolidates regulatory documents and internal rules to enable auditors to quickly locate compliance evidence.
RAGFlow enforces real-time document-level ACLs and granular multi-level isolation across tenant, department, role, and project-level boundaries with strict static and dynamic security controls.
Each RAGFlow response cites its source, enabling one-click navigation to the original paragraph or clause.
RAGFlow integrates natively with mainstream financial data sources to support stock research and decision-making workflows.
RAGFlow v0.27.0 was released on 24 Aug 2026.
RAGFlow v0.27.0 is the last major version with Python as the backend language.
RAGFlow positions itself as an intelligent agent data foundation built on knowledge compilation to serve various agent frameworks.
RAGFlow is an open-source RAG engine · Built-in ingestion pipeline cleanses and processes multi-format data into rich semantic re · Combines vector search, BM25, and custom scoring with advanced re-ranking for answer accur
Yes, RAGFlow is an open-source RAG engine
Multi-format data ingestion pipeline that cleanses and structures data into rich semantic representations for retrieval
