RAGFlow
What it is
RAGFlow is an open-source retrieval-augmented generation engine and integrated agent platform for building a context layer for AI agents. Its ingestion pipeline processes data in multiple formats into semantic representations for retrieval. Search brings together vector search, BM25, custom scoring, and advanced reranking. Visual workflows connect RAG, tools, and MCPs for agent orchestration, while model connections support online, local, and OpenAI-compatible providers for knowledge bases, chats, search, and agents. Documented sources include Notion, Google Drive, S3, Microsoft Teams, REST API, and Sitemap. RAGFlow provides HTTP and Python APIs, and a chat assistant can be embedded in another webpage with an iframe. Docker deployment is documented with a minimum build requirement of 4 CPU cores, 16 GB RAM, and 50 GB disk. The free plan includes five apps, one team member, 0.1 GB dataset storage, and 500 monthly credits, but no API key. Paid plans start at $29 per month; the Starter plan includes an API key. ARM users may need to build their own image, as RAGFlow says it does not maintain ARM Docker images.
For and against
For
- Search combines vector search and BM25.
- Visual workflows integrate RAG, tools, and MCPs.
- HTTP and Python APIs are available.
- Supports cloud and self-hosted deployment.
- Starter plan includes an API key.
Against
- Free plan does not include an API key.
- Docker deployment requires at least 4 CPU cores, 16 GB RAM, and 50 GB disk.
- RAGFlow does not maintain ARM Docker images.
- Paid plans start at $29 per month.
The verdict
RAGFlow combines data ingestion, search, model connections, and agent workflow tools, with both cloud and self-hosted options. Teams should account for the free plan’s limits and the stated Docker and ARM considerations.
Who it suits
RAGFlow is described as built for enterprise, with listed solutions for financial services, legal and compliance, manufacturing, and education. It suits teams building retrieval and agent workflows that need cloud or self-hosted deployment.
Plans and prices
Free
5 apps · 1 team member · 0.1 GB dataset storage · 500 credits/month
Read 15 Oct 2026 · ragflow.io
Starter
50 apps · 5 team members · 5 GB dataset storage · 5,000 credits/month
Read 15 Oct 2026 · ragflow.io
Pro
Unlimited apps · 20 team members · 50 GB dataset storage · 20,000 credits/month
Read 15 Oct 2026 · ragflow.io
Enterprise
BYOC deployment · on-premises deployment · dedicated support · custom SLA
Read 15 Oct 2026 · ragflow.io
On the record
- Agent orchestration
- Visual workflows combine retrieval, tools and MCP services for agent construction.ragflow.io · read 15 Oct 2026
- Agent workflows
- Its visual workflows integrate RAG, tools, and MCPs for agent orchestration.ragflow.io · read 29 Sep 2026
- API and embedding
- RAGFlow provides HTTP and Python APIs and supports embedding a Chat assistant in a third-party webpage with an iframe.ragflow.io · read 29 Sep 2026
- API migration
- RAGFlow 1.0 moves its public REST backend from Python to Go and documents endpoint and parameter changes.ragflow.io · read 15 Oct 2026
- Architecture limitation
- The official Go image targets Linux AMD64; ARM64 requires a matching dependency image and native libraries.ragflow.io · read 15 Oct 2026
- Chat channels
- Supported chat-channel integrations include Discord, DingTalk, Telegram, WeCom and Feishu/Lark.ragflow.io · read 15 Oct 2026
- Chunking control
- Users can inspect chunking results and intervene in parsing through configurable chunk templates.ragflow.io · read 15 Oct 2026
- Company founded
- LinkedIn lists InfiniFlow as founded in 2023.linkedin.com · read 15 Oct 2026
- Company headquarters
- LinkedIn lists InfiniFlow headquarters in Shanghai, China.linkedin.com · read 15 Oct 2026
- Company legal name
- Crunchbase lists the legal name as InfiniFlow Inc.crunchbase.com · read 15 Oct 2026
- Company size
- LinkedIn lists InfiniFlow as having 11–50 employees.linkedin.com · read 15 Oct 2026
- Data connectors
- Documented data sources include Notion, Google Drive, S3, Microsoft Teams, REST API, and Sitemap.ragflow.io · read 29 Sep 2026
- Data processing
- Its built-in ingestion pipeline cleanses and processes multi-format data into semantic representations for retrieval.ragflow.io · read 29 Sep 2026
- Deep document understanding
- RAGFlow supports parsing complex documents such as scanned PDFs, tables, images and slide decks.ragflow.io · read 15 Oct 2026
- Deployment complexity
- Independent analysis says Docker deployment also runs Elasticsearch or Infinity, MinIO, MySQL and Redis, increasing operational complexity.datacamp.com · read 15 Oct 2026
- Developer interfaces
- Independent documentation describes web UI, REST, Python and JavaScript APIs, MCP and agent workflows.andrew.ooo · read 15 Oct 2026
- Document ingestion
- Its built-in ingestion pipeline cleans and processes multi-format data into semantic representations for retrieval.ragflow.io · read 15 Oct 2026
- Enterprise support
- The Enterprise plan lists dedicated support and a custom SLA.ragflow.io · read 29 Sep 2026
