RAGFlow

RAGFlow is the open-source Retrieval-Augmented Generation engine built by InfiniFlow Inc. It combines deep document understanding (DeepDoc parsing of PDFs, images, tables and scanned files) with hybrid retrieval — dense vector search, BM25 full-text and tensor/multi-vector re-ranking — and an integrated visual agent platform, to serve as a context layer for LLM applications. The platform ships as an Apache-2.0 self-hosted Docker deployment and as RAGFlow Cloud, a hosted multi-tenant service. Its RESTful HTTP API covers dataset (knowledge base) management, document ingestion and parsing, chunk management, retrieval, chat assistants, sessions, agents, memory, workspace file versioning and search apps, plus an OpenAI-compatible chat-completions surface. A first-party Python SDK and an optional self-hosted Model Context Protocol server expose the same retrieval core to agents.

RAGFlow publishes 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Retrieval Augmented Generation, Search, and Vector Database.

RAGFlow’s developer surface includes documentation, getting-started guide, API reference, engineering blog, support, pricing, signup flow, and 30 more developer resources.

🌐 Visit website 📡 Source on GitHub
1 APIs 1 MCP Servers
CompanyArtificial IntelligenceRetrieval Augmented GenerationSearchVector DatabaseDocument ProcessingKnowledge ManagementAgentsOpen SourceLLMModel Context Protocol

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

RAGFlow HTTP API

The RAGFlow RESTful HTTP API — 95 documented operations under /api/v1, authenticated with a tenant API key carried as a bearer token. Covers dataset management, document upload ...

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

RAGFlow MCP Server

A first-party Model Context Protocol server that InfiniFlow ships inside the RAGFlow repository at mcp/server/server.py. It is an OPTIONAL, DISABLED-BY-DEFAULT component of a RA...

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Ragflow Plans Pricing

5 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Ragflow Rate Limits

3 limits

RATE LIMITS

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Ragflow Authentication

1 scheme

SECURITY

Ragflow Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Ragflow Vulnerability Disclosure

Hackerone

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

GettingStarted
GettingStarted
 SignUp
SignUp
 Sandbox
Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

MCPServer
MCPServer
 AgentSkill
AgentSkill
 LLMsTxt
LLMsTxt

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 Conformance
Conformance
 DataModel
DataModel
 Lifecycle
Lifecycle
 Components
Components

Build 5

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 SourceCode
SourceCode
 Packages
Packages
 SDKs
SDKs
 ToolCrosswalk
ToolCrosswalk

Access & Security 5

Authentication, authorization, and security posture

Compliance
Compliance
 Security
Security
 VulnerabilityDisclosure
VulnerabilityDisclosure
 DomainSecurity
DomainSecurity
 Authentication
Authentication

Operate 7

Status, limits, changes, and where to get help

Roadmap
Roadmap
 Support
Support
 Community
Community
 Deprecation
Deprecation
 ChangeLog
ChangeLog
 ReleaseNotes
ReleaseNotes
 RateLimits
RateLimits

Scroll for all 7

Commercial 4

Pricing, plans, and the legal terms of use

Pricing
Pricing
 TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy
 Plans
Plans

Company 2

The organization behind the API

Website
Website
 Blog
Blog

Source (apis.yml)

apis.yml Raw ↑ 
aid: ragflow
name: RAGFlow
description: RAGFlow is the open-source Retrieval-Augmented Generation engine built by InfiniFlow Inc. It combines deep document
  understanding (DeepDoc parsing of PDFs, images, tables and scanned files) with hybrid retrieval — dense vector search, BM25
  full-text and tensor/multi-vector re-ranking — and an integrated visual agent platform, to serve as a context layer for
  LLM applications. The platform ships as an Apache-2.0 self-hosted Docker deployment and as RAGFlow Cloud, a hosted multi-tenant
  service. Its RESTful HTTP API covers dataset (knowledge base) management, document ingestion and parsing, chunk management,
  retrieval, chat assistants, sessions, agents, memory, workspace file versioning and search apps, plus an OpenAI-compatible
  chat-completions surface. A first-party Python SDK and an optional self-hosted Model Context Protocol server expose the
  same retrieval core to agents.
url: https://raw.githubusercontent.com/api-evangelist/ragflow/refs/heads/main/apis.yml
image: https://ragflow.io/img/logo.svg
x-type: company
x-source: harvest:self-hosted-agent-stack
specificationVersion: '0.20'
created: '2026-08-27'
modified: '2026-08-27'
tags:
- Company
- Artificial Intelligence
- Retrieval Augmented Generation
- Search
- Vector Database
- Document Processing
- Knowledge Management
- Agents
- Open Source
- LLM
- Model Context Protocol
apis:
- aid: ragflow-http-api
  name: RAGFlow HTTP API
  description: The RAGFlow RESTful HTTP API — 95 documented operations under /api/v1, authenticated with a tenant API key
    carried as a bearer token. Covers dataset management, document upload / parse / ingest, chunk management, retrieval, chat
    assistants, sessions, agents, memory, file and workspace-commit management, search apps, and an OpenAI-compatible chat-completions
    endpoint. Documented as a human reference; no machine-readable OpenAPI is published.
  humanURL: https://ragflow.io/docs/http_api_reference
  baseURL: https://cloud.ragflow.io/api/v1
  tags:
  - Retrieval Augmented Generation
  - Search
  - Document Processing
  - Agents
  properties:
  - type: APIReference
    url: https://ragflow.io/docs/http_api_reference
  - type: Documentation
    url: https://ragflow.io/docs
  - type: Authentication
    url: authentication/ragflow-authentication.yml
  - type: ErrorCatalog
    url: errors/ragflow-error-codes.yml
  - type: Conventions
    url: conventions/ragflow-conventions.yml
  - type: DataModel
    url: data-model/ragflow-data-model.yml
  - type: RateLimits
    url: rate-limits/ragflow-rate-limits.yml
  - type: Lifecycle
    url: lifecycle/ragflow-lifecycle.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://ragflow.io/
- type: Documentation
  url: https://ragflow.io/docs
- type: GettingStarted
  url: https://ragflow.io/docs
- type: APIReference
  url: https://ragflow.io/docs/http_api_reference
- type: Blog
  url: https://ragflow.io/blog
- type: GitHubOrganization
  url: https://github.com/infiniflow
- type: SourceCode
  url: https://github.com/infiniflow/ragflow
- type: Roadmap
  url: https://github.com/infiniflow/ragflow/issues/12241
- type: Support
  url: https://ragflow.io/contact-us
- type: Community
  url: https://discord.gg/NjYzJD3GM3
- type: Pricing
  url: https://ragflow.io/#pricing-plan
- type: SignUp
  url: https://cloud.ragflow.io/
- type: TermsOfService
  url: https://ragflow.io/policies/terms
- type: PrivacyPolicy
  url: https://ragflow.io/policies/privacy
- type: Compliance
  url: https://ragflow.io/policies/dpa
- type: Security
  url: security/ragflow-vulnerability-disclosure.yml
- type: VulnerabilityDisclosure
  url: security/ragflow-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/ragflow-domain-security.yml
- type: Packages
  url: packages/ragflow-packages.yml
- type: SDKs
  url: packages/ragflow-packages.yml
- type: MCPServer
  url: mcp/ragflow-mcp.yml
- type: ToolCrosswalk
  url: mcp/ragflow-tool-crosswalk.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/ragflow-llms.txt
- type: Conventions
  url: conventions/ragflow-conventions.yml
- type: ErrorCatalog
  url: errors/ragflow-error-codes.yml
- type: Authentication
  url: authentication/ragflow-authentication.yml
- type: Conformance
  url: conformance/ragflow-conformance.yml
- type: DataModel
  url: data-model/ragflow-data-model.yml
- type: Lifecycle
  url: lifecycle/ragflow-lifecycle.yml
- type: Deprecation
  url: lifecycle/ragflow-lifecycle.yml
- type: ChangeLog
  url: changelog/ragflow-changelog.yml
- type: ReleaseNotes
  url: https://ragflow.io/docs/release_notes
- type: Plans
  url: plans/ragflow-plans-pricing.yml
- type: RateLimits
  url: rate-limits/ragflow-rate-limits.yml
- type: Sandbox
  url: sandbox/ragflow-sandbox.yml
- type: Components
  url: components/ragflow-components.yml
x-enrichment:
  date: '2026-08-27'
  status: enriched
  artifacts_added: 21
  pass: local-v1

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this
  • find_providersBrowse and filter every provider in the catalog.
  • get_provider_artifactsEvery artifact this provider publishes, grouped by type.
  • get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
  • get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
  • get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
  • get_provider_ratingPRO — composite, band, trend and facet scores.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This provider 
curl "https://apis.io/api/v1/providers/ragflow"
All providers 
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose 
curl "https://apis.io/api/v1/providers/ragflow/operations?limit=25"
How their score was established 
curl "https://apis.io/api/v1/providers/ragflow/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.