{
 "slug": "ragflow",
 "name": "RAGFlow",
 "tagline": "RAG engine with deep document understanding and citation-grounded answers",
 "category": "ai-llm",
 "use_cases": [
  "rag",
  "document-qa",
  "knowledge-base"
 ],
 "aliases": [],
 "status": "live",
 "upstream": {
  "vendor": "InfiniFlow",
  "url": "https://ragflow.io",
  "license": "Apache-2.0",
  "license_url": "https://github.com/infiniflow/ragflow/blob/main/LICENSE"
 },
 "image": {
  "os": "Ubuntu 24.04 LTS",
  "cis_level": 1,
  "ports": [
   80,
   443
  ],
  "artifacts": [
   "/etc/lynxroute/sbom.json",
   "/etc/lynxroute/cis-report.html",
   "/usr/share/doc/lynxroute/CIS_TAILORED_PROFILE.md"
  ]
 },
 "clouds": {
  "aws": {
   "status": "live",
   "version": "0.27.3",
   "last_build": "2026-10-25",
   "entity_id": "prod-lu3xmzzxvf7hs",
   "ami_alias": "/aws/service/marketplace/prod-lu3xmzzxvf7hs/latest",
   "listing_url": "https://aws.amazon.com/marketplace/pp/prodview-rjldiwx7rxadi",
   "recommended_instance_type": "m6i.xlarge",
   "price_usd_per_hour": 0.05,
   "free_trial_days": 5,
   "unit": "instance-hour"
  },
  "azure": {
   "status": "live",
   "version": "0.27.2",
   "last_build": "2026-09-13",
   "offer_id": "ragflow",
   "plan_id": "payg-gen2",
   "image_urn": "lynxroute:ragflow:payg-gen2:latest",
   "listing_url": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/lynxroute.ragflow?tab=Overview",
   "recommended_vm_size": "Standard_D4s_v3",
   "price_usd_per_vcpu_hour": 0.028,
   "unit": "vcpu-hour"
  },
  "alicloud": {
   "status": "not_offered"
  }
 },
 "urls": {
  "page": "https://lynxroute.com/products/ragflow/",
  "json": "https://lynxroute.com/products/ragflow/product.json"
 },
 "release_notes": [
  {
   "version": "0.27.3",
   "title": "RAGFlow 0.27.3",
   "notes": "* RAGFlow 0.27.3 on Ubuntu 24.04 LTS - patch update from 0.27.2. Apache-2.0 unchanged\n* Retrieval paging past 64 results over MCP, document_ids filtering in the agent retrieval node, and reranking on natural chunk text\n* Adds a Feishu Wiki data-source connector, deletable parser-operator files in pipelines, and HTML-fragment parsing\n* Fixes dataset-scoped authorization for task cancellation and document download, IPv6 transition addresses in the SSRF URL guard, and retries transient S3 storage failures\n* Fixes QA pairs dropped from multiline table cells, large sparse spreadsheet and JSON BOM parsing, and a DOCX preview update loop\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the current CIS Level 1 hardened Ubuntu 24.04 LTS base for the latest Ubuntu security updates\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-10-25"
   }
  },
  {
   "version": "0.27.2",
   "title": "RAGFlow 0.27.2",
   "notes": "* RAGFlow 0.27.2 on Ubuntu 24.04 LTS - patch update from 0.27.1. Apache-2.0 unchanged\n* The Agentic RAG retrieval framework has been rebuilt for faster reasoning and stronger benchmark results, and deep document analysis - layout, OCR and table structure - now runs in-process\n* Adds a Sitemap data source for sitemap.xml web ingestion, OneDrive and Zendesk connectors, MonkeyOCRv2 parsing, EPUB document preview, and Excel citations located in the document preview\n* Adds a RERANK_TOKEN_LIMIT_MODE setting, knowledge-compilation runtime settings, and match highlighting in retrieval testing and search\n* Fixes images uploaded in chat being ignored by vision models, non-UTF-8 CSV and TXT decoding, and updates Starlette to 1.3.1 for CVE-2026-54283\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the current CIS Level 1 hardened Ubuntu 24.04 LTS base for the latest Ubuntu security updates\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-09-11",
    "azure": "2026-09-13"
   }
  },
  {
   "version": "0.27.1",
   "title": "RAGFlow 0.27.1",
   "notes": "* RAGFlow 0.27.1 on Ubuntu 24.04 LTS - patch update from 0.27.0. Apache-2.0 unchanged\n* Adds an Azure DevOps data-source connector, You.com and Serply web-search providers, and the Synthorai model provider\n* The retrieval API exposes rerank_candidates_count, KNN top_k and num_candidates, and metadata filters are pushed down to the metadata index for faster retrieval\n* Fixes PDF parsing failures in chat, datasets with zero chunks not being listed, a QA spreadsheet parser dropping rows whose answer is zero, and reasoning-enabled chat ignoring the dialog system prompt\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-09-06",
    "azure": "2026-09-10"
   }
  },
  {
   "version": "0.27.0",
   "title": "RAGFlow 0.27.0",
   "notes": "* RAGFlow 0.27.0 on Ubuntu 24.04 LTS - minor update from 0.26.4. Apache-2.0 unchanged\n* New model providers, filters on the chat and search pages, a wiki folder, and a data compilation layer\n* The task executor is migrated to Go, with embedding support and Google Cloud Storage added\n* Security: a large batch of dependency remediations, covering nginx (CVE-2026-9256), axios, protobuf, httplib2, aiosmtplib, Markdown, cbor2, azure-core and curl_cffi among others\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-08-23"
   }
  },
  {
   "version": "0.26.4",
   "title": "RAGFlow 0.26.4",
   "notes": "* RAGFlow 0.26.4 on Ubuntu 24.04 LTS - maintenance release (patches 0.26.2-0.26.4) with bugfixes: dataflow rerun restore, Ollama and LM-Studio provider fixes, MCP server pagination fix, and document-parser refinements\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-git",
   "live": {
    "aws": "2026-07-20",
    "azure": "2026-07-11"
   }
  },
  {
   "version": "0.26.1",
   "title": "RAGFlow 0.26.1 - June 2026",
   "notes": "* RAGFlow 0.26.1 on Ubuntu 24.04 LTS - maintenance release (patch from 0.26.0)\n* Fixes: corrected token billing and embedding limits; legacy /chat/completions compatibility mode\n* New: editable model types; chat-channel deployments (Discord, Feishu); Langfuse session grouping\n* Certbot pre-installed - enable a trusted HTTPS certificate: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-06-25",
    "azure": "2026-06-21"
   }
  },
  {
   "version": "0.26.0",
   "title": "RAGFlow 0.26.0 - June 2026",
   "notes": "* RAGFlow 0.26.0 on Ubuntu 24.04 LTS\n* Certbot pre-installed for one-command trusted HTTPS\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-06-16"
   }
  },
  {
   "version": "0.25.6",
   "title": "RAGFlow 0.25.6 - June 2026",
   "notes": "* New Browser agent component for autonomous web navigation\n* Lightweight @tool decorator for Python functions\n* RAPTOR AHC (Psi-RAG) mode\n* Bug fixes\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-06-06",
    "azure": "2026-06-08"
   }
  },
  {
   "version": "0.25.5",
   "title": "RAGFlow 0.25.5 - May 2026",
   "notes": "* RAGFlow 0.25.5 on Ubuntu 24.04 LTS\n* Performance: dataset search path latency reduced 50–100% (removed\n  expensive vector fetch and rerank similarity computation), metadata\n  filters pushed down to Infinity backend, Redis caching for TTS,\n  atomic document counter updates, faster server startup + lower\n  memory usage\n* New: local & SSH providers in admin panel\n* Agent: structured output aggregation, metadata filter reuse\n* Various reranking module robustness fixes\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-05-23"
   }
  },
  {
   "version": "0.25.4",
   "title": "RAGFlow 0.25.4 - Initial release (May 2026)",
   "notes": "* RAGFlow 0.25.4 upstream Docker image (infiniflow/ragflow:v0.25.4) on Ubuntu 24.04 LTS\n* Docker Compose stack: ragflow_server + ragflow_mysql (8.0.39) + ragflow_es (8.11.3) + ragflow_minio + ragflow_redis (valkey/valkey:8)\n* CIS Level 1 hardening applied (ansible-lockdown/UBUNTU24-CIS)\n* CVE-scanned before every release\n* Self-registration enabled at first boot; auto-closed by a systemd watcher after the first user signs up\n* MySQL, Elasticsearch, MinIO and Redis passwords (>=32 chars each) rotated per instance at first boot\n* Upstream Go admin server (--enable-adminserver) explicitly NOT enabled - the AMI runs the Apache-2.0 Python server only\n* Backing stores (MySQL, Elasticsearch, MinIO, Redis) bound to the docker bridge only - not reachable from outside the host\n* ragflow container bound to 127.0.0.1:8088; host Nginx terminates TLS on 443\n* No provider API keys pre-configured - operator configures OpenAI, Anthropic, Bedrock, Ollama, etc. in the web UI\n* Persistent storage at /opt/ragflow/{mysql,es,minio,redis} - any of these can be moved to a dedicated EBS volume\n* UFW firewall pre-configured (TCP 22, 80, 443 only)\n* fail2ban, auditd, AppArmor pre-configured\n* SBOM (CycloneDX 1.6) at /etc/lynxroute/sbom.json\n* CIS Conformance Report (OpenSCAP) at /etc/lynxroute/cis-report.html\n* IMDSv2 enforced\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-05-18"
   }
  }
 ],
 "release_history": [
  {
   "version": "0.27.3",
   "aws": "2026-10-25"
  },
  {
   "version": "0.27.2",
   "aws": "2026-09-11",
   "azure": "2026-09-13"
  },
  {
   "version": "0.27.1",
   "aws": "2026-09-06",
   "azure": "2026-09-10"
  },
  {
   "version": "0.27.0",
   "aws": "2026-08-23"
  },
  {
   "version": "0.26.4",
   "aws": "2026-07-20",
   "azure": "2026-07-11"
  },
  {
   "version": "0.26.1",
   "aws": "2026-06-25",
   "azure": "2026-06-21"
  },
  {
   "version": "0.26.0",
   "aws": "2026-06-16"
  },
  {
   "version": "0.25.6",
   "aws": "2026-06-06",
   "azure": "2026-06-08"
  },
  {
   "version": "0.25.5",
   "aws": "2026-05-23"
  },
  {
   "version": "0.25.4",
   "aws": "2026-05-18"
  }
 ],
 "deploy": {
  "aws_cli": "# subscribe once on the AWS Marketplace listing, then:\naws ec2 run-instances \\\n  --image-id resolve:ssm:/aws/service/marketplace/prod-lu3xmzzxvf7hs/latest \\\n  --instance-type m6i.xlarge --key-name my-key --security-group-ids sg-xxxxxxxx",
  "azure_cli": "# accept the plan terms once, then:\naz vm image terms accept --publisher lynxroute --offer ragflow --plan payg-gen2\naz vm create -g my-rg -n ragflow --size Standard_D4s_v3 \\\n  --image lynxroute:ragflow:payg-gen2:latest --admin-username azureuser --generate-ssh-keys"
 },
 "description": {
  "what_is": "RAGFlow is an open-source Retrieval-Augmented Generation engine for enterprise document intelligence. Its deep document understanding layer (deepdoc) parses PDFs, Word, slides, spreadsheets, scanned books and images with layout recognition, table extraction and chunk-level citation tracking - so every answer the LLM produces is traceable back to a paragraph, page, table cell or figure in the original source. RAGFlow ingests files into knowledge bases, builds hybrid vector plus full-text indices in Elasticsearch, stores blobs in MinIO, and exposes a multi-tenant web UI plus REST API plus MCP server for chat, agents, and programmatic retrieval. Supports any LLM provider through a single dropdown - OpenAI, Anthropic Claude, AWS Bedrock, Azure OpenAI, Google Gemini, Cohere, Mistral, DeepSeek, Ollama, vLLM, and many more. Agent workflows let the model browse, run SQL, call tools, and chain retrieval over multiple knowledge bases. Apache-2.0 license, no vendor lock-in.",
  "image_adds": "Security hardening:\n* Self-registration with auto-close - the first user who hits the web UI becomes the workspace owner, then the registration endpoint is closed automatically by a background service\n* No baked-in admin email, no default credentials shipped on disk - the customer owns the identity layer\n* MySQL, Elasticsearch, MinIO and Redis passwords rotated at first boot (>=32 chars each), never baked into the image\n* Upstream Go admin server (license-tracker module) explicitly NOT enabled - the image runs the pure Apache-2.0 Python server only\n* Containers bound to the docker bridge - no backing store (MySQL, Elasticsearch, MinIO, Redis) is reachable from outside the host\n* Nginx reverse proxy with TLS, HTTP-to-HTTPS redirect, WebSocket support for streaming chat, security headers\n* UFW firewall pre-configured - only TCP 22, 80, 443 are exposed\n* fail2ban, AppArmor\n* CVE scan - every image is scanned for vulnerabilities before release\n\nOut of the box, with no external services:\n* Elasticsearch 8.11.3 vector + full-text store with xpack.security enabled\n* Embedding model bundled inside the upstream ragflow image - no external embedding API key required\n* MinIO blob store for document originals\n* MySQL 8 for users, tenants, knowledge bases, datasets\n* Valkey 8 (BSD-3, OSS Redis fork) for cache + task queue\n\nOS hardening (CIS Level 1):\n* CIS Ubuntu 24.04 LTS Level 1 benchmark applied via ansible-lockdown\n* auditd, SSH hardening, kernel hardening, IMDSv2 enforced\n\nCompliance artifacts:\n* SBOM - CycloneDX 1.6 at /etc/lynxroute/sbom.json\n* CIS Conformance Report at /etc/lynxroute/cis-report.html\n* CIS Tailored Profile at /usr/share/doc/lynxroute/CIS_TAILORED_PROFILE.md"
 },
 "generated_at": "2026-10-31T09:36:34Z"
}