Catalog / AI & LLM

RAGFlow

RAG engine with deep document understanding and citation-grounded answers

CIS Level 1 hardened Ubuntu 24.04 LTS image by Lynxroute · unique credentials at first boot · CVE-scanned · SBOM and CIS report inside

Availability and pricing
CloudVersionSoftware priceLast build
AWS Marketplace
EC2 AMI · all commercial regions
0.27.3$0.05/hr
Recommended instance: m6i.xlarge · 5-day free trial
2026-10-25Listing ↗
Azure Marketplace
VM image · plan payg-gen2 · Gen2
0.27.2$0.028/vCPU/hr
Recommended VM: Standard_D4s_v3
2026-09-13Listing ↗

Software price only; cloud infrastructure is billed separately by the provider. Prices in USD.

Image facts
Base OSUbuntu 24.04 LTS
HardeningCIS Level 1, Ubuntu 24.04 LTS (tailored)
LicenseApache-2.0
UpstreamInfiniFlow
Machine-readableproduct.json · catalog.json
What is RAGFlow

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.

What the Lynxroute image adds

Security hardening:

  • 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
  • No baked-in admin email, no default credentials shipped on disk - the customer owns the identity layer
  • MySQL, Elasticsearch, MinIO and Redis passwords rotated at first boot (>=32 chars each), never baked into the image
  • Upstream Go admin server (license-tracker module) explicitly NOT enabled - the image runs the pure Apache-2.0 Python server only
  • Containers bound to the docker bridge - no backing store (MySQL, Elasticsearch, MinIO, Redis) is reachable from outside the host
  • Nginx reverse proxy with TLS, HTTP-to-HTTPS redirect, WebSocket support for streaming chat, security headers
  • UFW firewall pre-configured - only TCP 22, 80, 443 are exposed
  • fail2ban, AppArmor
  • CVE scan - every image is scanned for vulnerabilities before release

Out of the box, with no external services:

  • Elasticsearch 8.11.3 vector + full-text store with xpack.security enabled
  • Embedding model bundled inside the upstream ragflow image - no external embedding API key required
  • MinIO blob store for document originals
  • MySQL 8 for users, tenants, knowledge bases, datasets
  • Valkey 8 (BSD-3, OSS Redis fork) for cache + task queue

OS hardening (CIS Level 1):

  • CIS Ubuntu 24.04 LTS Level 1 benchmark applied via ansible-lockdown
  • auditd, SSH hardening, kernel hardening, IMDSv2 enforced

Compliance artifacts:

  • SBOM - CycloneDX 1.6 at /etc/lynxroute/sbom.json
  • CIS Conformance Report at /etc/lynxroute/cis-report.html
  • CIS Tailored Profile at /usr/share/doc/lynxroute/CIS_TAILORED_PROFILE.md
Deploy

Launch in one command

Credentials are generated at first boot and written to /root/ragflow-credentials.txt.

# subscribe once on the AWS Marketplace listing, then:
aws ec2 run-instances \
  --image-id resolve:ssm:/aws/service/marketplace/prod-lu3xmzzxvf7hs/latest \
  --instance-type m6i.xlarge --key-name my-key --security-group-ids sg-xxxxxxxx
# accept the plan terms once, then:
az vm image terms accept --publisher lynxroute --offer ragflow --plan payg-gen2
az vm create -g my-rg -n ragflow --size Standard_D4s_v3 \
  --image lynxroute:ragflow:payg-gen2:latest --admin-username azureuser --generate-ssh-keys
Release notes

Latest release

The most recent release with notes; the full release history is in product.json.

RAGFlow 0.27.3

AWS · 2026-10-25
  • RAGFlow 0.27.3 on Ubuntu 24.04 LTS - patch update from 0.27.2. Apache-2.0 unchanged
  • Retrieval paging past 64 results over MCP, document_ids filtering in the agent retrieval node, and reranking on natural chunk text
  • Adds a Feishu Wiki data-source connector, deletable parser-operator files in pipelines, and HTML-fragment parsing
  • Fixes dataset-scoped authorization for task cancellation and document download, IPv6 transition addresses in the SSRF URL guard, and retries transient S3 storage failures
  • Fixes QA pairs dropped from multiline table cells, large sparse spreadsheet and JSON BOM parsing, and a DOCX preview update loop
  • Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com
  • Rebuilt on the current CIS Level 1 hardened Ubuntu 24.04 LTS base for the latest Ubuntu security updates