ragflow
infiniflow/ragflow
RAGFlow is an open-source Retrieval-Augmented Generation engine based on deep document understanding. It provides robust ingestion, OCR, parsing, and workflow canvas components for building enterprise-grade RAG applications.
87.7k 10.3kApache-2.0Updated 2026-08-13
85
GreatOverview
RAGFlow is a comprehensive RAG (Retrieval-Augmented Generation) framework designed to handle complex document parsing, OCR, and multi-format data ingestion. It leverages a dual-stack backend featuring Python (Quart, Peewee) and Go modules for high-performance parsing and server execution, coupled with a React/TypeScript frontend workspace. The codebase emphasizes strict code cleanliness, aggressive refactoring of legacy compatibility layers, and tiered testing using specialized build flags.
Capabilities
- ▸Deep document parsing and OCR via deepdoc integrations
- ▸Multi-service RAG workflow orchestration and agent canvas execution
- ▸Tiered Go and Python testing pipelines with CGO dependencies
- ▸Full-stack development environment supporting Python 3.13+, Go, and React+Vite
Best for
Developing and maintaining the RAGFlow core engine codebase, Configuring advanced document parsing pipelines for PDF, DOCX, XLSX, and markdown documents, Running integrated backend and frontend validation tests using custom build scripts, Orchestrating multi-service local development with Docker Compose and various vector/search backends
Works with
Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
85Task usefulness20%77 → +15.4
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%49 → +5.9
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%100 → +15.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%100 → +8.0
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total85.0 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Standard repository development guidelines with no specific elevated security vulnerabilities noted in the operating instructions. Standard database and storage service credentials management applies via local configuration and docker-compose files.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.