{"data":{"slug":"automataia-graphrag-rs","name":"graphrag-rs","tagline":"GraphRAG-rs implements Graph-based Retrieval Augmented Generation for knowledge graph creation and natural language querying with entity extraction and LLM integration.","github_url":"https://github.com/automataIA/graphrag-rs","owner":"automataIA","repo":"graphrag-rs","owner_avatar_url":"https://avatars.githubusercontent.com/u/53933533?v=4","primary_language":"Rust","stars":526,"forks":50,"topics":["ai","embeddings","entity-extraction","graphrag","knowledge-graph","llama-cpp","llm","nlp","ollama-api","retrieval-augmented-generation","rust","rust-crate","semantic-search","vector-search"],"archived":false,"github_pushed_at":"2026-06-02T20:02:47+00:00","maintenance_label":"Steady","stars_delta_30d":4,"url":"https://www.graphcanon.com/tools/automataia-graphrag-rs","markdown_url":"https://www.graphcanon.com/tools/automataia-graphrag-rs.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/automataia-graphrag-rs","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=automataia-graphrag-rs","description":"GraphRAG-rs is a high-performance, state-of-the-art Rust implementation of GraphRAG (Graph-based Retrieval Augmented Generation) that builds knowledge graphs from documents and enables natural language querying with configurable entity extraction and local LLM integration","homepage_url":"https://automataia.github.io/graphrag-rs/","license":"MIT","open_issues":0,"watchers":6,"ai_summary":"A Rust implementation of GraphRAG that constructs knowledge graphs from documents, supporting natural language queries through configurable entity extraction and local LLM integration.","readme_excerpt":"## 30-Second Quick Start\n\n**CLI (no config file needed):**\n\n```bash\ncargo install --path graphrag-cli           # one-time install\ngraphrag index ./mydoc.txt                  # builds ./graphrag-data\ngraphrag ask \"What is the main topic?\"      # answers from the graph\n```\n\nAdd `--ollama` to either command for LLM-quality entity extraction\n(requires `ollama serve` running locally).\n\n**Library (Rust):**\n\n```rust\nuse graphrag::GraphRAG;\n\n#[tokio::main]\nasync fn main() -> anyhow::Result<()> {\n    let mut g = GraphRAG::quick_start(\"Plato's Symposium full text here...\").await?;\n    println!(\"{}\", g.ask(\"Who is Diotima?\").await?);\n    Ok(())\n}\n```\n\nBoth flows use sensible defaults — hash-fallback embeddings, pattern-based\nentity extraction, persistent workspace. Opt into Ollama / GLiNER / custom\nchunking with the builder when you need more.\n\n---\n\n### System Requirements\n- **Rust 1.85+** with `wasm32-unknown-unknown` target\n- **Node.js 18+** (for WASM builds)\n- **Git** for cloning\n\n---\n\n# Install Visual Studio Build Tools with C++ support\n\n---\n\n# Install Rust with Windows target support\nrustup target add wasm32-unknown-unknown\n```\n\n---\n\n## Deployment Options\n\nGraphRAG-rs supports **three deployment architectures** - choose based on your needs:\n\n---\n\n# Install trunk for WASM builds\ncargo install trunk wasm-bindgen-cli\n\n---\n\n# Optional: Install globally\ncargo install --path .\n```\n\n---\n\n## Quick Start (5 Lines!)\n\nThe fastest way to get started with GraphRAG:\n\n```rust\nuse graphrag_core::prelude::*;\n\n#[tokio::main]\nasync fn main() -> Result<()> {\n    let mut graphrag = GraphRAG::quick_start(\"Your document text\").await?;\n    let answer = graphrag.ask(\"What is this about?\").await?;\n    println!(\"{}\", answer);\n    Ok(())\n}\n```\n\n---\n\n# backend = \"jina\"       # Cost-optimized ($0.02/1M)\n\n---\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.","github_created_at":"2025-09-21T19:03:13+00:00","created_at":"2026-07-11T11:35:12.578654+00:00","updated_at":"2026-08-23T06:02:23.258958+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"embeddings","name":"embeddings"},{"slug":"entity-extraction","name":"entity-extraction"},{"slug":"graphrag","name":"graphrag"},{"slug":"knowledge-graph","name":"knowledge-graph"},{"slug":"llama-cpp","name":"llama-cpp"},{"slug":"llm","name":"llm"},{"slug":"nlp","name":"nlp"}],"trust":{"provenance":{"is_fork":false,"github_id":1061365581,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-23T06:02:22.548Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":81,"last_release_at":null,"stars_delta_30d":4,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:35:14.619Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-23T06:02:22.980Z"},"languages":{"value":["rust"],"source":"github.language","observed_at":"2026-08-23T06:02:22.980Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-23T06:02:22.980Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need Rust-based implementation for integration into existing Rust projects","Require state-of-the-art GraphRAG performance for document to graph conversion"],"when_not_to_use":["Seeking solutions that offer cloud-hosted machine learning services directly","Projects that demand Python libraries due to ecosystem dependencies"],"source":"enrich:decision_facts","observed_at":"2026-07-15T10:00:39.403Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"GraphRAG-rs creates knowledge graphs from documents, enables natural language querying with customizable entity extraction and local LLM support, written in Rust."}]}}