{"data":{"slug":"ledat98-nexusrag","name":"NexusRAG","tagline":"Hybrid RAG system with vector search and knowledge graph","github_url":"https://github.com/LeDat98/NexusRAG","owner":"LeDat98","repo":"NexusRAG","owner_avatar_url":"https://avatars.githubusercontent.com/u/121386506?v=4","primary_language":"Python","stars":497,"forks":106,"topics":["chromadb","citation","docling","document-parsing","fastapi","gemini","knowledge-base","knowledge-graph","lightrag","ollama","rag","react","reranking","retrieval-augmented-generation","streaming","vector-search"],"archived":false,"github_pushed_at":"2026-04-20T14:20:09+00:00","maintenance_label":"Slowing","stars_delta_30d":163,"url":"https://www.graphcanon.com/tools/ledat98-nexusrag","markdown_url":"https://www.graphcanon.com/tools/ledat98-nexusrag.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ledat98-nexusrag","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ledat98-nexusrag","description":"Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual intelligence (image/table captioning), agentic streaming chat, and inline citations. Powered by Gemini or local Ollama models.","homepage_url":null,"license":null,"open_issues":3,"watchers":5,"ai_summary":"NexusRAG is a hybrid Retrieval-Augmented Generation (RAG) system that integrates vector search capabilities with a knowledge graph. It includes features such as document parsing, visual intelligence, agentic streaming chat, and inline citations.","readme_excerpt":"### Option A: Docker (Full Stack)\n\n```bash\ngit clone https://github.com/LeDat98/NexusRAG.git\ncd NexusRAG\ncp .env.example .env","github_created_at":"2026-03-15T08:08:42+00:00","created_at":"2026-07-11T11:36:28.738141+00:00","updated_at":"2026-08-23T12:02:08.754793+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"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"},{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"chromadb","name":"chromadb"},{"slug":"citation","name":"citation"},{"slug":"docling","name":"docling"},{"slug":"document-parsing","name":"document-parsing"},{"slug":"fastapi","name":"fastapi"},{"slug":"gemini","name":"gemini"},{"slug":"knowledge-base","name":"knowledge-base"},{"slug":"knowledge-graph","name":"knowledge-graph"}],"trust":{"provenance":{"is_fork":false,"github_id":1182227156,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-23T12:02:07.972Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":124,"last_release_at":null,"stars_delta_30d":163,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:36:30.032Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-23T12:02:08.439Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-08-23T12:02:08.439Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-23T12:02:08.439Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-08-23T12:02:08.439Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Be cautious about compatibility with specific models and dependencies, as the repository does not specify comprehensive dependency management."],"requires_docker":false},"constraints":{"requires_docker":false},"when_to_use":["Use NexusRAG if you need to incorporate both vector search capabilities and a rich knowledge graph into your AI application.","When your application benefits from the integration of Gemini or local Ollama models for enhanced text understanding and generation."],"when_not_to_use":["Avoid using NexusRAG in scenarios where real-time processing power is limited, as agentic streaming chat and visual intelligence can be computationally intensive.","NexusRAG might not be the best fit if your project strictly requires open-source licensing compliance due to its unknown license status."],"source":"enrich:decision_facts","observed_at":"2026-07-12T18:16:31.678Z"},"constraint_facets":{"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Be cautious about compatibility with specific models and dependencies, as the repository does not specify comprehensive dependency management."},{"label":"Adopt for","value":"NexusRAG is a hybrid RAG system integrating vector search with a knowledge graph. It supports document parsing, visual intelligence (such as image/table captioning), agentic streaming chat, and inline citations."}]}}