{"data":{"slug":"bessouat40-raglight","name":"RAGLight","tagline":"A modular framework for Retrieval-Augmented Generation that supports integration with various LLMs and external tools.","github_url":"https://github.com/Bessouat40/RAGLight","owner":"Bessouat40","repo":"RAGLight","owner_avatar_url":"https://avatars.githubusercontent.com/u/71939720?v=4","primary_language":"Python","stars":670,"forks":101,"topics":["agentic-ai","agentic-rag","agentic-workflow","artificial-intelligence","data-science","framework","huggingface","lmstudio","mcp","mcp-tools","mistral-api","mistralai","ollama","openai","openai-api","rag","retrieval-augmented","retrieval-augmented-generation","vector-database"],"archived":false,"github_pushed_at":"2026-06-25T19:10:20+00:00","maintenance_label":"Steady","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/bessouat40-raglight","markdown_url":"https://www.graphcanon.com/tools/bessouat40-raglight.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bessouat40-raglight","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bessouat40-raglight","description":"RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.","homepage_url":"https://raglight.mintlify.app/","license":"MIT","open_issues":12,"watchers":5,"ai_summary":"RAGLight offers a flexible way to integrate different LLMs, embeddings, vector stores, and third-party tools using MCP.","readme_excerpt":"### Deploy with Docker Compose\n\nThe quickest way to deploy in production :\n\n```bash\ncd examples/serve_example\ncp .env.example .env   # edit values as needed\ndocker-compose up\n```\n\nThe `docker-compose.yml` uses `extra_hosts: host.docker.internal:host-gateway` so the container can reach an Ollama instance running on the host machine.\n\n---\n\n---\n\n## Use RAGLight with Docker\n\nYou can use RAGLight inside a Docker container easily.\nFind Dockerfile example here : [examples/Dockerfile.example](https://github.com/Bessouat40/RAGLight/blob/main/examples/Dockerfile.example)","github_created_at":"2024-12-12T20:37:11+00:00","created_at":"2026-07-11T11:27:45.509274+00:00","updated_at":"2026-08-22T00:01:00.815035+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"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"}],"tags":[{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"data-science","name":"data-science"},{"slug":"framework","name":"framework"},{"slug":"huggingface","name":"huggingface"},{"slug":"mcp-tools","name":"mcp-tools"},{"slug":"retrieval-augmented-generation","name":"retrieval-augmented-generation"},{"slug":"vector-database","name":"vector-database"}],"trust":{"provenance":{"is_fork":false,"github_id":902570217,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T00:01:00.044Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":57,"last_release_at":"2026-03-24T15:38:42Z","stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:27:46.862Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T00:01:00.495Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-22T00:01:00.495Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-22T00:01:00.495Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-22T00:01:00.495Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you require seamless integration with various Language Models (LLMs) like Hugging Face or OpenAI models, making RAGLight a suitable choice for diverse model environments.","If your project necessitates flexible connection to third-party tools and data sources via MCP, allowing for extended functionalities beyond standard Retrieval-Augmented Generation capabilities."],"when_not_to_use":["Avoid using RAGLight if your workflow strictly demands proprietary integration methods that are not supported by its modular framework structure.","If the project focuses on a specific LLM without the need for flexibility or interchangeability, the overhead of configuring diverse integrations in RAGLight might be unnecessary."],"source":"enrich:decision_facts","observed_at":"2026-07-14T21:42:57.927Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"RAGLight emerges as an adaptable framework for Retrieval-Augmented Generation, offering integration flexibility with multiple LLMs and external tools through MCP."}]}}