{"data":{"slug":"microsoft-rag-time","name":"rag-time","tagline":"RAG Time: A 5-week Learning Journey to Mastering RAG","github_url":"https://github.com/microsoft/rag-time","owner":"microsoft","repo":"rag-time","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"Jupyter Notebook","stars":898,"forks":320,"topics":["ai","azure","binary-quantization","generative-ai","gpt","hnsw","hybrid-search","indexing","keyword-search","language-model","llm","matryoshka-representation-learning","multimodal","openai","rag","responsible-ai","retrieval-augmented-generation","scalar-quantization","vector-search","visual-studio-code"],"archived":false,"github_pushed_at":"2025-06-17T15:00:20+00:00","maintenance_label":"Dormant","stars_delta_30d":5,"url":"https://www.graphcanon.com/tools/microsoft-rag-time","markdown_url":"https://www.graphcanon.com/tools/microsoft-rag-time.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-rag-time","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-rag-time","description":"RAG Time: A 5-week Learning Journey to Mastering RAG","homepage_url":"https://github.com/microsoft/rag-time","license":"MIT","open_issues":4,"watchers":16,"ai_summary":"Provides a structured learning path and resources for mastering Retrieval-Augmented Generation (RAG) techniques.","readme_excerpt":"# RAG Time: Ultimate Guide to Mastering RAG\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n🚀 Master RAG with RAG Time! Learn how to build smarter AI applications with Retrieval-Augmented Generation. This repo includes step-by-step guides, live coding samples, and expert insights—everything you need to go from beginner to RAG pro!\n\n**📺 All episodes of RAG Time are live! [Watch the full series now on YouTube.](https://aka.ms/rag-time/journeys)**\n\n## 🤔 Why Learn RAG with RAG Time?\n\n- **Expert-Led** – Learn directly from AI & Microsoft experts.\n- **Future-Proof Your AI Skills** – Stay ahead with cutting-edge retrieval techniques.\n- **Exclusive Video Content** – Interviews with AI leaders, in-depth tech talks, and practical demonstrations.\n- **Sample Code** – Follow along with ready-to-use implementations and best practices.\n- **Doodles & Visual Explanations** – Complex concepts made simple with engaging visuals.\n  \n## 🚀 Get Started in 3 Easy Steps  \n\n1. [Fork](https://github.com/microsoft/rag-time/fork) the repository.\n2. Clone the repository to your local machine:\n  ```bash\n  git clone https://github.com/your-org/rag-time.git\n  cd rag-time\n  ```\n3. Navigate to the Journey of your choice and follow the README Instructions.\n\n## Learning Journeys\nRAG Time runs every **Wednesday at 9AM PT** from **March 5th to April 2nd**. Each journey covers unique topics with leadership insights, tech talks, and code samples\n| **Journey Page**                                                                                                             | **Description**                                                     | **Video**                                 | **Code Sample**                                                                 | **Blog**                                   |\n|------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------|-------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------|\n| [RAG and Knowledge Retrieval Fundamentals](./Journey%201%20-%20RAG%20and%20Knowledge%20Retrieval%20Fundamentals/README.md)                           | Understand the strategic importance of RAG and knowledge retrieval           | [Watch now](https://aka.ms/rag-time/journey1) | [Sample](./Journey%201%20-%20RAG%20and%20Knowledge%20Retrieval%20Fundamentals/sample/1-RAG-Fundamentals.ipynb)                                                | [Journey 1](https://aka.ms/rag-time/journey1-blog) |\n| [Build the Ultimate Retrieval System](./Journey%202%20-%20Build%20the%20Ultimate%20Retrieval%20System%20for%20RAG/README.md) | Explore how Azure AI Search powers retrieval system                 | [Watch now](https://aka.ms/rag-time/journey2) | [Sample](./Journey%202%20-%20Build%20the%20Ultimate%20Retrieval%20System%20for%20RAG/sample/2-Build-The-Ultimate-Retrieval-System-For-RAG.ipynb) | [Journey 2](https://aka.ms/rag-time/journey2-blog)                                     |\n| [Optimize Your Vector Index at Scale](./Journey%203%20-%20Optimize%20your%20Vector%20Index%20for%20Scale/README.md)          | Learn real-world optimization techniques for scaling vector indexes | [Watch now](https://aka.ms/rag-time/journey3) | [Sample](./Journey%203%20-%20Optimize%20your%20Vector%20Index%20for%20Scale/sample/3-Vector-Compression.ipynb)                                   | [Journey 3](https://aka.ms/rag-time/journey3-blog)                                   |\n| [RAG for All Your Data](./Journey%204%20-%20RAG%20for%20All%20your%20Data%20Multimodal%20and%20Beyond/README.md)             | Discover how multimodal data can be indexed and retrieved           | [Watch now](https://aka.ms/rag-time/journey4) | [Sample](./Journey%204%20-%20RAG%20for%20All%20your%20Data%20Multimodal%20and%20Beyond/s","github_created_at":"2024-12-11T17:25:02+00:00","created_at":"2026-07-11T11:34:45.327745+00:00","updated_at":"2026-08-23T06:02:07.912563+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"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"generative-ai","name":"generative-ai"},{"slug":"hybrid-search","name":"hybrid-search"},{"slug":"indexing","name":"indexing"},{"slug":"language-model","name":"language-model"},{"slug":"llm","name":"llm"},{"slug":"rag","name":"rag"},{"slug":"vector-search","name":"vector-search"}],"trust":{"provenance":{"is_fork":false,"github_id":901986230,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-23T06:02:07.165Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":431,"last_release_at":null,"stars_delta_30d":5,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:34:46.910Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-23T06:02:07.643Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-08-23T06:02:07.643Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-23T06:02:07.643Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":8,"requires_docker":false},"constraints":{"min_ram_gb":8,"requires_docker":false},"when_to_use":["When you need a detailed, week-by-week learning path specifically focused on the nuances of RAG techniques, from basics to advanced applications.","If your project requires understanding both indexing methods (like HNSW and Hybrid Search) and generation models for effective RAG implementations."],"when_not_to_use":["If you prefer ad-hoc or self-directed learning without a structured timeline. Other tools may offer more flexible formats, which can be preferable if adhering to strict schedules is not ideal.","When your focus is solely on either indexing or generation models and not the integration of both for RAG. In this case, specialized resources for just indexing or model training might suffice."],"source":"enrich:decision_facts","observed_at":"2026-07-12T17:45:39.309Z"},"constraint_facets":{"min_ram_gb":8,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Min 8 GB RAM"},{"label":"Adopt for","value":"RAG Time is tailored for those looking to systematically learn and apply Retrieval-Augmented Generation techniques in a structured 5-week program."},{"label":"License detail","value":"The MIT License provides freedom to use, copy, modify and distribute the software provided that copyright and license information are retained."}]}}