[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-82462":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},82462,"llm-zoomcamp","DataTalksClub\u002Fllm-zoomcamp","DataTalksClub","LLM Zoomcamp - a free online course about real-life applications of LLMs. In 10 weeks you will learn how to build an AI system that answers questions about your knowledge base.","",null,"Jupyter Notebook",6188,1094,107,1,0,541,779,795,1623,112.12,false,"main",true,[],"2026-06-12 04:01:38","\u003Cdiv align=\"center\">\n\n\u003Cimg width=\"80%\" src=\"images\u002Fllm-zoomcamp-2026.jpg\" alt=\"LLM Zoomcamp 2026 - Free Course on Building LLM Applications with RAG, Agents, and Vector Search\" \u002F>\n\n\u003Ch1>LLM Zoomcamp: Free Course on Building LLM Applications with RAG, Agents & Vector Search\u003C\u002Fh1>\n\u003Ch3>Go from LLM basics to a production-ready AI assistant in 10 weeks\u003C\u002Fh3>\n\n\u003Cp>Learn Retrieval-Augmented Generation, vector search, embeddings, AI agents, function calling, evaluation, monitoring, hybrid search, reranking, and more - all in a free, open-source, hands-on course by \u003Ca href=\"https:\u002F\u002Fdatatalks.club\u002F\">DataTalks.Club\u003C\u002Fa>.\u003C\u002Fp>\n\n\u003Ca href=\"https:\u002F\u002Fairtable.com\u002FappPPxkgYLH06Mvbw\u002Fshr7WtxHEPXxaui0Q\">\u003Cimg src=\"https:\u002F\u002Fuser-images.githubusercontent.com\u002F875246\u002F185755203-17945fd1-6b64-46f2-8377-1011dcb1a444.png\" height=\"50\" \u002F>\u003C\u002Fa>\n\n\n[![PRs Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg?style=for-the-badge)](CONTRIBUTING.md)\n[![Join Slack](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSlack-Join%20Community-4A154B?style=for-the-badge&logo=slack)](https:\u002F\u002Fdatatalks.club\u002Fslack.html)\n\n⭐ Star this repo to stay updated with new modules and cohort announcements\n\n\u003C\u002Fdiv>\n\n## 🔗 Quick Links & Resources\n\n| Resource | Link |\n|-|-|\n| 📁 Course materials | [GitHub repository](https:\u002F\u002Fgithub.com\u002FDataTalksClub\u002Fllm-zoomcamp) |\n| 🎥 Video lectures | [YouTube playlist](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL3MmuxUbc_hIB4fSqLy_0AfTjVLpgjV3R) |\n| 📅 Cohort schedule & deadlines | [courses.datatalks.club](https:\u002F\u002Fcourses.datatalks.club\u002Fllm-zoomcamp-2026) |\n| 💬 Slack community | [#course-llm-zoomcamp](https:\u002F\u002Fapp.slack.com\u002Fclient\u002FT01ATQK62F8\u002FC06TEGTGM3J) |\n| 📣 Announcements | [Telegram](https:\u002F\u002Ft.me\u002Fllm_zoomcamp) |\n| 🏆 2025 cohort projects | [courses.datatalks.club\u002Fllm-zoomcamp-2025\u002Fprojects](https:\u002F\u002Fcourses.datatalks.club\u002Fllm-zoomcamp-2025\u002Fprojects) |\n\n\nLLM Zoomcamp teaches you how to build practical, production-ready LLM applications step by step.\n\n## 👥 Who Should Join?\n\nThis course is for people who learn by doing. After completing it, you'll have a working codebase and the hands-on experience to build your own LLM-powered applications.\n\n- Software Engineers: Add LLMs, RAG, and modern search capabilities to real products\n- Data Engineers: Understand how vector search, hybrid search, and retrieval pipelines fit into production systems\n- ML Practitioners: Get a structured way to evaluate and monitor LLM-based applications\n\n\n## 🎓 Prerequisites\n\n- Python: You can write code confidently\n- Command Line: Comfortable with terminal\n- Docker: Basic familiarity\n- ML \u002F LLMs: Not required\n- Hardware: Any laptop or PC. No GPU needed\n- Expenses: ~$1-5 in API credits\n\n> [!NOTE]\n> If you can write a Python function and have heard of ChatGPT, you have enough to get started.\n\n\n\n## 🗓️ How to Take LLM Zoomcamp\n\nThere are two ways to follow the course: live and self-paced.\n\n| | Live Cohort | Self-Paced |\n|-|-|-|\n| Start | June 8, 2026, 17:00 CET | Anytime |\n| Lectures | Pre-recorded | Pre-recorded |\n| Homework | Graded | Available but not scored |\n| Leaderboard | ✅ Yes | ❌ No |\n| Peer Review | ✅ Yes | ❌ No |\n| Certificate | ✅ Yes | ❌ No |\n| Cost | Free | Free |\n| Register | [Sign up here](https:\u002F\u002Fairtable.com\u002FappPPxkgYLH06Mvbw\u002Fshr7WtxHEPXxaui0Q) | Just start learning! |\n\n> [!IMPORTANT]\n> \"Live cohort\" does not mean live classes. All lectures are pre-recorded. \"Live\" means working with others, having deadlines, getting your homework and project scored, review your peers, and getting a certificate at the end.\n\nSelf-paced steps:\n\n1. Follow the materials on [GitHub](https:\u002F\u002Fgithub.com\u002FDataTalksClub\u002Fllm-zoomcamp)\n2. Ask questions and share progress in [Slack](https:\u002F\u002Fdatatalks.club\u002Fslack.html)\n3. Do homeworks (self-checked) and build a project for your portfolio\n\n\n## 📚 Course Syllabus\n\n- [1. Agentic RAG](01-agentic-rag\u002F). Build a RAG pipeline with keyword search, then make it agentic with function calling\n- [2. Vector Search](02-vector-search\u002F). Semantic search with embeddings, minsearch, sqlitesearch, and PGVector\n- [3. Orchestration](03-orchestration\u002F). AI orchestration with Kestra\n- [Workshop - Data Ingestion](cohorts\u002F2025\u002Fworkshops\u002Fdlt.md). Ingest data with dlt from external sources into your RAG system\n- [4. Evaluation](04-evaluation\u002F). Measure retrieval and answer quality with offline and online eval\n- [5. Monitoring](05-monitoring\u002F). Monitor user feedback and system health with live dashboards\n- [6. Best Practices](06-best-practices\u002F). LangChain, hybrid search. Combine vector + keyword search; rerank results for higher precision\n- [7. End-to-End Project](07-project-example\u002F). A complete project example: a fitness assistant built with LLMs\n- [Capstone Project](project.md). Ship a complete end-to-end project of your choice from scratch\n\nRecommended approach:\n\n1. Watch the video for each module\n2. Complete the homework to reinforce the concepts\n3. Build your capstone project applying everything end-to-end\n\n\n\n## 🏆 Capstone Project\n\nThe capstone is your chance to apply everything end-to-end. You'll build a complete, working RAG application built and owned by you.\n\nWhat you'll build:\n\n- A searchable knowledge base. Choose a dataset, ingest, clean, and store it for retrieval\n- A retrieval pipeline. Implement the full RAG flow: retrieve context, assemble prompts, call an LLM, return grounded answers\n- An evaluation process. Measure how well your system retrieves and answers using search metrics or LLM-as-a-Judge\n- A user-facing interface. A simple UI or API (Streamlit, FastAPI, or similar) so others can try your app\n- Monitoring & feedback loops. Track queries, feedback, and performance over time\n\n\n### Past community project ideas\n\n- Fitness & nutrition assistant\n- Study companion for textbooks or course notes\n- Medical FAQ assistant\n- Codebase Q&A bot\n- News summarization and retrieval tool\n\n> [!NOTE]\n> See the full [capstone project guidelines](project.md) and browse [all 2025](https:\u002F\u002Fcourses.datatalks.club\u002Fllm-zoomcamp-2025\u002Fprojects) and [2024](https:\u002F\u002Fcourses.datatalks.club\u002Fllm-zoomcamp-2024\u002Fprojects) cohort submissions for inspiration.\n\n\n\n## 🏅 How to Get a Certificate\n\nTo earn your certificate:\n\n1. Complete the final project. Build a real-world RAG application demonstrating all course concepts\n2. Peer review 3 projects. Evaluate and provide written feedback on three fellow students' submissions\n3. Meet the deadlines. Submit your project and reviews within the cohort schedule\n\n> Certificates are issued after all peer reviews are completed. Self-paced learners are not eligible for certification but can build portfolio projects freely.\n\n\n\n## 👨‍🏫 Meet the Instructors\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\" width=\"50%\">\n      \u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F875246\" width=\"120px;\" alt=\"Alexey Grigorev\" \u002F>\u003Cbr \u002F>\u003Cbr \u002F>\n      \u003Ca href=\"https:\u002F\u002Flinkedin.com\u002Fin\u002Fagrigorev\u002F\">\u003Cb>Alexey Grigorev\u003C\u002Fb>\u003C\u002Fa>\u003Cbr \u002F>\n      \u003Csub>Founder, DataTalks.Club\u003C\u002Fsub>\u003Cbr \u002F>\u003Cbr \u002F>\n      \u003Csub>Founder of DataTalks.Club and creator of multiple open-source ML courses reaching tens of thousands of learners worldwide. Former principal data scientist with deep expertise in ML systems and engineering.\u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" width=\"50%\">\n      \u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002FSVizor42\" width=\"120px;\" alt=\"Timur Kamaliev\" \u002F>\u003Cbr \u002F>\u003Cbr \u002F>\n      \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Ftimurkamaliev\u002F\">\u003Cb>Timur Kamaliev\u003C\u002Fb>\u003C\u002Fa>\u003Cbr \u002F>\n      \u003Csub>Senior Data Scientist\u003C\u002Fsub>\u003Cbr \u002F>\u003Cbr \u002F>\n      \u003Csub>AI Engineer specializing in building production LLM systems, RAG pipelines, and agentic applications. Hands-on practitioner with real-world experience shipping GenAI products.\u003C\u002Fsub>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\n\n## Sponsors\n\nA huge thanks to our sponsors for making this course possible!\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fkestra.io\u002F\">\n    \u003Cimg height=\"80\" src=\"https:\u002F\u002Fgithub.com\u002FDataTalksClub\u002Fdata-engineering-zoomcamp\u002Fraw\u002Fmain\u002Fimages\u002Fkestra.svg\" alt=\"Kestra - Open-Source Orchestration Platform\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdlthub.com\u002F\">\n    \u003Cimg height=\"80\" src=\"https:\u002F\u002Fgithub.com\u002FDataTalksClub\u002Fdata-engineering-zoomcamp\u002Fraw\u002Fmain\u002Fimages\u002Fdlthub.png\" alt=\"dlt Hub - Open-Source Data Ingestion\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n> [!TIP]\n> Interested in supporting the DataTalks.Club community? Reach out to [alexey@datatalks.club](mailto:alexey@datatalks.club).\n\n\n\n## 💬 Testimonials\n\n> \"This course gave me hands-on experience in building LLM-powered applications, including prompt engineering, retrieval-augmented generation (RAG), pipeline orchestration, and vector search optimization.\"\n>\n> — Alexander Daniel Rios, LLM Zoomcamp Graduate\n\n> \"Not gonna lie - this course took longer than planned. By the end, I was running on fumes, forcing myself to push through the final modules. But I made it. What I loved: hands-on experience building real AI systems (not just theory!), deep dives into RAG, vector databases, evaluation, and monitoring, and the wealth of production-ready practices that matter in enterprise environments.\"\n>\n> — Vasiliy Chernykh, LLM Zoomcamp Graduate\n\n[Read more testimonials from past graduates →](https:\u002F\u002Fdatatalks.club\u002Fblog\u002Fllm-zoomcamp.html)\n\n\n\n## 🤝 Community & Support\n\n### Join DataTalks.Club on Slack\n\nJoin the [`#course-llm-zoomcamp`](https:\u002F\u002Fapp.slack.com\u002Fclient\u002FT01ATQK62F8\u002FC06TEGTGM3J) channel on [DataTalks.Club Slack](https:\u002F\u002Fdatatalks.club\u002Fslack.html) for discussions, troubleshooting, and networking with fellow learners and the course team.\n\nTo keep discussions useful for everyone:\n- Follow [our posting guidelines](asking-questions.md) when asking questions\n- Review the [community guidelines](https:\u002F\u002Fdatatalks.club\u002Fslack\u002Fguidelines.html)\n\n### Learning in Public\n\nWe actively encourage sharing your progress online throughout the course. Post what you're building on LinkedIn, Twitter\u002FX, or a blog. It helps you get noticed and connect with others in the field. It also earns you bonus points toward your homework and project scores.\n\n\n\n## ❓ FAQ\n\n> Full FAQ: [datatalks.club\u002Ffaq\u002Fllm-zoomcamp.html](https:\u002F\u002Fdatatalks.club\u002Ffaq\u002Fllm-zoomcamp.html)\n\nQ: Is this course really free?\u003Cbr\u002F>\nA: Yes. All videos, materials, and homework are free. You may spend $1-5 in OpenAI API credits if you run the code yourself.\n\nQ: Do I need a GPU?\u003Cbr\u002F>\nA: No. All exercises are designed to run on a standard laptop using cloud APIs.\n\nQ: What does \"live cohort\" mean? Are there live classes?\u003Cbr\u002F>\nA: No mandatory live classes. \"Live\" means homework deadlines, automatic scoring, a leaderboard, peer review, and certificate eligibility are all enabled. All lectures are pre-recorded.\n\nQ: Can I join after the cohort has started?\u003Cbr\u002F>\nA: Yes. You can join after the start date, but deadlines remain fixed. Some homework forms may already be closed.\n\nQ: Can I join mid-cohort or self-paced?\u003Cbr\u002F>\nA: Yes. All materials stay available after each cohort ends. Self-paced learners are always welcome, though certificates require a live cohort.\n\nQ: Will I get a certificate?\u003Cbr\u002F>\nA: Yes. Complete the final project and peer review 3 students' projects during the live cohort to earn your certificate. Self-paced mode does not include certification.\n\nQ: Do I need to complete every homework to get a certificate?\u003Cbr\u002F>\nA: No. You only need to complete the final project and peer reviews to get it.\n\nQ: What if I get stuck?\u003Cbr\u002F>\nA: Discuss your problem in [`#course-llm-zoomcamp`](https:\u002F\u002Fapp.slack.com\u002Fclient\u002FT01ATQK62F8\u002FC06TEGTGM3J) on Slack. The community and instructors are active there. Also check the [FAQ page](https:\u002F\u002Fdatatalks.club\u002Ffaq\u002Fllm-zoomcamp.html) for detailed answers.\n\nQ: How much time should I expect to spend?\u003Cbr\u002F>\nA: Expect roughly 5-10 hours per week, depending on your background and how deep you go into the materials.\n\n\n\n## 🤝 Contributing\n\nFound a bug in the course materials? Know how to improve an explanation or fix broken code? Contributions are welcome and appreciated.\n\n1. Fork the repository\n2. Make your fix or improvement\n3. Open a pull request with a clear description\n\nEvery contribution helps future learners. Thank you 🙏\n\n\n\n## 🌐 About DataTalks.Club\n\n\u003Cp align=\"center\">\n  \u003Cimg width=\"40%\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F1243a44a-84c8-458d-9439-aaf6f3a32d89\" alt=\"DataTalks.Club - Global Community of Data Enthusiasts\" \u002F>\n\u003C\u002Fp>\n\n[DataTalks.Club](https:\u002F\u002Fdatatalks.club\u002F) is a global online community of data enthusiasts — a place to learn, share knowledge, ask questions, and support each other through free courses, events, and an active Slack community.\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdatatalks.club\u002F\">Website\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fdatatalks.club\u002Fslack.html\">Slack\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fus19.campaign-archive.com\u002Fhome\u002F?u=0d7822ab98152f5afc118c176&id=97178021aa\">Newsletter\u003C\u002Fa> •\n  \u003Ca href=\"http:\u002F\u002Flu.ma\u002Fdtc-events\">Events\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fcalendar.google.com\u002Fcalendar\u002F?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ\">Google Calendar\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002F@DataTalksClub\u002Ffeatured\">YouTube\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDataTalksClub\">GitHub\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fdatatalks-club\u002F\">LinkedIn\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Ftwitter.com\u002FDataTalksClub\">Twitter\u003C\u002Fa>\n\u003C\u002Fp>\n\n> [!NOTE]\n> Most activity happens on [Slack](https:\u002F\u002Fdatatalks.club\u002Fslack.html). Join us there for updates, discussions, and community events. Learn more at [DataTalksClub Community Navigation](https:\u002F\u002Fwww.notion.so\u002FDataTalksClub-Community-Navigation-bf070ad27ba44bf6bbc9222082f0e5a8).\n","LLM Zoomcamp 是一个关于构建大型语言模型（LLM）实际应用的免费在线课程。在为期10周的学习过程中，学员将掌握如何创建能够基于知识库回答问题的人工智能系统。该项目核心功能包括检索增强生成（RAG）、向量搜索、嵌入表示学习等关键技术，并通过实践项目帮助参与者从基础到构建生产级AI助手。适合软件工程师、数据工程师及机器学习从业者用于提升技能，在真实产品中集成或优化LLM相关技术。整个课程采用Jupyter Notebook形式提供代码示例与练习，要求参与者具备Python编程能力及基本的命令行操作经验。",2,"2026-06-11 04:08:43","high_star"]