base on LLM Zoomcamp - a free online course about building a Q&A system # LLM Zoomcamp <p align="center"> <img src="images/llm-zoomcamp.jpg" /> </p> 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. <p align="center"> <a href="https://airtable.com/appPPxkgYLH06Mvbw/shr7WtxHEPXxaui0Q"><img src="https://user-images.githubusercontent.com/875246/185755203-17945fd1-6b64-46f2-8377-1011dcb1a444.png" height="50" /></a> </p> - Give us a star to support the course! - Register in [DataTalks.Club's Slack](https://datatalks.club/slack.html) - Join the [`#course-llm-zoomcamp`](https://app.slack.com/client/T01ATQK62F8/C06TEGTGM3J) channel - Join the [course Telegram channel with announcements](https://t.me/llm_zoomcamp) - The videos are published on [DataTalks.Club's YouTube channel](https://www.youtube.com/c/DataTalksClub) in [the course playlist](https://www.youtube.com/playlist?list=PL3MmuxUbc_hKiIVNf7DeEt_tGjypOYtKV) - [Frequently asked technical questions](https://docs.google.com/document/d/1m2KexowAXTmexfC5rVTCSnaShvdUQ8Ag2IEiwBDHxN0/edit?usp=sharing) - [Course Calendar](https://calendar.google.com/calendar/?cid=NjkxOThkOGFhZmUyZmQwMzZjNDFkNmE2ZDIyNjE5YjdiMmQyZDVjZTYzOGMxMzQyZmNkYjE5Y2VkNDYxOTUxY0Bncm91cC5jYWxlbmRhci5nb29nbGUuY29t) ## 2025 cohort - Start date: TBA (Spring-Summer 2025) ## Self-paced mode * You can watch the course at your own pace * Just follow the modules and watch the videos * Don't forget to do the homework to make sure you learned the materials * We strongly suggest doing a project and then sharing it in slack to ask for feedback ## Pre-requisites * Comfortable with programming and Python * Comfortable with command line * Docker * No previous exposure to AI or ML is required ## Syllabus We encourage [Learning in Public](learning-in-public.md) ### Pre-course workshops Implement a search engine: [Video](https://www.youtube.com/watch?v=nMrGK5QgPVE), [code](https://github.com/alexeygrigorev/build-your-own-search-engine) ### 1. [Introduction to LLMs and RAG](01-intro/) * LLMs and RAG * Preparing the environment * Retrieval and the basics of search * OpenAI API * Simple RAG with Open AI * Text search with Elasticsearch ### 2. [Open-source LLMs](02-open-source/) * Getting an environment with a GPU * Open-source models from HuggingFace Hub * Running LLMs on a CPU with Ollama * Creating a simple UI with Streamlit ### 3. [Vector databases](03-vector-search/) * Vector search * Creating and indexing embeddings * Vector search with Elasticsearch * Offline evaluation of retrieval ### [Workshop: dlt](cohorts/2024/workshops/dlt.md) ### 4. [Evaluation and monitoring](04-monitoring/) * Offline evaluation of RAG * Cosine and LLM-as-a-Judge metrics * Tracking chat history and user feedback * Creating dashboards with Grafana for visualization ### 5. [LLM orchestration and ingestion](05-orchestration/) * Ingesting data with Mage ### 6. [Best practices](06-best-practices/) * Techniques to improve RAG pipeline * Hybrid search * Document reranking * Hybrid search with LangChain ### 7. [Bonus: End-to-End project example](07-project-example/) (Optional) * Building an end-to-end fitness assistant project * Examples of pre-processing text datasets ### LLM Zoomcamp 2024 Competition [More details](cohorts/2024/competition/) ### [Hands-on project](project.md) <p align="center"> <a href="https://airtable.com/appPPxkgYLH06Mvbw/shr7WtxHEPXxaui0Q"><img src="https://user-images.githubusercontent.com/875246/185755203-17945fd1-6b64-46f2-8377-1011dcb1a444.png" height="50" /></a> </p> ## Instructors - [Alexey Grigorev](https://linkedin.com/in/agrigorev/) - [Magdalena Kuhn](https://www.linkedin.com/in/magdalenakuhn/) - [Balaji Dhamodharan](https://www.linkedin.com/in/balaji-dhamodharan-91b45615/) - [Tommy Dang](https://www.linkedin.com/in/dangtommy/) - [Timur Kamaliev](https://www.linkedin.com/in/timurkamaliev/) ## Asking questions The best way to get support is to use [DataTalks.Club's Slack](https://datatalks.club/slack.html). Join the [`#course-llm-zoomcamp`](https://app.slack.com/client/T01ATQK62F8/C06TEGTGM3J). To make discussions in Slack more organized: * Follow [these recommendations](asking-questions.md) when asking for help * Read the [DataTalks.Club community guidelines](https://datatalks.club/slack/guidelines.html) ## Supporters and partners Thanks to the course sponsors for making it possible to run this course <p align="center"> <a href="https://mage.ai/"> <img height="120" src="https://github.com/DataTalksClub/data-engineering-zoomcamp/raw/main/images/mage.svg"> </a> </p> <p align="center"> <a href="https://dlthub.com/"> <img height="80" src="https://github.com/DataTalksClub/data-engineering-zoomcamp/raw/main/images/dlthub.png"> </a> </p> <p align="center"> <a href="https://saturncloud.io/"> <img height="120" src="images/saturn-cloud.png"> </a> </p> Do you want to support our course and our community? Please reach out to [[email protected]]([email protected]) ", Assign "at most 3 tags" to the expected json: {"id":"9974","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"