mo-vellanki / llm-zoomcamp

LLM Zoomcamp - a free online course about building a Q&A system

LLM Zoomcamp

LLM Zoomcamp - a free online course about real-life applications of LLMs. In 10 weeks you will learn how to build an AI bot that can answer questions about your knowledge base.

• Register in DataTalks.Club's Slack
• Join the #course-llm-zoomcamp channel
• Join the course Telegram channel with announcements
• The videos are published on DataTalks.Club's YouTube channel in the course playlist
• Frequently asked technical questions
• Course Calendar
• Materials specific to 2024 cohort

We will cover topics like LLMs and RAG.

Start date: June 17

Give us a star to support the initiative!

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

Pre-course workshops

Introduction

• build a simple Q&A system
• Video: https://www.youtube.com/watch?v=q-p36Ak6YI8
• Code: https://github.com/alexeygrigorev/llm-rag-workshop

Implement a search engine

• Video: https://www.youtube.com/watch?v=nMrGK5QgPVE
• Code: https://github.com/alexeygrigorev/build-your-own-search-engine

Introduction to LLMs and RAG

• LLMs and RAG
• Preparing the environment
• Retrieval and the basics of search
• OpenAI API
• Simple RAG with Open AI
• Text search with Elasticsearch

Open-source LLMs

• 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

Vector databases

• Vector search
• Creating and indexing embeddings
• Vector search with Elasticsearch

Workshop: dlt

LLM orchestration and ingestion pipelines

• Ingesting data with Mage

Monitoring and Guardrails

• Monitoring with ground-truth
• Metrics (RAGAs)
• Dashboarding with Grafana for visualization
• Monitoring chat
• Guardrails

Tips and Tricks for advanced RAG systems

• Best practices

LLM Zoomcamp 2024 Competition

More details

Hands-on project

Instructors

• Alexey Grigorev
• Magdalena Kuhn
• Balaji Dhamodharan

Asking questions

The best way to get support is to use DataTalks.Club's Slack. Join the #course-llm-zoomcamp.

To make discussions in Slack more organized:

• Follow these recommendations when asking for help
• Read the DataTalks.Club community guidelines

Supporters and partners

Thanks to the course sponsors for making it possible to run this course

Do you want to support our course and our community? Please reach out to [email protected]