LLM Zoomcamp 2025 has officially started!. Here’s what you need to do during Module 1 👇. 1/3

Register for today’s event: 3/3.

What to do now:. 🔸 Join the hackathon channel on our Slack.🔸 Submit your idea before the session for live feedback.🔸 Register for the launch. Submit your idea: 2/3.

The Summer 2025 AI Hackathon starts today with a live launch session!. In the session, I’ll cover:. 🔸 What the hackathon is about.🔸 How to submit ideas.🔸 Project examples.🔸 How to form a team.🔸 Live Q&A. 1/3

🚀 @FireboltHQ just announced Firebolt core – the same distributed query engine behind Firebolt, but now available as a free self-hosted version. All you need to do is run a single docker command. And it’s amazingly fast!. Check it out!.

Register now and get ready to dive in with Hiba's real-world insights: 3/3.

What Hiba Will Cover:. 🔸 Transform REST API docs into semantic nodes via dlt.🔸 Develop a central ontology for linking resources and behaviors.🔸 Use Cognee to embed and index nodes in a semantic space.🔸 Visualize and query graphs for complex insights. 2/3.

Hiba brings hands-on experience in data pipelines, modeling, LLMs, and ML. She'll walk you step-by-step through turning flat API docs into a rich, queryable graph. 1/3.

We've just updated the details for our upcoming hands-on workshop!. Workshop: Building a Knowledge Graph from REST API Documentation with dlt & Cognee. Speaker: Hiba Jamal, AI Engineer at dltHub. Date: Monday, June 30. Time: 4:30 PM CET. 🧵

Register here: Bring your questions! I’ll cover as many as I can during the session. 3/3.

We’ll start simple and go deep:. 🔸 Build a basic RAG (search + prompt + LLM).🔸 Add agentic behavior: decide when to search vs. answer.🔸 Handle multi-step, reasoning-driven flows.🔸 Use OpenAI function calling.🔸 Organize tools with PydanticAI. 2/3.

Go from basic RAG pipelines to agentic AI flows. I’m hosting a free workshop on that topic!. Date: Tue, 1 July.Time: 4:30 PM CET. You’ll build a working assistant that:. 🔸 Searches FAQs.🔸 Decides when to act.🔸 Asks follow-up questions.🔸 Updates its own knowledge base. 1/3

By the end, you’ll have a fully working ingestion pipeline for RAG, built entirely with open-source tools. LLM Zoomcamp students: submit the homework and earn bonus points on the leaderboard!. Everyone else is welcome to join too. Register here: 3/3.

Learn how to:. 🔸 Extract data from REST APIs with dlt.🔸 Vectorize and load into a database.🔸 Index semantically using Cognee.🔸 Manage evolving record relationships.🔸 Build a portable, open-source pipeline run anywhere (notebooks, Airflow, Dagster, Mage. ). 2/3.

Join us and dlthub for a special LLM Zoomcamp workshop!. Learn to build a smart, always-up-to-date data pipeline for your RAG projects. Save the date: Monday, June 30, at 4:30 PM CET. 1/3

Watch the course on YouTube and get your certification!. 👉 Register here to get certified: 2/2.

🔸 Build ETL pipelines from scratch.🔸 Manage schemas, ingest, and transform data.🔸 Automate 90% of tasks with dlt.🔸 Implement advanced loading (incremental, SCD2, performance tuning).🔸 Deploy using Crontab, GitHub Actions, Airflow.🔸 Use LLMs for code and docs creation. 1/2.

New free short course on data engineering with Python and AI/LLMs!. Together with Adrian Brudaru (CEO of @dltHub), we created a new free course, and it’s now live on @freeCodeCamp!. Here's what it covers:

Proud of this collaboration with Qdrant, one of the best open-source vector databases, and excited to help you bring vector search into your real-world RAG applications. 👉 Check out the module:

This module covers:. 🔸 Getting started with vector databases using Qdrant.🔸 Embedding text data.🔸 Indexing and searching.🔸 RAG with vector search.🔸 Hybrid search techniques. 🔥 We’ve also added brand-new hands-on notebooks!.

Excited to share something new from the LLM Zoomcamp!. Together with Evgeniya, Kacper, and our friends at @qdrant_engine, we’ve updated and expanded the Vector Search module, and it’s now live!. Here’s what you’ll explore: