Последние посты
LLM Zoomcamp
10 сент., 08:27
If you submitted your project for attempt 3, now it's time to evaluate your peershttps://courses.datatalks.club/cadmin/llm-zoomcamp-2026/project/project3/submissionsHave fun learning!LLM Zoomcamp
19 авг., 06:34
It's time to evaluate your peers and learn from them!If you submitted a project for attempt 2, you'll find your assignments herehttps://courses.datatalks.club/llm-zoomcamp-2026/project/project2Have fun!LLM Zoomcamp
18 авг., 14:31
We're talking about making agents more durablehttps://www.youtube.com/watch?v=KdmX-ZPuKbsJoin now or watch later in recoridngYouTubeRunning Durable Agents in Production - Nicholas LotzIn this talk, Nicholas Lotz, Developer Relations Engineer at Orkes, shares his hands-on expertise in building resilient, enterprise-ready AI agents from managing local Python processes to deploying fault-tolerant distributed architectures. We explore how…LLM Zoomcamp
18 авг., 06:13изменён
Amar Agrawal, one of the graduates of my AI Engineering Buildcamp course, made a tool for helping course participants choose a projectIf you're starting working on your project attempt 3 now and need help with the idea, check it out:https://project-ideation-tool.streamlit.appIf you have any feedback for Amar, please share it hereStreamlitProject IdeatorA conversational AI tool that helps builders find a concrete portfolio project idea through a des...LLM Zoomcamp
17 авг., 08:46
Today is the last day to submit your final project under Attempt 2.If you've already handed in your project, it's time to review your peers' projects.If you're still working on the project, you still have Attempt 3, which is due on 8 September (Tue) at 1 AM CET.Here are the resources you can use:• Check out Module 7 to see an example of a complete project as a reference. • For more information about the project guidelines and peer review, read the Project section.Finalize your project or review your peers here: https://courses.datatalks.club/llm-zoomcamp-2026/P.S. You only need to submit your project once. You can find peers to review under the Attempt that you used to submit your project.LLM Zoomcamp
14 авг., 21:13
I just wrote an article about doing evaluationsIt complements what we studied in the course so I'm sure you'll find it usefulhttps://alexeyondata.substack.com/p/how-to-do-evals-in-2026Enjoy!SubstackHow to Do Evals in 2026A tool-agnostic framework for evaluating AI agentsLLM Zoomcamp
12 авг., 21:32
Your certificates are not ready yet. There will be a separate announcement about it after the second attempt is over. Please be patient =)LLM Zoomcamp
12 авг., 19:32
The results for attempt 1 are readyGood job everyone!LLM Zoomcamp
4 авг., 20:21
Great job working on your projects!Now it's time to learn from your peers. If you submitted your project for attempt 1, you will find your peer review assignments here:https://courses.datatalks.club/llm-zoomcamp-2026/project/project1/evalHave fun!LLM Zoomcamp
3 авг., 11:46
Stream about the FAQ assistantJoin now or watch later in recording:https://www.youtube.com/watch?v=CyH61xiYSnkYouTubeFAQ Assistant in Practice: End-To-End Flow - Alexey GrigorevIn this talk, Alexey Grigorev, Founder of DataTalks.Club, breaks down the production architecture behind the community's automated FAQ assistant, moving from messy, user-edited Google Docs to a streamlined, serverless RAG pipeline. We explore practical strategies…LLM Zoomcamp
3 авг., 08:20
Today is the deadline for Attempt 1 of the final project.Submit your project by 1:00 AM CET today.As you continue working, check Module 7 for a complete project example that you can use as a reference. It covers:• Generating data, setting up the project, and building the initial RAG flow • Evaluating retrieval with ground truth data, Hit Rate, MRR, and boosting • Evaluating RAG with LLM-as-a-Judge and model comparisons • Building a Flask API, ingestion pipeline, and project structure • Adding Docker Compose, PostgreSQL logging, and Grafana monitoring • Reviewing the final result, costs, and practical project tips • Applying different chunking strategies to articles, transcripts, and slidesFor submission guidelines and peer-review requirements, read the Project section.If you cannot submit today, you will have Attempt 2, with a deadline of Tuesday, August 11, at 1:00 AM CET.GitHubllm-zoomcamp/07-project-example at main · DataTalksClub/llm-zoomcampLLM 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. Register here 👇🏼 - D...LLM Zoomcamp
1 авг., 23:15
In the course we use the FAQ dataset as the main running exampleIn this article I describe how it's curated and how the FAQ assistant you see in Slack workshttps://alexeyondata.substack.com/p/rebuilding-a-faq-system-for-datatalksclubAlso, if you'd rather watch me explain it than read the article, we'll have a live stream about it on YouTubehttps://luma.com/fb91wje9See you soon!I hope you're having fun with your projects!Aishippingblog(Re)Building a FAQ System for DataTalks.ClubServing 100k+ Learners with a Serverless FAQ AssistantLLM Zoomcamp
21 июл., 14:36
We're talking about using tracking to get insights user tracing using Snowplow and Vercel AIhttps://www.youtube.com/watch?v=A2nMgZWyza8Watch now or later in recordingYouTubeTracking and Personalizing AI Agents with Snowplow - Jordan Peck, James BorlaseIn this workshop, James Borlase and Jordan Peck, Solutions Engineers at Snowplow, share their expertise in behavioral event tracking and context engineering from capturing multi-layered application traces to feeding real-time user context from Snowplow Signals…LLM Zoomcamp
20 июл., 12:52
We are hosting a live workshop on tracking and personalizing AI agents.📅 Tuesday, July 21 🕟 16:30 CESTAgent applications usually use the current conversation as context. But users also interact with the rest of the product. They open pages, change filters, compare options, and complete different steps before asking the agent a question.In this workshop, we will show how to capture that behavioral data and pass it back into an AI agent.We will use a travel chatbot as an example and instrument it across 3 layers:• Client-side user activity • Server-side application events • Agent actions and decisionsYou will learn how to:• Set up a pipeline • Validate events against schemas • Track activity across the applicationLumaTrack and personalize AI agents with Snowplow and the Vercel AI SDK · LumaAI agents usually rely on the conversation as their main source of context. But users also interact with the rest of the product. They open pages, change…LLM Zoomcamp
20 июл., 08:46
It's time to start working on your final project.Check out Module 7 to see an example of a complete project as a reference.It covers:• Intro: Generating data, setting up the project, initial RAG flow • Evaluating Retrieval: Ground truth data, Hit Rate, MRR, boosting • Evaluating RAG: LLM-as-a-Judge, comparing models • Interface and Ingestion: Flask API, ingestion pipeline, project structure • Monitoring and Containerization: Docker Compose, PostgreSQL logging, Grafana • Summary: Final result, cost analysis, tips for your project • Chunking for Longer Texts: Different chunking strategies for articles, transcripts, slidesFor more information about the project guidelines and peer review, read the Project section.You also asked us to postpone the deadline for dlt workshop homework. You'll have one more week to complete it.LLM Zoomcamp
13 июл., 18:38
We have prepared the homework for the dlt workshop as well as the monitoring moduleAnd they are both about monitoring and observability, and in both you will learn something new in addition to what we covered in the course:- for the monitoring homework we'll learn about OTel and instrument the RAG assistant with OTel collectors - for the dlt hub homework, we'll use Pydantic Logfire and see how we can use dlt to ingest the traces back from Logfire for our local analysisHave fun!LLM Zoomcamp
13 июл., 06:30
This week in LLM Zoomcamp: Module 5, Monitoring.We build:- A Streamlit chat app with RAG - Metric capture for LLM calls and cost - PostgreSQL storage for conversations - User feedback with thumbs up and thumbs down - Automatic relevance evaluation with a built-in judge - Streamlit and Grafana dashboards - A Docker Compose setup for running everything togetherYou’ll see what your LLM application is doing after it is deployed.You need conversations, feedback, cost, relevance, and dashboards. Otherwise it is hard to know what to improve next.Materials: https://github.com/DataTalksClub/llm-zoomcamp/tree/main/05-monitoringGitHubllm-zoomcamp/05-monitoring at main · DataTalksClub/llm-zoomcampLLM 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. Register here 👇🏼 - D...LLM Zoomcamp
9 июл., 07:04
On Tuesday, July 21, we have a workshop on tracking and personalizing AI agents with Snowplow and the Vercel AI SDK.Your agent can see the chat history but not what the user is doing in the product. If you want the agent to respond based on the user's current session, capture that context and make it available to the model.This workshop shows how to do that with a Next.js travel chatbot.The approach:1. Track client behavior (page views, clicks, filters) 2. Track server-side events (purchases, bookings) 3. Track agent decisions (tool calls, outcomes) 4. Validate events against schemas in real time 5. Compute session attributes with Snowplow Signals 6. Inject those attributes into the system promptYou'll set up the pipeline, add tracking at each layer, and use live session data to shape the agent's responses.Tuesday, July 21 4:30 PM - 6:00 PM GMT+2 YouTubeLumaTrack and personalize AI agents with Snowplow and the Vercel AI SDK · LumaAI agents usually rely on the conversation as their main source of context. But users also interact with the rest of the product. They open pages, change…LLM Zoomcamp
7 июл., 15:57
We're starting in a few miniteshttps://www.youtube.com/watch?v=rG2YW3YCq64Join now or watch later in recordingYouTubeLLM Zoomcamp 2026 Office Hours (Kestra)Connect with DataTalks.Club: - Join the community - https://datatalks.club/slack.html - Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2Fs…1,940Открыть в TelegramLLM Zoomcamp
7 июл., 05:24
We will have office hours today with Will from Kestra at 18:00 CETWe will share the link here 5-10 minutes before the startIf you want to get a reminder, you can use this link https://luma.com/d19r4ko1You can ask questions in advance using this linkhttps://app.sli.do/event/pH1w9PSq8dJZahTia24SKeLumaLLM Zoomcamp Office Hours (Kestra) · LumaYou can ask Will any question about LLM orchestration
