
Deep Dive120min
ChatGPT & LLMs: A Practical Starter's Guide to Language Chains
This course offers a comprehensive guide to developing ChatGPT-powered applications using Python. Ideal for programmers, it covers various generative AI aspects, LangChain API, external API integrations, vector databases, document-to-vector strategies, and creating reasoning agents. It also addresses accuracy enhancement, potential tuning, and common challenges in AI production.

Marcin SzymaniukTantusData

Bartlomiej SadlejTantusData
talkDetail.whenAndWhere
Friday, June 21, 10:15-12:15
BSD
Would you like to do something more than just create prompts for ChatGPT? How about building an application? An application that utilizes the power of generative AI. From scratch! All you need is Python knowledge, your laptop, and an open mind.Sounds great? Or maybe you are afraid there is too much hype about ChatGPT? If so - that's good - we will cover the tricky bits and pitfalls as well!Who is this course for?Ideal for those with programming experience (preferably in Python) who are eager to explore ChatGPT-driven LLM applications.Agenda:IntroductionExploring various LLMs to find the right fit.Intro to Langchain.Using Chains and Agents (Hands-on)LangChain API and context management.External API integrations.Chains vs. Agents.Question Answering over Documents (Hands-on)Basics of embeddings.Vector databases overview.Document-to-vector strategies and challenges.Building a simple app with ChatGPT, VectorDb, and Langchain.Creating Reasoning Agents (Hands-on)Dynamic decision-making.Integration with tools like Google Search and Wolfram Alpha.SummaryEnhancing accuracy and safety: self-querying, hallucination checking.LLM in production: key challenges.Potential tuning: embeddings, inference, accuracy cost.This workshop is a deep dive into the development of ChatGPT-powered applications, providing practical, hands-on experience with the latest tools and techniques.

Marcin Szymaniuk
Specialising in monetising big data for clients since the 07's, Marcin is leading a team of seasoned data engineers specialised in everything Data Engineering, ML, ML-ops, and Cloud. Marcin is an expert in non-standard issues and those more run-down-the-mill that must be solved quickly and conveniently. His experience spans industries and various project sizes. However, his speciality remains in AI, ML and deployment.

Bartlomiej Sadlej
The driven Data Engineer at TantusData, where he specialises in deep learning technologies. A Computer Science graduate who commands an extensive repertoire of programming languages, ranging from C++, Python, and Rust to Java, SQL, and the dynamic duo of JavaScript with React and Redux. Bartek's programming prowess extends to intricate areas such as algorithms, networking, databases, and concurrent and async programming. His strong mathematical foundation amplifies his interests in Machine Learning and Deep Learning. Beyond coding, Bartek's proficiency makes him a natural when it comes to the complexities of computer science, making him an invaluable co-facilitator for deep dives and other workshops.
talkDetail.shareFeedback
talkDetail.feedbackExpired
talkDetail.feedbackPeriodExpired
occupancy.title
occupancy.votingClosed
occupancy.votingWindowExpired
comments.speakerNotEnabledComments