Pomoc Live Chat OD O,OOZŁ
ODBIERZ TWÓJ BONUS :: »
Książki Ebooki Kursy video Audiobooki Promocje Nowości Bestsellery Darmowe ebooki
Pobierz aplikację Bony Podaruj prezent

TOP tytuł w super cenie » 50% taniej

Data Strategy for LLMs. Build reliable AI applications with RAG, fine-tuning, evaluation, and context engineering Eslam Kamal, Rany ElHousieny, Yash Sheth

Książka w języku angielskim angielski
Data Strategy for LLMs. Build reliable AI applications with RAG, fine-tuning, evaluation, and context engineering Eslam Kamal, Rany ElHousieny, Yash Sheth - okladka książki

Data Strategy for LLMs. Build reliable AI applications with RAG, fine-tuning, evaluation, and context engineering Eslam Kamal, Rany ElHousieny, Yash Sheth - okladka książki

Data Strategy for LLMs. Build reliable AI applications with RAG, fine-tuning, evaluation, and context engineering Eslam Kamal, Rany ElHousieny, Yash Sheth - audiobook MP3

Data Strategy for LLMs. Build reliable AI applications with RAG, fine-tuning, evaluation, and context engineering Eslam Kamal, Rany ElHousieny, Yash Sheth - audiobook CD

Autorzy:
Eslam Kamal, Rany ElHousieny, Yash Sheth
Wydawnictwo:
Packt Publishing (Z chęcią przeczytam książkę w języku polskim)
Ocena:
Bądź pierwszym, który oceni tę książkę
Stron:
452
Dostępne formaty:
     PDF
     ePub

Ebook
143,10 zł 159,00 zł (-10%)
143,10 zł najniższa cena z 30 dni

Dodaj do koszyka Dostępny natychmiast po opłaceniu zakupu lub Kup na prezent Kup 1-kliknięciem

Przenieś na półkę

Do przechowalni

Most teams building applications with large language models (LLMs) start by choosing a model. Yet the same models are available to everyone, and the one that leads today may be replaced within months. What makes an LLM application reliable is the data around the model: the sources it draws on, the context it receives, the examples it learns from, and the tests that show whether it works.
This book walks you through that data lifecycle, from selecting and preparing sources to building a retrieval-augmented generation (RAG) system and fixing the data problems it meets in production. You will apply synthetic data generation to fill coverage gaps, learn what LLM fine-tuning and post-training require, and combine prompts, retrieval, tools, and post-training into one customization process. Examples from four assistant scenarios (personal productivity, domain-specific, enterprise knowledge, and content moderation) show how the same data decision plays out differently in each.
You will also create task-specific LLM evaluation data, catch quality problems with automated checks and human oversight, and manage the context that AI agents rely on at runtime. By the end of this book, you will know how to select, prepare, test, and maintain the data that makes LLM applications useful and reliable, with hands-on Python examples you can run and adapt.

O autorach książki

Eslam Kamal is an applied AI leader with 20 years of professional experience, including roles at Microsoft and Meta. His work spans natural language understanding, responsible AI, multimodal AI, and conversational AI systems. At Microsoft Research, he worked on language understanding. He later led applied science work across Microsoft Copilot, GitHub Copilot, and Azure Responsible AI. At Meta, he focused on conversational quality for Meta AI on Ray-Ban Meta glasses. He subsequently returned to Microsoft to lead applied AI for Dynamics 365Contact Center. His experience has shaped a practical focus on how training and evaluation data influence model behavior and the reliability of deployed AI systems.
Rany ElHousieny is an AI solutions architect and senior AI engineering manager with over two decades of experience in AI, NLP, and ML. He spent 20 years at Microsoft, including time at Microsoft Research. Currently, he manages generative AI engineering teams at Clearwater Analytics, building retrieval, context engineering, and multi-agent systems for investment management. He co-authored an AWS Machine Learning Blog post on Clearwater's generative AI work. On Medium and LinkedIn, he writes regularly about AI systems architecture, RAG, multi-agent orchestration, context engines, and knowledge graphs. He also created the Agentic Repos framework that Chapter 11 builds on and was the technical reviewer of LLM Engineer's Handbook (Packt).

Packt Publishing - inne książki

Zamknij

Przenieś na półkę
Dodano produkt na półkę
Usunięto produkt z półki
Przeniesiono produkt do archiwum
Przeniesiono produkt do biblioteki
Proszę czekać...
ajax-loader

Zamknij

Wybierz metodę płatności

Ebook
143,10 zł
Dodaj do koszyka
Zamknij Pobierz aplikację mobilną Ebookpoint