Book: 'Data Analysis with LLMs. Text, Tables, Images and Audio'
OpenAI
Anthropic
Cohere
Hugging Face
This article announces a new book by Cornell University professor Immanuel Trummer, which teaches how to apply large language models (LLMs) to data analysis tasks. The book covers text, tables, images, audio, and graphs, using Python and libraries like OpenAI, LangChain, and LlamaIndex.
Immanuel Trummer, an associate professor at Cornell University, has authored a book on using large language models (LLMs) for data analysis. The book demonstrates how to integrate generative AI into the daily work of a data scientist, covering projects that use the OpenAI Python library, tools such as LangChain and LlamaIndex, and models from Anthropic, Cohere, and Hugging Face. Readers will learn to use AI for obtaining structured and unstructured data, analyzing sound and images, and optimizing costs and quality in data analysis. The book includes chapters on classification, clustering, transformation, and analysis of multimodal data; creating natural language query interfaces; building LLM-based agents for autonomous analysis; and prompt engineering and model tuning. It is aimed at software developers, data professionals, and enthusiasts with basic Python knowledge but no prior experience with language models. The article includes endorsements from industry figures and mentions a 25% discount for Habr readers with the promo code LLM.
- Abbreviations
- LLM = Large Language Model — большая языковая модель
Source: Хабр — Data Mining —
original