What do you think?
Rate this book
RAG-Driven Generative AI: Build custom retrieval augmented generation pipelines with LlamaIndex, Deep Lake, and Pinecone
- GenresArtificial Intelligence
338 pages, Paperback
Published September 30, 2024
10 people are currently reading
38 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 of 1 review
November 23, 2024
The book provides a comprehensive guide to building advanced multimodal AI systems with Retrieved Augmented Generation (RAG).
It offers practical insights into designing, building, managing and optimising pipelines that include large language models (LLMs), vector databases, knowledge graphs.
Few of the key topics include techniques for improving output accuracy of the combined similarity search and prompting LLMs, optimising retrieval from vector databases, improving all the steps of ingesting documents in vector storages: format conversion, chunking, indexing, ranking.
Thought the chapters dedicated to various implementation of the RAG systems, from naive to advanced and optimised, it covers as well hands-on implementations examples using various technologies: LlamaIndex, Deep Lake, Pinecone, ChromaDB. Models from HuggingFace and OpenAI are used for these applications.
The book is useful for data scientists, AI engineers, machine learning professionals, and MLOps practitioners, as well as software developers, product managers, and project leads aiming to create robust, context-aware AI systems for diverse applications.
It offers practical insights into designing, building, managing and optimising pipelines that include large language models (LLMs), vector databases, knowledge graphs.
Few of the key topics include techniques for improving output accuracy of the combined similarity search and prompting LLMs, optimising retrieval from vector databases, improving all the steps of ingesting documents in vector storages: format conversion, chunking, indexing, ranking.
Thought the chapters dedicated to various implementation of the RAG systems, from naive to advanced and optimised, it covers as well hands-on implementations examples using various technologies: LlamaIndex, Deep Lake, Pinecone, ChromaDB. Models from HuggingFace and OpenAI are used for these applications.
The book is useful for data scientists, AI engineers, machine learning professionals, and MLOps practitioners, as well as software developers, product managers, and project leads aiming to create robust, context-aware AI systems for diverse applications.
Displaying 1 of 1 review