LlamaIndex
LlamaIndex is an open-source software framework for connecting large language models with external data through ingestion, indexing, retrieval, and querying.
Generative AI in Action
LlamaIndex is a data framework that connects large language models with private data sources through ingestion, indexing, retrieval, and query interfaces.
- How it is used
- Supports retrieval-augmented generation workflows that use documents with large language models.
- How deep it goes
- Illustrates PDF-loading and embedding setup in a RAG listing; the supplied excerpt does not show the complete query workflow.
- Examples
- Uses a directory of dog-book PDFs, an OpenAI embedding model, and a local storage path.
- What you can do after
- Apply it via LlamaIndex to configure PDF loading and embeddings for a RAG workflow.
The Complete Obsolete Guide to Generative AI
LlamaIndex is a software framework for building large-language-model applications that connect models with external or private data.
- How it is used
- Connects local files and prepared datasets to GPT for style-oriented prompting, question answering, and exploratory analysis.
- How deep it goes
- Walks through Python setup, file loading, index construction, and querying, without explaining internal indexing mechanics.
- Examples
- Demonstrates population CSV questions and household-data rankings for net wealth and likely product investors.
- What you can do after
- Apply it via Python and the OpenAI API to index local data and ask natural-language questions about it.
Read how The Complete Obsolete Guide to Generative AI explains LlamaIndex →
Data Analysis with LLMs
LlamaIndex is an open-source software framework for building applications that connect language models to external data and retrieval systems.
- How it is used
- Connects language-model questions to relevant parts of large, varied datasets through indexing and retrieval.
- How deep it goes
- Walks through loading, chunking, embedding, retrieval, and a short Python implementation without detailing model internals.
- Examples
- Uses a command-line Python program to answer questions over business-unit files, including text documents and PowerPoint presentations.
- What you can do after
- Apply it via LlamaIndex to load a file directory, build an index, and query its contents.
The Art of AI Product Development
An open-source software framework for connecting language-model applications with external data and computational capabilities.
- How it is used
- Supports agent workflows that search and retrieve relevant documents from large amounts of data.
- How deep it goes
- Defines the framework’s retrieval role and trade-offs but does not explain implementation internals.
- Examples
- Uses querying different language models and retrieving relevant documents from large data collections.
- What you can do after
- Build search and retrieval applications that query language models and return relevant documents.
Read how The Art of AI Product Development explains LlamaIndex →
Also covered in
- Hugging Face in Action
- Transformers in Action
- Effective Conversational AI
- Context EngineeringIn early access (MEAP)
- Retrieval Augmented Generation, The Foundational IdeasIn early access (MEAP)
What to know first
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- retrieval-augmented generationRetrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- embeddingAn embedding is a numerical vector representation of an item in a feature space, encoding selected properties or relationships for computational tasks such as comparison or retrieval.
- PDFPDF, or Portable Document Format, is a standardized page-description document format designed to preserve the layout and appearance of documents across systems.
Related concepts
- iterative retrievalimplements · Iterative retrieval is a strategy that performs multiple retrieval steps, using intermediate results to refine queries or guide subsequent searches.
- LangChainalternative to · LangChain is an open-source software framework for building applications that compose language models with prompts, data sources, tools, and other components.
- retrieval-augmented generationuses · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- datasetuses · A dataset is an organized collection of related data items, records, observations, or examples treated as a unit for storage, processing, or analysis.
- GPTSimpleVectorIndexhas part · GPTSimpleVectorIndex is a LlamaIndex module that maintains an index for retrieving data relevant to language-model queries.
- similarity searchuses · Similarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
Questions about LlamaIndex
What is LlamaIndex?
LlamaIndex is an open-source software framework for connecting large language models with external data through ingestion, indexing, retrieval, and querying.
Which Manning books explain LlamaIndex?
Generative AI in Action, The Complete Obsolete Guide to Generative AI, Data Analysis with LLMs and The Art of AI Product Development.
What should I know before learning LlamaIndex?
Manning books that teach LlamaIndex usually introduce language model, retrieval-augmented generation, embedding and PDF first.
What is the difference between LlamaIndex and LangChain?
LlamaIndex is an open-source software framework for connecting large language models with external data through ingestion, indexing, retrieval, and querying. LangChain is an open-source software framework for building applications that compose language models with prompts, data sources, tools, and other components.
What are the parts of LlamaIndex?
LlamaIndex includes GPTSimpleVectorIndex.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.



