LangChain

As explained in Data Storytelling with Altair and AI

LangChain is a software framework for building applications that connect language models with prompts, external data sources, and other components.

LangChain is a framework for connecting language models with external sources and assembling context-aware applications. Its central idea is a chain: components from different modules working together. section 7.4.2

A chain can combine:

• LLM wrappers for providers such as OpenAI and Hugging Face. section 7.4.2
• Prompt templates for chatbot and question-answering tasks. section 7.4.2
• Indexes that supply additional context from external data. section 7.4.2

Product-description RAG application

Load an HTML product page, split it into overlapping chunks, generate embeddings, persist the chunks in Chroma, and connect the store to a RetrievalQA chain. A prompt restricts answers to retrieved context, while ChatOpenAI generates the response and returns source documents.

Figure 7.13 A RAG-based system

Architecture diagram for the retrieval-augmented generation system. section 7.4.2

How Data Storytelling with Altair and AI covers it

How deep it goes

Explains chains and components, then demonstrates loading, chunking, embedding, retrieval, prompting, and querying.

Examples

Uses a smartphone HTML page, Chroma collection, OpenAI embeddings, a constrained prompt, and a RetrievalQA query.

What it assumes

Assumes an HTML data source and access to an LLM, embeddings, and vector database components.

What you can do after

Build a retrieval-augmented application that answers product questions from indexed HTML context.

How it connects

Connects LLMs with prompt templates, indexes, embeddings, vector databases, retrieval, and retrieval-augmented generation.

liveBookmanning.com

Read Data Storytelling with Altair and AI on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Build AI-Enhanced Web AppsLangChain is a software framework, including its JavaScript implementation, for composing applications that use language models, tools, retrieval, and multi-step chains.
• 

  liveBookmanning.com
  AI Agents and ApplicationsLangChain is an open-source framework for building applications that combine language models with data sources, tools, and multi-step workflows.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionLangChain is a software framework for developing applications that combine language models with tools, data sources, and orchestration logic.
• 

  liveBookmanning.com
  Data Analysis with LLMsLangChain is an open-source software framework for developing applications that integrate language models with prompts, data, and external actions.
• 

  liveBookmanning.com
  MongoDB 8.0 in Action, Third EditionLangChain is a software framework for building applications that compose large language models with prompts, tools, memory, and retrieval components.
• 

  liveBookmanning.com
  Generative AI in ActionLangChain is a software framework that provides modular components for building applications around large language models and related natural-language services.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA Python library for building applications with large language models through tools, abstractions, and component chaining.
• 

  liveBookmanning.com
  The Art of AI Product DevelopmentLangChain is a software framework for developing applications that compose language models with prompts, retrieved context, memory, tools, and other components.
• 

  liveBookmanning.com
  LLMs in ProductionLangChain is a software framework for building applications that combine language models with prompts, tools, data sources, and workflow logic.
• 

  liveBookmanning.com
  Starting Data Analytics with Generative AI and PythonLangChain is a software framework for developing applications that compose language models with prompts, tools, data sources, and conversation state.
• 

  liveBookmanning.com
  Software Testing with Generative AILangChain is a software library and toolset for developing applications that integrate with language models.
• 

  liveBookmanning.com
  Machine Learning Platform EngineeringLangChain is a software framework for building applications that compose language models with prompts, tools, retrieval, and other processing components.
• 

  liveBookmanning.com
  Effective Conversational AILangChain is a software library for developing applications that compose language models with prompts, data sources, retrieval, and other processing components.
• 

  liveBookmanning.com
  The Complete Obsolete Guide to Generative AILangChain is a software framework for building applications that coordinate large language models with tools, data sources, and multistep operations.
• 

  liveBookmanning.com
  Build Applications with Local AI Models on a MacLangChain is a software framework for building applications with language models by connecting them to data sources and composable components.
• 

  liveBookmanning.com
  Just Use Postgres!LangChain is a software framework for building applications that compose language models with prompts, tools, data sources, and processing steps.
• 

  liveBookmanning.com
  Investing for ProgrammersLangChain is a software framework for building applications that compose large language models with prompts, tools, data sources, and workflow logic.
• 

  liveBookmanning.com
  Building Reliable AI SystemsLangChain is an open-source software framework for building applications that coordinate language models with prompts, data sources, tools, and retrieval workflows.

Compare how 19 books explain LangChain →

Related concepts

• language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
• 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.
• contractuses · An API contract is a specification of the operations, data, and behavioral expectations that govern interactions between software components.
• prompt templateuses · A prompt template is a reusable structure for organizing instructions, context, and variable inputs supplied to a language model.
• LangGraphused by · LangGraph is a framework for building stateful, graph-structured workflows and applications, including those involving language models and agents.

This explainer was generated by Manning's knowledge graph from the text of Data Storytelling with Altair and AI. The section links point to the parts of the book it draws on.