Component architecture

LangChain’s power comes from how its components work together to create sophisticated AI applications. This page provides diagrams showcasing the relationships between different components.

Core component ecosystem

The diagram below shows how LangChain’s major components connect to form complete AI applications:

    graph TD
    %% Input processing
    subgraph "📥 Input processing"
        A[Text input] --> B[Document loaders]
        B --> C[Text splitters]
        C --> D[Documents]
    end

    %% Embedding & storage
    subgraph "🔢 Embedding & storage"
        D --> E[Embedding models]
        E --> F[Vectors]
        F --> G[(Vector stores)]
    end

    %% Retrieval
    subgraph "🔍 Retrieval"
        H[User Query] --> I[Embedding models]
        I --> J[Query vector]
        J --> K[Retrievers]
        K --> G
        G --> L[Relevant context]
    end

    %% Generation
    subgraph "🤖 Generation"
        M[Chat models] --> N[Tools]
        N --> O[Tool results]
        O --> M
        L --> M
        M --> P[AI response]
    end

    %% Orchestration
    subgraph "🎯 Orchestration"
        Q[Agents] --> M
        Q --> N
        Q --> K
        Q --> R[Memory]
    end

    classDef trigger fill:#F6FFDB,stroke:#6E8900,stroke-width:2px,color:#2E3900
    classDef process fill:#E5F4FF,stroke:#006DDD,stroke-width:2px,color:#030710
    classDef output fill:#EBD0F0,stroke:#885270,stroke-width:2px,color:#441E33
    classDef neutral fill:#F2FAFF,stroke:#40668D,stroke-width:2px,color:#2F4B68

    class A,H trigger
    class B,C,E,I,K,M,N,Q process
    class D,F,J,L,O,P,R neutral
    class G output

How components connect

Each component layer builds on the previous ones:

Input processing – Transform raw data into structured documents
Embedding & storage – Convert text into searchable vector representations
Retrieval – Find relevant information based on user queries
Generation – Use AI models to create responses, optionally with tools
Orchestration – Coordinate everything through agents and memory systems

Component categories

LangChain organizes components into these main categories:

Category	Purpose	Key Components	Use Cases
Models	AI reasoning and generation	Chat models, LLMs, Embedding models	Text generation, reasoning, semantic understanding
Tools	External capabilities	APIs, databases, etc.	Web search, data access, computations
Agents	Orchestration and reasoning	ReAct agents, tool calling agents	Nondeterministic workflows, decision making
Memory	Context preservation	Message history, custom state	Conversations, stateful interactions
Retrievers	Information access	Vector retrievers, web retrievers	RAG, knowledge base search
Document processing	Data ingestion	Loaders, splitters, transformers	PDF processing, web scraping
Vector Stores	Semantic search	Chroma, Pinecone, FAISS	Similarity search, embeddings storage

Common patterns

RAG (Retrieval-Augmented generation)

    graph LR
    A[User question] --> B[Retriever]
    B --> C[Relevant docs]
    C --> D[Chat model]
    A --> D
    D --> E[Informed response]

    classDef trigger fill:#F6FFDB,stroke:#6E8900,stroke-width:2px,color:#2E3900
    classDef process fill:#E5F4FF,stroke:#006DDD,stroke-width:2px,color:#030710
    classDef neutral fill:#F2FAFF,stroke:#40668D,stroke-width:2px,color:#2F4B68

    class A trigger
    class B,D process
    class C,E neutral

Agent with tools

    graph LR
    A[User request] --> B[Agent]
    B --> C{Need tool?}
    C -->|Yes| D[Call tool]
    D --> E[Tool result]
    E --> B
    C -->|No| F[Final answer]

    classDef trigger fill:#F6FFDB,stroke:#6E8900,stroke-width:2px,color:#2E3900
    classDef process fill:#E5F4FF,stroke:#006DDD,stroke-width:2px,color:#030710
    classDef decision fill:#FDF3FF,stroke:#7E65AE,stroke-width:2px,color:#504B5F
    classDef neutral fill:#F2FAFF,stroke:#40668D,stroke-width:2px,color:#2F4B68

    class A trigger
    class B,D process
    class C decision
    class E,F neutral

Multi-agent system

    graph LR
    A[Complex Task] --> B[Supervisor agent]
    B --> C[Specialist agent 1]
    B --> D[Specialist agent 2]
    C --> E[Results]
    D --> E
    E --> B
    B --> F[Coordinated response]

    classDef trigger fill:#F6FFDB,stroke:#6E8900,stroke-width:2px,color:#2E3900
    classDef process fill:#E5F4FF,stroke:#006DDD,stroke-width:2px,color:#030710
    classDef neutral fill:#F2FAFF,stroke:#40668D,stroke-width:2px,color:#2F4B68

    class A trigger
    class B,C,D process
    class E,F neutral

Learn more

Agents Context engineering in agents