examples/

LangGraphGo Examples

This directory contains various examples demonstrating the features of LangGraphGo.

Basic Concepts

• Basic Example: Simple graph with hardcoded steps.
• Basic LLM: Integration with LLMs.
• Conditional Routing: Dynamic routing based on state.
• Conditional Edges: Using conditional edges.

Advanced Features

• Parallel Execution: Fan-out/Fan-in execution with state merging.
• Configuration: Using runtime configuration to pass metadata and settings.
• Custom Reducer: Defining custom state reducers for complex merge logic.
• State Schema: Managing complex state updates with Schema and Reducers.
• Subgraphs: Composing graphs within graphs (New).
• Streaming Modes: Advanced streaming with updates, values, and messages modes.
• Smart Messages: Intelligent message merging with ID-based upserts.
• Command API: Dynamic control flow and state updates from nodes.
• Ephemeral Channels: Managing temporary state that clears after each step.
• Listeners: Attaching event listeners to the graph.

Persistence (Checkpointing)

• Memory: In-memory checkpointing.
• PostgreSQL: Persistent state using PostgreSQL.
• SQLite: Persistent state using SQLite.
• Redis: Persistent state using Redis.
• Durable Execution: Crash recovery and resuming execution from checkpoints.

Human-in-the-loop

• Human Approval: Workflow with interrupts and human approval steps.
• Time Travel / HITL: Inspecting, modifying state history, and forking execution (UpdateState).
• Dynamic Interrupt: Pausing execution from within a node using graph.Interrupt.

Pre-built Agents

• Create Agent: Easy way to create an agent with options.
• Dynamic Skill Agent: Agent with dynamic skill discovery and selection.
• ReAct Agent: Reason and Action agent using tools.
• Supervisor: Multi-agent orchestration using a supervisor.
• Swarm: Multi-agent collaboration using handoffs.

Memory

• Memory Basic: Basic usage of LangChain memory.
• Memory Chatbot: Chatbot with memory integration.

RAG (Retrieval Augmented Generation)

• RAG Basic: Basic RAG implementation.
• RAG Pipeline: Complete RAG pipeline.
• RAG Advanced: Advanced RAG techniques.
• RAG Conditional: Conditional RAG workflow.
• RAG with Embeddings: RAG using embeddings.
• RAG with LangChain: RAG using LangChain components.
• RAG with VectorStores: RAG using LangChain VectorStores.
• RAG with Chroma: RAG using Chroma database.

Other

• Visualization: Generating Mermaid diagrams for graphs.
• LangChain Integration: Using LangChain tools and models.
• Tavily Search: Using Tavily search tool with ReAct agent.
• Exa Search: Using Exa search tool with ReAct agent.
• GoSkills Integration: Integrating GoSkills as tools for agents.
• MCP Agent: Using Model Context Protocol (MCP) tools with agents.