langchainrust

A LangChain-inspired Rust framework for building LLM applications.

What it solves: Build Agents, RAG, BM25 keyword search, Hybrid retrieval, LangGraph workflows - all in pure Rust.

Core Features

Full documentation: 中文文档 | English

Architecture

┌─────────────────────────────────────────────────────────────┐
│                      langchainrust                           │
├─────────────────────────────────────────────────────────────┤
│  LLM Layer                                                   │
│  ├── OpenAIChat / OllamaChat                                 │
│  ├── Function Calling (bind_tools)                          │
│  └── Streaming (stream_chat)                                │
├─────────────────────────────────────────────────────────────┤
│  Agent Layer                                                 │
│  ├── ReActAgent / FunctionCallingAgent                      │
│  ├── AgentExecutor                                          │
│  └── LangGraph (StateGraph, Subgraph, Parallel)             │
├─────────────────────────────────────────────────────────────┤
│  Retrieval Layer                                             │
│  ├── RAG (TextSplitter, VectorStore)                        │
│  ├── BM25 (Keyword Search, AutoMerging)                     │
│  ├── Hybrid (BM25 + Vector, RRF Fusion)                     │
│  └── Storage (InMemory, MongoDB)                            │
├─────────────────────────────────────────────────────────────┤
│  Utility Layer                                               │
│  ├── Memory (Buffer, Window, Summary)                       │
│  ├── Chains (LLMChain, SequentialChain)                     │
│  ├── Prompts (PromptTemplate, ChatPromptTemplate)           │
│  ├── Tools (Calculator, DateTime, URLFetch)                 │
│  └── Callbacks (LangSmith, StdOut)                          │
└─────────────────────────────────────────────────────────────┘

Installation

[dependencies]
langchainrust = "0.2.6"
tokio = { version = "1.0", features = ["full"] }

# Optional features
langchainrust = { version = "0.2.6", features = ["mongodb-persistence"] }  # MongoDB storage
langchainrust = { version = "0.2.6", features = ["qdrant-integration"] }    # Qdrant vector DB

Quick Start

use langchainrust::{OpenAIChat, OpenAIConfig, BaseChatModel};
use langchainrust::schema::Message;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let config = OpenAIConfig {
        api_key: std::env::var("OPENAI_API_KEY")?,
        base_url: "https://api.openai.com/v1".to_string(),
        model: "gpt-3.5-turbo".to_string(),
        ..Default::default()
    };
    
    let llm = OpenAIChat::new(config);
    
    let response = llm.chat(vec![
        Message::system("You are a helpful assistant."),
        Message::human("What is Rust?"),
    ], None).await?;
    
    println!("{}", response.content);
    Ok(())
}

BM25 Keyword Search

use langchainrust::{BM25Retriever, Document};

let mut retriever = BM25Retriever::new();

retriever.add_documents_sync(vec![
    Document::new("Rust is a systems programming language"),
    Document::new("Python is a scripting language"),
]);

let results = retriever.search("systems programming", 3);

for result in results {
    println!("Document: {}", result.document.content);
    println!("Score: {}", result.score);
}

More examples in Usage Guide (中文).

Documentation

Examples

# No API key required
cargo run --example prompt_template
cargo run --example tools

# Requires API key
export OPENAI_API_KEY="your-key"
cargo run --example hello_llm
cargo run --example agent_with_tools

See examples/ directory for more.

Testing

cargo test

Roadmap

See ROADMAP.md for details.

Contributing

Contributions welcome! See CONTRIBUTING.md.

License

MIT or Apache-2.0, at your option.