🦜️🔗LangChain Rust

⚡ 通过组合性使用 LLM 构建应用，使用 Rust！ ⚡

🤔 这是什么？

这是 LangChain 的 Rust 语言实现。

当前功能

LLMs
Embeddings
VectorStores
- OpenSearch
- Postgres
- Qdrant
- Sqlite
- SurrealDB
Chain
Agents
- Chat Agent with Tools
- Open AI Compatible Tools Agent
Tools
- Serpapi/Google
- DuckDuckGo Search
- Wolfram/Math
- Command line
- Text2Speech
Semantic Routing
- Static Routing
- Dynamic Routing

Document Loaders

PDF

use futures_util::StreamExt;

async fn main() {
    let path = "./src/document_loaders/test_data/sample.pdf";

    let loader = PdfExtractLoader::from_path(path).expect("Failed to create PdfExtractLoader");
    // let loader = LoPdfLoader::from_path(path).expect("Failed to create LoPdfLoader");

    let docs = loader
        .load()
        .await
        .unwrap()
        .map(|d| d.unwrap())
        .collect::<Vec<_>>()
        .await;

}

Pandoc

use futures_util::StreamExt;

async fn main() {

    let path = "./src/document_loaders/test_data/sample.docx";

    let loader = PandocLoader::from_path(InputFormat::Docx.to_string(), path)
        .await
        .expect("Failed to create PandocLoader");

    let docs = loader
        .load()
        .await
        .unwrap()
        .map(|d| d.unwrap())
        .collect::<Vec<_>>()
        .await;
}

HTML

use futures_util::StreamExt;
use url::Url;

async fn main() {
    let path = "./src/document_loaders/test_data/example.html";
    let html_loader = HtmlLoader::from_path(path, Url::parse("https://example.com/").unwrap())
        .expect("Failed to create html loader");

    let documents = html_loader
        .load()
        .await
        .unwrap()
        .map(|x| x.unwrap())
        .collect::<Vec<_>>()
        .await;
}

HTML 转 Markdown

use futures_util::StreamExt;
use url::Url;

async fn main() {
    let path = "./src/document_loaders/test_data/example.html";
    let html_to_markdown_loader = HtmlToMarkdownLoader::from_path(path, Url::parse("https://example.com/").unwrap(), HtmlToMarkdownOptions::default().with_skip_tags(vec!["figure".to_string()]))
        .expect("Failed to create html to markdown loader");

    let documents = html_to_markdown_loader
        .load()
        .await
        .unwrap()
        .map(|x| x.unwrap())
        .collect::<Vec<_>>()
        .await;
}

CSV

use futures_util::StreamExt;

async fn main() {
    let path = "./src/document_loaders/test_data/test.csv";
    let columns = vec![
        "name".to_string(),
        "age".to_string(),
        "city".to_string(),
        "country".to_string(),
    ];
    let csv_loader = CsvLoader::from_path(path, columns).expect("Failed to create csv loader");

    let documents = csv_loader
        .load()
        .await
        .unwrap()
        .map(|x| x.unwrap())
        .collect::<Vec<_>>()
        .await;
}

Git 提交

use futures_util::StreamExt;

async fn main() {
    let path = "/path/to/git/repo";
    let git_commit_loader = GitCommitLoader::from_path(path).expect("Failed to create git commit loader");

    let documents = csv_loader
        .load()
        .await
        .unwrap()
        .map(|x| x.unwrap())
        .collect::<Vec<_>>()
        .await;
}

源代码


let loader_with_dir =
SourceCodeLoader::from_path("./src/document_loaders/test_data".to_string())
.with_dir_loader_options(DirLoaderOptions {
glob: None,
suffixes: Some(vec!["rs".to_string()]),
exclude: None,
});

let stream = loader_with_dir.load().await.unwrap();
let documents = stream.map(|x| x.unwrap()).collect::<Vec<_>>().await;

安装

该库的运行严重依赖于 serde_json。

步骤 1：添加 `serde_json`

首先，确保已将 serde_json 添加到您的 Rust 项目中。

cargo add serde_json

步骤 2：添加 `langchain-rust`

然后，您可以将 langchain-rust 添加到您的 Rust 项目中。

简单安装

cargo add langchain-rust

使用 Sqlite

sqlite-vss

从 https://github.com/asg017/sqlite-vss 下载额外的 sqlite_vss 库

cargo add langchain-rust --features sqlite-vss

sqlite-vec

从 https://github.com/asg017/sqlite-vec 下载额外的 sqlite_vec 库

cargo add langchain-rust --features sqlite-vec

使用 Postgres

cargo add langchain-rust --features postgres

使用 SurrialDB

cargo add langchain-rust --features surrealdb

使用 Qdrant

cargo add langchain-rust --features qdrant

请记得根据您具体的使用场景替换特性标志 sqlite、postgres 或 surrealdb。

这将在您的 Cargo.toml 文件中同时添加 serde_json 和 langchain-rust 作为依赖项。现在，当您构建项目时，这两个依赖项将被获取并编译，并可在您的项目中使用。

请记住，serde_json 是必需的依赖项，而 sqlite、postgres 和 surrealdb 是根据项目需求可选添加的特性。

快速入门对话链

use langchain_rust::{
    chain::{Chain, LLMChainBuilder},
    fmt_message, fmt_placeholder, fmt_template,
    language_models::llm::LLM,
    llm::openai::{OpenAI, OpenAIModel},
    message_formatter,
    prompt::HumanMessagePromptTemplate,
    prompt_args,
    schemas::messages::Message,
    template_fstring,
};

#[tokio::main]
async fn main() {
    //We can then initialize the model:
    // If you'd prefer not to set an environment variable you can pass the key in directly via the `openai_api_key` named parameter when initiating the OpenAI LLM class:
    // let open_ai = OpenAI::default()
    //     .with_config(
    //         OpenAIConfig::default()
    //             .with_api_key("<your_key>"),
    //     ).with_model(OpenAIModel::Gpt4oMini.to_string());
    let open_ai = OpenAI::default().with_model(OpenAIModel::Gpt4oMini.to_string());


    //Once you've installed and initialized the LLM of your choice, we can try using it! Let's ask it what LangSmith is - this is something that wasn't present in the training data so it shouldn't have a very good response.
    let resp = open_ai.invoke("What is rust").await.unwrap();
    println!("{}", resp);

    // We can also guide it's response with a prompt template. Prompt templates are used to convert raw user input to a better input to the LLM.
    let prompt = message_formatter![
        fmt_message!(Message::new_system_message(
            "You are world class technical documentation writer."
        )),
        fmt_template!(HumanMessagePromptTemplate::new(template_fstring!(
            "{input}", "input"
        )))
    ];

    //We can now combine these into a simple LLM chain:

    let chain = LLMChainBuilder::new()
        .prompt(prompt)
        .llm(open_ai.clone())
        .build()
        .unwrap();

    //We can now invoke it and ask the same question. It still won't know the answer, but it should respond in a more proper tone for a technical writer!

    match chain
        .invoke(prompt_args! {
        "input" => "Quien es el escritor de 20000 millas de viaje submarino",
           })
        .await
    {
        Ok(result) => {
            println!("Result: {:?}", result);
        }
        Err(e) => panic!("Error invoking LLMChain: {:?}", e),
    }

    //If you want to prompt to have a list of messages you could use the `fmt_placeholder` macro

    let prompt = message_formatter![
        fmt_message!(Message::new_system_message(
            "You are world class technical documentation writer."
        )),
        fmt_placeholder!("history"),
        fmt_template!(HumanMessagePromptTemplate::new(template_fstring!(
            "{input}", "input"
        ))),
    ];

    let chain = LLMChainBuilder::new()
        .prompt(prompt)
        .llm(open_ai)
        .build()
        .unwrap();
    match chain
        .invoke(prompt_args! {
        "input" => "Who is the writer of 20,000 Leagues Under the Sea, and what is my name?",
        "history" => vec![
                Message::new_human_message("My name is: luis"),
                Message::new_ai_message("Hi luis"),
                ],

        })
        .await
    {
        Ok(result) => {
            println!("Result: {:?}", result);
        }
        Err(e) => panic!("Error invoking LLMChain: {:?}", e),
    }
}