Skip to main content

Crate ai_lib_rust

Crate ai_lib_rust 

Source
Expand description

§ai-lib-rust

这是 AI-Protocol 规范的高性能 Rust 参考实现，提供统一的多厂商 AI 模型交互接口。

Protocol Runtime for AI-Protocol - A high-performance Rust reference implementation that enables provider-agnostic AI model interactions.

§Overview

This library implements the AI-Protocol specification as a runtime, where all logic is operators and all configuration is protocol. It provides a unified interface for interacting with AI models across different providers without hardcoding provider-specific logic.

§Core Philosophy

  • Protocol-Driven: All behavior is configured through protocol manifests, not code
  • Provider-Agnostic: Unified interface across OpenAI, Anthropic, Google, and others
  • Streaming-First: Native support for Server-Sent Events (SSE) streaming
  • Type-Safe: Strongly typed request/response handling with comprehensive error types

§Key Features

  • Unified Client: AiClient provides a single entry point for all AI interactions
  • Protocol Loading: Load and validate protocol manifests from local files or remote URLs
  • Streaming Pipeline: Configurable operator pipeline for response processing
  • Batching: Efficient request batching with batch::BatchCollector
  • Caching: Response caching with pluggable backends via cache module
  • Resilience: Circuit breaker and rate limiting via resilience module
  • Content Safety: Guardrails for content filtering via guardrails module
  • Telemetry: Optional feedback collection via telemetry module

§Quick Start

use ai_lib_rust::{AiClient, AiClientBuilder, Message, MessageRole};

#[tokio::main]
async fn main() -> ai_lib_rust::Result<()> {
    let client = AiClientBuilder::new()
        .with_protocol_path("protocols/openai.yaml")?
        .with_api_key("your-api-key")
        .build()?;

    let messages = vec![
        Message::user("Hello, how are you?"),
    ];

    // Streaming response
    let mut stream = client.chat_stream(&messages, None).await?;
    // Process stream events...
     
    Ok(())
}

§Module Organization

ModuleDescription
protocolProtocol specification loading and validation
clientAI client implementation and builders
pipelineStreaming response pipeline operators
typesCore type definitions (messages, events, tools)
batchRequest batching and parallel execution
cacheResponse caching with multiple backends
embeddingsEmbedding generation and vector operations
resilienceCircuit breaker and rate limiting
guardrailsContent filtering and safety checks
tokensToken counting and cost estimation
telemetryOptional feedback and telemetry collection

Re-exports§

pub use client::CallStats;
pub use client::CancelHandle;
pub use client::ChatBatchRequest;
pub use client::EndpointExt;
pub use client::AiClient;
pub use client::AiClientBuilder;
pub use telemetry::FeedbackEvent;
pub use telemetry::FeedbackSink;
pub use types::events::StreamingEvent;
pub use types::message::Message;
pub use types::message::MessageRole;
pub use types::tool::ToolCall;
pub use error::Error;
pub use error::ErrorContext;

Modules§

batch
请求批处理模块：提供高效的批量请求收集和执行功能。
cache
响应缓存模块：提供可插拔的缓存后端以减少重复 API 调用。
client
Unified client interface for AI-Protocol runtime.
embeddings
向量嵌入模块：提供文本嵌入生成和向量相似度计算功能。
error
Error type for the library 错误处理模块：提供统一的错误类型和结构化错误上下文。
guardrails
内容安全模块：提供可配置的内容过滤和敏感信息检测功能。
pipeline
流水线处理模块：实现流式响应处理的核心算子执行引擎。
plugins
Plugin and middleware system.
protocol
协议规范层：负责加载、验证和管理 AI-Protocol 规范文件。
resilience
弹性模式模块：提供熔断器和限流器等可靠性保障机制。
telemetry
遥测与反馈模块：提供可选的、应用可控的用户反馈收集机制。
tokens
Token 计数与成本估算模块：提供多种 Token 统计方法和价格计算功能。
transport
types
类型系统模块：定义基于 AI-Protocol 规范的核心数据类型。
utils
Utility modules

Type Aliases§

BoxStream
A unified pinned, boxed stream that emits PipeResult<T>
PipeResult
A specialized Result for pipeline operations
Result
Result type alias for the library