Crate zai_rs 

ZAI-RS: Zhipu AI Rust SDK

zai-rs is a type-safe Rust SDK that provides complete support for the Zhipu AI (BigModel) APIs. It offers strongly typed API clients and models for a wide range of AI capabilities including chat, image generation, speech recognition, and text-to-speech.

Capabilities

• Chat completions (text, vision, and voice)
• Image generation
• Speech-to-text (audio transcription)
• Text-to-speech (audio synthesis)
• Tool/function calling integration
• File management (upload, list, content, delete)
• Streaming responses via Server-Sent Events (SSE)

Module Structure

• client — HTTP client and networking
• model — Data models, API request/response types
• file — File management features
• batches — Batch processing endpoints (list batches)
• toolkits — Tool calling and execution framework

Quick Start

use zai_rs::{client::http::*, model::*};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let model = GLM4_5_flash {};
    let key = std::env::var("ZHIPU_API_KEY").unwrap();
    let client = ChatCompletion::new(model, TextMessage::user("Hello"), key);
    let _resp = client.post().await?;
    Ok(())
}

Features

• Type safety with compile-time checks to minimize runtime errors
• Async support powered by Tokio
• Streaming support for real-time responses
• Tool integration for function calling and external tools
• Built-in validation and error handling

Re-exports

pub use client::error::*;

Modules

batches

Batch Processing Module

client

HTTP Client Module

file

File Management Module

knowledge

Knowledge Base Module

model

Model Module

tool

Tool Module

toolkits

Toolkits Module

Macros

define_model_type

Macro for defining AI model types with standard implementations.

impl_message_binding

Macro for binding message types to AI models.

impl_model_markers

Macro for implementing multiple capability traits on model types.