| Crates.io | llm-tools-config |
| lib.rs | llm-tools-config |
| version | 0.1.0 |
| created_at | 2025-03-17 14:47:42.912422+00 |
| updated_at | 2025-03-17 14:47:42.912422+00 |
| description | for generating LLM tools configurations for OpenAI, Gemini and more. |
| homepage | |
| repository | https://github.com/zTgx/llm-tools-config |
| max_upload_size | |
| id | 1595571 |
| size | 13,114 |
llm-tools-config is a Rust library designed to simplify the generation of tools configurations for Large Language Models (LLMs), specifically targeting OpenAI, Gemini and more. It automates the creation of JSON schemas required for function calling, making it easier to integrate external tools and APIs with your LLM applications.
Add llm-tools-config to your Cargo.toml file:
[dependencies]
llm-tools-config = "0.1.0"
Here's a basic example of how to use llm-tools-config to generate a tools configuration:
use llm_tools_config::{FunctionDefinition, FunctionParameter, ToolConfig, generate_gemini_tools_config, generate_openai_tools_config};
fn main() {
let config = ToolConfig {
functions: vec![
FunctionDefinition {
name: "get_current_weather".to_string(),
description: "Get the current weather".to_string(),
parameters: vec![
FunctionParameter {
name: "location".to_string(),
description: "City name".to_string(),
r#type: "string".to_string(),
enum_values: None,
required: true,
},
FunctionParameter {
name: "unit".to_string(),
description: "Temperature unit".to_string(),
r#type: "string".to_string(),
enum_values: Some(vec!["celsius".to_string(), "fahrenheit".to_string()]),
required: false,
},
],
},
],
};
match generate_gemini_tools_config(&config) {
Ok(gemini_json) => println!("Gemini Config: {}", gemini_json),
Err(e) => eprintln!("Gemini Config Generation Error: {}", e),
}
match generate_openai_tools_config(&config) {
Ok(openai_json) => println!("OpenAI Config: {}", openai_json),
Err(e) => eprintln!("OpenAI Config Generation Error: {}", e),
}
}
Contributions are welcome! Please feel free to submit a pull request or open an issue for bugs or feature requests.
This project is licensed under the MIT License.