Struct replicate_rust::Replicate

pub struct Replicate {
    pub predictions: Prediction,
    pub models: Model,
    pub trainings: Training,
    pub collections: Collection,
    /* private fields */
}

Fields

predictions: Prediction

Holds a reference to a Prediction struct. Use to run inference given model inputs and version.

models: Model

Holds a reference to a Model struct. Use to get information about a model.

trainings: Training

Holds a reference to a Training struct. Use to create a new training run.

collections: Collection

Holds a reference to a Collection struct. Use to get and list model collections present in Replicate.

Implementations

impl Replicate

Rust Client for interacting with the Replicate API.

pub fn new(config: Config) -> Self

Create a new Replicate client.

Example

use replicate_rust::{Replicate, config::Config};

let config = Config::default();
let replicate = Replicate::new(config);

pub fn run<K: Serialize, V: Serialize>( &self, version: String, inputs: HashMap<K, V> ) -> Result<GetPrediction, Box<dyn Error>>

Run a model with the given inputs in a blocking manner.

Arguments

• version - The version of the model to run.
• inputs - The inputs to the model in the form of a HashMap.

Example

use replicate_rust::{Replicate, config::Config};

let config = Config::default();
let replicate = Replicate::new(config);

// Construct the inputs.
let mut inputs = std::collections::HashMap::new();
inputs.insert("prompt", "a  19th century portrait of a wombat gentleman");

let version = String::from("stability-ai/stable-diffusion:27b93a2413e7f36cd83da926f3656280b2931564ff050bf9575f1fdf9bcd7478");

// Run the model.
let result = replicate.run(version, inputs);

// Print the result.
match result {
   Ok(result) => println!("Success : {:?}", result.output),
  Err(e) => println!("Error : {}", e),
}

Errors

TODO : Add errors