Struct Model 

pub struct Model<'c> {
    pub task_type: Option<TaskType>,
    /* private fields */
}

A client for generating embeddings using Google’s embedding service

Provides both single and batch embedding capabilities with configurable task types.

Example

use google_ai_rs::{Client, GenerativeModel};

let client = Client::new(auth).await?;
let embedding_model = client.embedding_model("embedding-001");

// Single embedding
let embedding = embedding_model.embed_content("Hello world").await?;

// Batch embeddings
let batch_response = embedding_model.new_batch()
    .add_content("First text")
    .add_content("Second text")
    .embed()
    .await?;

Fields

task_type: Option<TaskType>

Optional task type specification for embedding generation

Affects how embeddings are optimized:

• None: General purpose embeddings
• TaskType::RetrievalDocument: Optimized for document storage
• TaskType::RetrievalQuery: Optimized for query matching

Implementations

impl<'c> Model<'c>

pub fn new(client: &'c Client, name: &str) -> Self

Creates a new Model instance

Arguments

• client - Configured API client
• name - Model identifier (e.g., “embedding-001”)

pub fn task_type(self, task_type: TaskType) -> Self

Optional task type specification for embedding generation

Affects how embeddings are optimized:

• TaskType::RetrievalDocument: Optimized for document storage
• TaskType::RetrievalQuery: Optimized for query matching

pub async fn embed_content<T: TryIntoContent>( &self, content: T, ) -> Result<EmbedContentResponse, Error>

Embeds content using the API’s embedding service.

Consider batch embedding for multiple contents

Example

// Single text embedding
let embedding = model.embed_content("Hello world").await?;

// Multi-modal embedding
model.embed_content((
    "Query about this image",
    Part::blob("image/jpeg", image_data)
)).await?;

Errors

Returns Error::Net for transport-level errors or Error::Service for service errors

pub async fn embed_content_with_title<T>( &self, title: &str, content: T, ) -> Result<EmbedContentResponse, Error>

where T: TryIntoContent,

Embeds content with optional title context

Arguments

• title - Optional document title for retrieval tasks
• parts - Content input that converts to parts

pub fn new_batch(&self) -> Batch<'_>

Creates a new batch embedding context

pub async fn embed_batch<I, T>( &self, contents: I, ) -> Result<BatchEmbedContentsResponse, Error>

where I: IntoIterator<Item = T>, T: TryIntoContent,

Embeds multiple contents as separate content items

Example

let texts = vec!["First", "Second", "Third"];
let batch = model.embed_batch(texts).await?;

pub async fn info(&self) -> Result<Info, Error>

returns information about the model.

Trait Implementations

impl<'c> Debug for Model<'c>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.