Something went wrong. Try again.
Routing embedding stack for Qwen3-Embedding-0.6B on Apple Silicon: orchestrator + MLX + llama.cpp backends
Something went wrong. Try again.
780 B · 26 lines
Rust
at main
123456789101112131415161718192021222324252627use serde::{Deserialize, Serialize};
/// Whether the input is a document (no prefix) or a query (instruction prefix).#[derive(Debug, Clone, Copy, PartialEq, Eq, Deserialize, Serialize)]#[serde(rename_all = "lowercase")]pub enum InputKind { Document, Query,}
/// Client-facing JSON body for POST /embed.#[derive(Debug, Clone, Deserialize, Serialize)]pub struct EmbedRequest { pub texts: Vec<String>, pub input_type: InputKind, /// Optional model size. Only "0.6B" is supported; anything else is rejected. #[serde(default, skip_serializing_if = "Option::is_none")] pub size: Option<String>,}
#[derive(Debug, Clone, Serialize, Deserialize)]pub struct EmbedResponse { pub vectors: Vec<Vec<f32>>, pub dim: usize, pub model: String,}