jina-embeddings-v5-text-nano-retrieval-mlx

import mlx.core as mx
from tokenizers import Tokenizer
from model import JinaEmbeddingModel
import json

with open("config.json") as f:
    config = json.load(f)

model = JinaEmbeddingModel(config)
weights = mx.load("model.safetensors")
model.load_weights(list(weights.items()))

tokenizer = Tokenizer.from_file("tokenizer.json")

# Encode query
query_embeddings = model.encode(
    ["Overview of climate change impacts on coastal cities"],
    tokenizer,
    task_type="retrieval.query",
)

# Encode document
document_embeddings = model.encode(
    ["Climate change has led to rising sea levels, increased frequency of extreme weather events..."],
    tokenizer,
    task_type="retrieval.passage",
)