Bombek1/gte-base-litert

import numpy as np
from ai_edge_litert.interpreter import Interpreter
from transformers import AutoTokenizer

# Load model and tokenizer
interpreter = Interpreter(model_path="thenlper_gte-base.tflite")
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-base")

def get_embedding(text: str) -> np.ndarray:
    """Get sentence embedding for input text."""
    encoded = tokenizer(
        text,
        padding="max_length",
        max_length=512,
        truncation=True,
        return_tensors="np"
    )

    interpreter.set_tensor(input_details[0]["index"], encoded["input_ids"].astype(np.int64))
    interpreter.set_tensor(input_details[1]["index"], encoded["attention_mask"].astype(np.int64))
    interpreter.invoke()

    return interpreter.get_tensor(output_details[0]["index"])[0]

# Example
embedding = get_embedding("Hello, world!")
print(f"Embedding shape: {embedding.shape}")  # (768,)

@article{li2023towards,
    title={Towards General Text Embeddings with Multi-stage Contrastive Learning},
    author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and others},
    journal={arXiv preprint arXiv:2308.03281},
    year={2023}
}