xc-llm-ascend/examples/offline_embed.py

#
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
# Copyright 2023 The vLLM team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# This file is a part of the vllm-ascend project.
# Adapted from https://www.modelscope.cn/models/Qwen/Qwen3-Embedding-0.6B
#

import os

import torch
from vllm import LLM

os.environ["VLLM_USE_MODELSCOPE"] = "True"
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"

def get_detailed_instruct(task_description: str, query: str) -> str:
    return f'Instruct: {task_description}\nQuery:{query}'


def main():
    # Each query must come with a one-sentence instruction that describes the task
    task = 'Given a web search query, retrieve relevant passages that answer the query'

    queries = [
        get_detailed_instruct(task, 'What is the capital of China?'),
        get_detailed_instruct(task, 'Explain gravity')
    ]
    # No need to add instruction for retrieval documents
    documents = [
        "The capital of China is Beijing.",
        "Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
    ]
    input_texts = queries + documents

    model = LLM(model="Qwen/Qwen3-Embedding-0.6B", task="embed")

    outputs = model.embed(input_texts)
    embeddings = torch.tensor([o.outputs.embedding for o in outputs])
    # Calculate the similarity scores between the first two queries and the last two documents
    scores = (embeddings[:2] @ embeddings[2:].T)
    print(scores.tolist())
    # [[0.7620252966880798, 0.14078938961029053], [0.1358368694782257, 0.6013815999031067]]


if __name__ == "__main__":
    main()