scripts/infinity_demo.py

import asyncio
from infinity_emb import AsyncEngineArray, EngineArgs, AsyncEmbeddingEngine
import numpy as np

array = AsyncEngineArray.from_args([
  EngineArgs(model_name_or_path = "openbmb/MiniCPM-Embedding-Light", engine="torch", dtype="float16", bettertransformer=False, pooling_method="mean", trust_remote_code=True),
])
queries = ["中国的首都是哪里？"] # "What is the capital of China?"
passages = ["beijing", "shanghai"] # "北京", "上海"

INSTRUCTION = "Query:"
queries = [f"{INSTRUCTION} {query}" for query in queries]


async def embed_text(engine: AsyncEmbeddingEngine,sentences): 
    async with engine: 
        embeddings, usage = await engine.embed(sentences=sentences)
    return embeddings

queries_embedding = asyncio.run(embed_text(array[0],queries))
passages_embedding = asyncio.run(embed_text(array[0],passages))

scores = (np.array(queries_embedding) @ np.array(passages_embedding).T)
print(scores.tolist())  # [[0.40356746315956116, 0.36183443665504456]]