| | import asyncio |
| | from infinity_emb import AsyncEngineArray, EngineArgs, AsyncEmbeddingEngine |
| | query = "中国的首都是哪里?" |
| | docs = ["beijing", "shanghai"] |
| |
|
| | INSTRUCTION = "Query:" |
| | query = f"{INSTRUCTION} {query}" |
| |
|
| | array = AsyncEngineArray.from_args( |
| | [EngineArgs(model_name_or_path = "OpenBMB/UltraRAG-Reranker", engine="torch", dtype="float16", bettertransformer=False, trust_remote_code=True, model_warmup=False)] |
| | ) |
| |
|
| | async def rerank(engine: AsyncEmbeddingEngine): |
| | async with engine: |
| | ranking, usage = await engine.rerank(query=query, docs=docs) |
| | print(list(zip(ranking, docs))) |
| |
|
| | asyncio.run(rerank(array[0])) |