Skip to main content
加载由 Intel® Extension for Transformers（ITREX）生成的量化 BGE 嵌入模型，并使用 ITREX Neural Engine（一个高性能 NLP 后端）在不牺牲精度的情况下加速模型推理。 请参阅我们的博客文章 使用 Intel Extension for Transformers 实现高效自然语言嵌入模型 和 BGE 优化示例 以获取更多详情。 
from langchain_community.embeddings import QuantizedBgeEmbeddings

model_name = "Intel/bge-small-en-v1.5-sts-int8-static-inc"
encode_kwargs = {"normalize_embeddings": True}  # set True to compute cosine similarity

model = QuantizedBgeEmbeddings(
    model_name=model_name,
    encode_kwargs=encode_kwargs,
    query_instruction="Represent this sentence for searching relevant passages: ",
)

/home/yuwenzho/.conda/envs/bge/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
2024-03-04 10:17:17 [INFO] Start to extarct onnx model ops...
2024-03-04 10:17:17 [INFO] Extract onnxruntime model done...
2024-03-04 10:17:17 [INFO] Start to implement Sub-Graph matching and replacing...
2024-03-04 10:17:18 [INFO] Sub-Graph match and replace done...

​
使用方法

text = "This is a test document."
query_result = model.embed_query(text)
doc_result = model.embed_documents([text])
在 GitHub 上编辑此页面 或提交问题。
通过 MCP 将这些文档连接 到 Claude、VSCode 等，获取实时解答。