Copy
---
title: IPEX-LLM - Intel CPU에서 로컬 BGE Embeddings 사용하기
---
> [IPEX-LLM](https://github.com/intel-analytics/ipex-llm)은 Intel CPU 및 GPU(예: iGPU가 있는 로컬 PC, Arc, Flex, Max와 같은 discrete GPU)에서 매우 낮은 지연 시간으로 LLM을 실행하기 위한 PyTorch 라이브러리입니다.
이 예제는 Intel CPU에서 `ipex-llm` 최적화를 사용하여 LangChain으로 embedding 작업을 수행하는 방법을 다룹니다. 이는 RAG, 문서 QA 등과 같은 애플리케이션에서 유용합니다.
## Setup
```python
pip install -qU langchain langchain-community
sentence-transformers를 설치합니다.
Copy
pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu
pip install sentence-transformers
Note Windows 사용자의 경우,ipex-llm설치 시--extra-index-url https://download.pytorch.org/whl/cpu는 필요하지 않습니다.
Basic Usage
Copy
from langchain_community.embeddings import IpexLLMBgeEmbeddings
embedding_model = IpexLLMBgeEmbeddings(
model_name="BAAI/bge-large-en-v1.5",
model_kwargs={},
encode_kwargs={"normalize_embeddings": True},
)
API reference
Copy
sentence = "IPEX-LLM is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max) with very low latency."
query = "What is IPEX-LLM?"
text_embeddings = embedding_model.embed_documents([sentence, query])
print(f"text_embeddings[0][:10]: {text_embeddings[0][:10]}")
print(f"text_embeddings[1][:10]: {text_embeddings[1][:10]}")
query_embedding = embedding_model.embed_query(query)
print(f"query_embedding[:10]: {query_embedding[:10]}")
Copy
---
<Callout icon="pen-to-square" iconType="regular">
[Edit the source of this page on GitHub.](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/text_embedding/ipex_llm.mdx)
</Callout>
<Tip icon="terminal" iconType="regular">
[Connect these docs programmatically](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
</Tip>