llamaIndex 基于GPU加载本地embedding模型_云gpu llamaindex

llamaIndex 基于GPU加载本地embedding模型

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.core import Settings
import os

os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:4000"
os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True"
documents = SimpleDirectoryReader("./data/paul_graham").load_data()


Settings.embed_model = HuggingFaceEmbedding(
    model_name="/home/leicq/Documents/LLM_models/bge-large-zh-v1.5"
    
)

index = VectorStoreIndex.from_documents(
    documents,
)
print("hello")
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19