【RAG】FastEmbed：一种轻量的快速文本嵌入工具

显示全部楼层

前言

在进行文本嵌入时，尤其是RAG系统，有一个快速高效的文本嵌入工具是非常有必要的。因此，FastEmbed设计目标是提升计算效率，同时保持嵌入表示的质量。此外，FastEmbed还支持一些图像嵌入模型。

特点：

高效的计算速度，适合大规模数据处理；使用ONNX Runtime实现最优性能。
低资源消耗，适用于多种设备和环境。FastEmbed刻意减少了对外部资源的依赖，并选择了ONNX Runtime作为其运行时框架。
灵活性强，可应用于不同的 NLP 任务。
兼容GPU，支持GPU加速计算，进一步提升效率。

使用

安装

#CPU版
pipinstallfastembed

#GPU版
pipinstallfastembed-gpu

fromfastembedimportTextEmbedding
fromtypingimportList

#Examplelistofdocuments
documentsist[str]=[
"Thisisbuilttobefasterandlighterthanotherembeddinglibrariese.g.Transformers,Sentence-Transformers,etc.",
"fastembedissupportedbyandmaintainedbyQdrant.",
]

#Thiswilltriggerthemodeldownloadandinitialization
embedding_model=TextEmbedding()
print("ThemodelBAAI/bge-small-en-v1.5isreadytouse.")

embeddings_generator=embedding_model.embed(documents)#reminderthisisagenerator
embeddings_list=list(embedding_model.embed(documents))
#youcanalsoconvertthegeneratortoalist,andthattoanumpyarray
print(len(embeddings_list[0]))#Vectorof384dimensions

密集文本嵌入

fromfastembedimportTextEmbedding

model=TextEmbedding(model_name="BAAI/bge-small-en-v1.5")
embeddings=list(model.embed(documents))

#[
#array([-0.1115,0.0097,0.0052,0.0195,...],dtype=float32),
#array([-0.1019,0.0635,-0.0332,0.0522,...],dtype=float32)
#]

稀疏文本嵌入

SPLADE++

fromfastembedimportSparseTextEmbedding

model=SparseTextEmbedding(model_name="prithivida/Splade_PP_en_v1")
embeddings=list(model.embed(documents))

#[
#SparseEmbedding(indices=[17,123,919,...],values=[0.71,0.22,0.39,...]),
#SparseEmbedding(indices=[38,12,91,...],values=[0.11,0.22,0.39,...])
#]

图像嵌入

fromfastembedimportImageEmbedding

images=[
"./path/to/image1.jpg",
"./path/to/image2.jpg",
]

model=ImageEmbedding(model_name="Qdrant/clip-ViT-B-32-vision")
embeddings=list(model.embed(images))

#[
#array([-0.1115,0.0097,0.0052,0.0195,...],dtype=float32),
#array([-0.1019,0.0635,-0.0332,0.0522,...],dtype=float32)
#]