【RAG】FastEmbed：一种轻量的快速文本嵌入工具 - 文章 - 开发者社区

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。

picture.image FastEmbed暂时支持模型一览（截止2024.08.20）

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  
pip install fastembed  
  
# GPU版  
pip install fastembed-gpu


        
          
from fastembed import TextEmbedding  
from typing import List  
  
# Example list of documents  
documents: List[str] = [  
    "This is built to be faster and lighter than other embedding libraries e.g. Transformers, Sentence-Transformers, etc.",  
    "fastembed is supported by and maintained by Qdrant.",  
]  
  
# This will trigger the model download and initialization  
embedding_model = TextEmbedding()  
print("The model BAAI/bge-small-en-v1.5 is ready to use.")  
  
embeddings_generator = embedding_model.embed(documents)  # reminder this is a generator  
embeddings_list = list(embedding_model.embed(documents))  
# you can also convert the generator to a list, and that to a numpy array  
print(len(embeddings_list[0]) ) # Vector of 384 dimensions

密集文本嵌入


        
          
from fastembed import TextEmbedding  
  
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++


        
          
from fastembed import SparseTextEmbedding  
  
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


        
          
from fastembed import ImageEmbedding  
  
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)  
# ]

参考文献

https://github.com/qdrant/fastembed

往期相关

[【推理加速】vLLM加速部署LLM重要参数](http://mp.weixin.qq.com/s?__biz=Mzg4NjI0NDg0Ng==&mid=2247486093&idx=1&sn=fb19e70acd42dbb2745404cc3f7dbb37&chksm=cf9dde0cf8ea571aa3222cf949079562e415f1980e329e831e19425b1963aa0c4152cf8fe6f0&scene=21#wechat_redirect)


[【工具】onnx模型结构信息查看方式：netron、onnxruntime和onnx](http://mp.weixin.qq.com/s?__biz=Mzg4NjI0NDg0Ng==&mid=2247486326&idx=1&sn=91f0f295627284162f937211119c80cc&chksm=cf9ddff7f8ea56e1d4cb10aced84154d90f3e23a90fbd8c26d2589b90d0b6cdfbd2e80ddb429&scene=21#wechat_redirect)