交叉编码器重排序器
本笔记本展示了如何在检索器中使用您自己的交叉编码器来实现重排序器，交叉编码器来自 Hugging Face 交叉编码器模型 或实现了交叉编码器函数的 Hugging Face 模型（例如：BAAI/bge-reranker-base）。 SagemakerEndpointCrossEncoder 使您能够使用加载在 Sagemaker 上的这些 HuggingFace 模型。
这建立在 ContextualCompressionRetriever 中的想法之上。本文档的整体结构来自 Cohere Reranker 文档。
要了解更多关于为什么交叉编码器可以与嵌入结合用作重排序机制以获得更好检索效果的信息，请参阅 Hugging Face Cross-Encoders 文档。
#!pip install faiss sentence_transformers
# OR (depending on Python version)
#!pip install faiss-cpu sentence_transformers
# Helper function for printing docs
def pretty_print_docs(docs):
print(
f"\n{'-' * 100}\n".join(
[f"Document {i+1}:\n\n" + d.page_content for i, d in enumerate(docs)]
)
)
设置基础向量存储检索器
让我们从初始化一个简单的向量存储检索器并存储 2023 年国情咨文演讲（分块）开始。我们可以设置检索器来检索大量文档 (20 个)。
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
documents = TextLoader("../../how_to/state_of_the_union.txt").load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
texts = text_splitter.split_documents(documents)
embeddingsModel = HuggingFaceEmbeddings(
model_name="sentence-transformers/msmarco-distilbert-dot-v5"
)
retriever = FAISS.from_documents(texts, embeddingsModel).as_retriever(
search_kwargs={"k": 20}
)
query = "What is the plan for the economy?"
docs = retriever.invoke(query)
pretty_print_docs(docs)
使用 CrossEncoderReranker 进行重排序
现在让我们用 ContextualCompressionRetriever 包装我们的基础检索器。 CrossEncoderReranker 使用 HuggingFaceCrossEncoder 来重排序返回的结果。
from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import CrossEncoderReranker
from langchain_community.cross_encoders import HuggingFaceCrossEncoder
model = HuggingFaceCrossEncoder(model_name="BAAI/bge-reranker-base")
compressor = CrossEncoderReranker(model=model, top_n=3)
compression_retriever = ContextualCompressionRetriever(
base_compressor=compressor, base_retriever=retriever
)
compressed_docs = compression_retriever.invoke("What is the plan for the economy?")
pretty_print_docs(compressed_docs)
Document 1:
More infrastructure and innovation in America.
More goods moving faster and cheaper in America.
More jobs where you can earn a good living in America.
And instead of relying on foreign supply chains, let’s make it in America.
Economists call it “increasing the productive capacity of our economy.”
I call it building a better America.
My plan to fight inflation will lower your costs and lower the deficit.
----------------------------------------------------------------------------------------------------
Document 2:
Second – cut energy costs for families an average of $500 a year by combatting climate change.
Let’s provide investments and tax credits to weatherize your homes and businesses to be energy efficient and you get a tax credit; double America’s clean energy production in solar, wind, and so much more; lower the price of electric vehicles, saving you another $80 a month because you’ll never have to pay at the gas pump again.
----------------------------------------------------------------------------------------------------
Document 3:
Look at cars.
Last year, there weren’t enough semiconductors to make all the cars that people wanted to buy.
And guess what, prices of automobiles went up.
So—we have a choice.
One way to fight inflation is to drive down wages and make Americans poorer.
I have a better plan to fight inflation.
Lower your costs, not your wages.
Make more cars and semiconductors in America.
More infrastructure and innovation in America.
More goods moving faster and cheaper in America.
将 Hugging Face 模型上传到 SageMaker 端点
这是一个示例 inference.py，用于创建与 SagemakerEndpointCrossEncoder 协同工作的端点。有关包含分步指南的更多详细信息，请参阅这篇文章。
它会动态下载 Hugging Face 模型，因此您无需在 model.tar.gz 中保留模型工件，例如 pytorch_model.bin。
import json
import logging
from typing import List
import torch
from sagemaker_inference import encoder
from transformers import AutoModelForSequenceClassification, AutoTokenizer
PAIRS = "pairs"
SCORES = "scores"
class CrossEncoder:
def __init__(self) -> None:
self.device = (
torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
)
logging.info(f"Using device: {self.device}")
model_name = "BAAI/bge-reranker-base"
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
self.model = AutoModelForSequenceClassification.from_pretrained(model_name)
self.model = self.model.to(self.device)
def __call__(self, pairs: List[List[str]]) -> List[float]:
with torch.inference_mode():
inputs = self.tokenizer(
pairs,
padding=True,
truncation=True,
return_tensors="pt",
max_length=512,
)
inputs = inputs.to(self.device)
scores = (
self.model(**inputs, return_dict=True)
.logits.view(
-1,
)
.float()
)
return scores.detach().cpu().tolist()
def model_fn(model_dir: str) -> CrossEncoder:
try:
return CrossEncoder()
except Exception:
logging.exception(f"Failed to load model from: {model_dir}")
raise
def transform_fn(
cross_encoder: CrossEncoder, input_data: bytes, content_type: str, accept: str
) -> bytes:
payload = json.loads(input_data)
model_output = cross_encoder(**payload)
output = {SCORES: model_output}
return encoder.encode(output, accept)