BCEmbedding: 面向RAG的双语跨语言嵌入模型

conda create --name bce python=3.10 -y
conda activate bce

pip install BCEmbedding==0.1.1

git clone git@github.com:netease-youdao/BCEmbedding.git
cd BCEmbedding
pip install -v -e .

from openmind import AutoTokenizer, AutoModel, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
from torch import Tensor
import openmind
import torch
import argparse
import time

# Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]  # First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="jeffding/bce-embedding-base_v1-openmind",
    )
    args = parser.parse_args()
    return args

def main():
    args = parse_args()
    model_path = args.model_name_or_path

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
        
    # Load model from HuggingFace Hub
    tokenizer = AutoTokenizer.from_pretrained(model_path,trust_remote_code=True)
    model = AutoModel.from_pretrained(model_path, trust_remote_code=True).to(device)
    start_time = time.time()
    sentences = ['如何更换花呗绑定银行卡', 'How to replace the Huabei bundled bank card']
    # Tokenize sentences
    encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt').to(device)

    # Compute token embeddings
    with torch.no_grad():
        model_output = model(**encoded_input)
    # Perform pooling. In this case, mean pooling.
    sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
    print("Sentence embeddings:")
    print(sentence_embeddings)
    
    end_time = time.time()
    print(f"硬件环境：{device},推理执行时间：{end_time - start_time}秒")
    
if __name__ == "__main__":
    main()

from BCEmbedding import EmbeddingModel

# list of sentences
sentences = ['sentence_0', 'sentence_1', ...]

# init embedding model
model = EmbeddingModel(model_name_or_path="maidalun1020/bce-embedding-base_v1")

# extract embeddings
embeddings = model.encode(sentences)

from BCEmbedding import RerankerModel

# your query and corresponding passages
query = 'input_query'
passages = ['passage_0', 'passage_1', ...]

# construct sentence pairs
sentence_pairs = [[query, passage] for passage in passages]

# init reranker model
model = RerankerModel(model_name_or_path="maidalun1020/bce-reranker-base_v1")

# method 0: calculate scores of sentence pairs
scores = model.compute_score(sentence_pairs)

# method 1: rerank passages
rerank_results = model.rerank(query, passages)

from transformers import AutoModel, AutoTokenizer

# list of sentences
sentences = ['sentence_0', 'sentence_1', ...]

# init model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('maidalun1020/bce-embedding-base_v1')
model = AutoModel.from_pretrained('maidalun1020/bce-embedding-base_v1')

device = 'cuda'  # if no GPU, set "cpu"
model.to(device)

# get inputs
inputs = tokenizer(sentences, padding=True, truncation=True, max_length=512, return_tensors="pt")
inputs_on_device = {k: v.to(self.device) for k, v in inputs.items()}

# get embeddings
outputs = model(**inputs_on_device, return_dict=True)
embeddings = outputs.last_hidden_state[:, 0]  # cls pooler
embeddings = embeddings / embeddings.norm(dim=1, keepdim=True)  # normalize

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# init model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('maidalun1020/bce-reranker-base_v1')
model = AutoModelForSequenceClassification.from_pretrained('maidalun1020/bce-reranker-base_v1')

device = 'cuda'  # if no GPU, set "cpu"
model.to(device)

# get inputs
inputs = tokenizer(sentence_pairs, padding=True, truncation=True, max_length=512, return_tensors="pt")
inputs_on_device = {k: v.to(device) for k, v in inputs.items()}

# calculate scores
scores = model(**inputs_on_device, return_dict=True).logits.view(-1,).float()
scores = torch.sigmoid(scores)

from sentence_transformers import SentenceTransformer

# list of sentences
sentences = ['sentence_0', 'sentence_1', ...]

# init embedding model
## New update for sentence-trnasformers. So clean up your "`SENTENCE_TRANSFORMERS_HOME`/maidalun1020_bce-embedding-base_v1" or "～/.cache/torch/sentence_transformers/maidalun1020_bce-embedding-base_v1" first for downloading new version.
model = SentenceTransformer("maidalun1020/bce-embedding-base_v1")

# extract embeddings
embeddings = model.encode(sentences, normalize_embeddings=True)

from sentence_transformers import CrossEncoder

# init reranker model
model = CrossEncoder('maidalun1020/bce-reranker-base_v1', max_length=512)

# calculate scores of sentence pairs
scores = model.predict(sentence_pairs)

from langchain.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_community.vectorstores.utils import DistanceStrategy

query = 'apples'
passages = [
        'I like apples', 
        'I like oranges', 
        'Apples and oranges are fruits'
    ]
  
# init embedding model
model_name = 'maidalun1020/bce-embedding-base_v1'
model_kwargs = {'device': 'cuda'}
encode_kwargs = {'batch_size': 64, 'normalize_embeddings': True, 'show_progress_bar': False}

embed_model = HuggingFaceEmbeddings(
    model_name=model_name,
    model_kwargs=model_kwargs,
    encode_kwargs=encode_kwargs
  )

# example #1. extract embeddings
query_embedding = embed_model.embed_query(query)
passages_embeddings = embed_model.embed_documents(passages)

# example #2. langchain retriever example
faiss_vectorstore = FAISS.from_texts(passages, embed_model, distance_strategy=DistanceStrategy.MAX_INNER_PRODUCT)

retriever = faiss_vectorstore.as_retriever(search_type="similarity", search_kwargs={"score_threshold": 0.5, "k": 3})

related_passages = retriever.get_relevant_documents(query)

from llama_index.embeddings import HuggingFaceEmbedding
from llama_index import VectorStoreIndex, ServiceContext, SimpleDirectoryReader
from llama_index.node_parser import SimpleNodeParser
from llama_index.llms import OpenAI

query = 'apples'
passages = [
        'I like apples', 
        'I like oranges', 
        'Apples and oranges are fruits'
    ]

# init embedding model
model_args = {'model_name': 'maidalun1020/bce-embedding-base_v1', 'max_length': 512, 'embed_batch_size': 64, 'device': 'cuda'}
embed_model = HuggingFaceEmbedding(**model_args)

# example #1. extract embeddings
query_embedding = embed_model.get_query_embedding(query)
passages_embeddings = embed_model.get_text_embedding_batch(passages)

# example #2. rag example
llm = OpenAI(model='gpt-3.5-turbo-0613', api_key=os.environ.get('OPENAI_API_KEY'), api_base=os.environ.get('OPENAI_BASE_URL'))
service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model)

documents = SimpleDirectoryReader(input_files=["BCEmbedding/tools/eval_rag/eval_pdfs/Comp_en_llama2.pdf"]).load_data()
node_parser = SimpleNodeParser.from_defaults(chunk_size=512)
nodes = node_parser.get_nodes_from_documents(documents[0:36])
index = VectorStoreIndex(nodes, service_context=service_context)
query_engine = index.as_query_engine()
response = query_engine.query("What is llama?")

python BCEmbedding/tools/eval_mteb/eval_embedding_mteb.py --model_name_or_path maidalun1020/bce-embedding-base_v1 --pooler cls

python BCEmbedding/tools/eval_mteb/eval_embedding_mteb.py --model_name_or_path {moka-ai/m3e-base | moka-ai/m3e-large} --pooler mean

python BCEmbedding/tools/eval_mteb/eval_embedding_mteb.py --model_name_or_path jinaai/jina-embeddings-v2-base-en --pooler mean --trust_remote_code

python BCEmbedding/tools/eval_mteb/eval_reranker_mteb.py --model_name_or_path maidalun1020/bce-reranker-base_v1

python BCEmbedding/evaluation/mteb/summarize_eval_results.py --results_dir {your_embedding_results_dir | your_reranker_results_dir}

pip install llama-index==0.9.22

# There should be two GPUs available at least.
CUDA_VISIBLE_DEVICES=0,1 python BCEmbedding/tools/eval_rag/eval_llamaindex_reproduce.py

python BCEmbedding/tools/eval_rag/summarize_eval_results.py --results_dir results/rag_reproduce_results

# There should be two GPUs available at least.
CUDA_VISIBLE_DEVICES=0,1 python BCEmbedding/tools/eval_rag/eval_llamaindex_multiple_domains.py

python BCEmbedding/tools/eval_rag/summarize_eval_results.py --results_dir results/rag_results

@misc{youdao_bcembedding_2023,
    title={BCEmbedding: Bilingual and Crosslingual Embedding for RAG},
    author={NetEase Youdao, Inc.},
    year={2023},
    howpublished={\url{https://github.com/netease-youdao/BCEmbedding}}
}