Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

BCEmbedding: Bilingual and Crosslingual Embedding for RAG

最新、最详细bce-reranker-base_v1相关信息,请移步(The latest "Updates" should be checked in):


主要特点(Key Features):

  • 中英日韩四个语种,以及中英日韩四个语种的跨语种能力(Multilingual and Crosslingual capability in English, Chinese, Japanese and Korean);
  • RAG优化,适配更多真实业务场景(RAG adaptation for more domains, including Education, Law, Finance, Medical, Literature, FAQ, Textbook, Wikipedia, etc.);
  • BCEmbedding适配长文本做rerank(Handle long passages reranking more than 512 limit in BCEmbedding);
  • RerankerModel可以提供 “平滑”的“绝对”相关性分数“平滑”对排序友好“绝对”分数用于过滤低质量passage。(RerankerModel provides "smooth" (for reranking) and "meaningful" (for filtering bad passages) similarity score, which help you figure out how relavent the query and passages are!)
  • 最佳实践(Best practice) :embedding召回top50-100片段,reranker对这50-100片段精排,最后取top5-10片段。(1. Get top 50-100 passages with bce-embedding-base_v1 for "recall"; 2. Rerank passages with bce-reranker-base_v1 and get top 5-10 for "precision" finally. )


Third-party Examples:



Click to Open Contents

Bilingual and Crosslingual Embedding (BCEmbedding), developed by NetEase Youdao, encompasses EmbeddingModel and RerankerModel. The EmbeddingModel specializes in generating semantic vectors, playing a crucial role in semantic search and question-answering, and the RerankerModel excels at refining search results and ranking tasks.

BCEmbedding serves as the cornerstone of Youdao's Retrieval Augmented Generation (RAG) implmentation, notably QAnything [github], an open-source implementation widely integrated in various Youdao products like Youdao Speed Reading and Youdao Translation.

Distinguished for its bilingual and crosslingual proficiency, BCEmbedding excels in bridging Chinese and English linguistic gaps, which achieves

  • A high performence on Semantic Representation Evaluations in MTEB;

  • A new benchmark in the realm of RAG Evaluations in LlamaIndex.


    BCEmbedding作为有道的检索增强生成式应用(RAG)的基石,特别是在QAnything [github]中发挥着重要作用。QAnything作为一个网易有道开源项目,在有道许多产品中有很好的应用实践,比如有道速读有道翻译


🌐 Bilingual and Crosslingual Superiority

Existing embedding models often encounter performance challenges in bilingual and crosslingual scenarios, particularly in Chinese, English and their crosslingual tasks. BCEmbedding, leveraging the strength of Youdao's translation engine, excels in delivering superior performance across monolingual, bilingual, and crosslingual settings.

EmbeddingModel supports Chinese (ch) and English (en) (more languages support will come soon), while RerankerModel supports Chinese (ch), English (en), Japanese (ja) and Korean (ko).



💡 Key Features

  • Bilingual and Crosslingual Proficiency: Powered by Youdao's translation engine, excelling in Chinese, English and their crosslingual retrieval task, with upcoming support for additional languages.

  • RAG-Optimized: Tailored for diverse RAG tasks including translation, summarization, and question answering, ensuring accurate query understanding. See RAG Evaluations in LlamaIndex.

  • Efficient and Precise Retrieval: Dual-encoder for efficient retrieval of EmbeddingModel in first stage, and cross-encoder of RerankerModel for enhanced precision and deeper semantic analysis in second stage.

  • Broad Domain Adaptability: Trained on diverse datasets for superior performance across various fields.

  • User-Friendly Design: Instruction-free, versatile use for multiple tasks without specifying query instruction for each task.

  • Meaningful Reranking Scores: RerankerModel provides relevant scores to improve result quality and optimize large language model performance.

  • Proven in Production: Successfully implemented and validated in Youdao's products.

    • 双语和跨语种能力:基于有道翻译引擎的强大能力,我们的BCEmbedding具备强大的中英双语和跨语种语义表征能力。

    • RAG适配:面向RAG做了针对性优化,可以适配大多数相关任务,比如翻译,摘要,问答等。此外,针对问题理解(query understanding)也做了针对优化,详见 基于LlamaIndex的RAG评测指标

    • 高效且精确的语义检索EmbeddingModel采用双编码器,可以在第一阶段实现高效的语义检索。RerankerModel采用交叉编码器,可以在第二阶段实现更高精度的语义顺序精排。

    • 更好的领域泛化性:为了在更多场景实现更好的效果,我们收集了多种多样的领域数据。

    • 用户友好:语义检索时不需要特殊指令前缀。也就是,你不需要为各种任务绞尽脑汁设计指令前缀。

    • 有意义的重排序分数RerankerModel可以提供有意义的语义相关性分数(不仅仅是排序),可以用于过滤无意义文本片段,提高大模型生成效果。

    • 产品化检验BCEmbedding已经被有道众多真实产品检验。

🚀 Latest Updates

🍎 Model List

Model Name Model Type Languages Parameters Weights
bce-embedding-base_v1 EmbeddingModel ch, en 279M download
bce-reranker-base_v1 RerankerModel ch, en, ja, ko 279M download

📖 Manual


First, create a conda environment and activate it.

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

Then install BCEmbedding for minimal installation:

pip install BCEmbedding==0.1.1

Or install from source:

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

Quick Start

1. Based on BCEmbedding

Use EmbeddingModel, and cls pooler is default.

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)

Use RerankerModel to calculate relevant scores and rerank:

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)


  • In RerankerModel.rerank method, we provide an advanced preproccess that we use in production for making sentence_pairs, when "passages" are very long.

2. Based on transformers

For EmbeddingModel:

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"

# 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

For RerankerModel:

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"

# 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)

3. Based on sentence_transformers

For EmbeddingModel:

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)

For RerankerModel:

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)

Integrations for RAG Frameworks

1. Used in langchain

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(

# 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)

2. Used in llama_index

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?")

⚙️ Evaluation

Evaluate Semantic Representation by MTEB

We provide evaluateion tools for embedding and reranker models, based on MTEB and C_MTEB.


1. Embedding Models

Just run following cmd to evaluate your_embedding_model (e.g. maidalun1020/bce-embedding-base_v1) in bilingual and crosslingual settings (e.g. ["en", "zh", "en-zh", "zh-en"]).

运行下面命令评测your_embedding_model(比如,maidalun1020/bce-embedding-base_v1)。评测任务将会在双语和跨语种(比如,["en", "zh", "en-zh", "zh-en"])模式下评测:

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

The total evaluation tasks contain 114 datastes of "Retrieval", "STS", "PairClassification", "Classification", "Reranking" and "Clustering".

评测包含 "Retrieval", "STS", "PairClassification", "Classification", "Reranking"和"Clustering" 这六大类任务的 114个数据集


  • All models are evaluated in their recommended pooling method (pooler).
    • mean pooler: "jina-embeddings-v2-base-en", "m3e-base", "m3e-large", "e5-large-v2", "multilingual-e5-base", "multilingual-e5-large" and "gte-large".
    • cls pooler: Other models.
  • "jina-embeddings-v2-base-en" model should be loaded with trust_remote_code.
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


  • 所有模型的评测采用各自推荐的pooler。"jina-embeddings-v2-base-en", "m3e-base", "m3e-large", "e5-large-v2", "multilingual-e5-base", "multilingual-e5-large"和"gte-large"的 pooler采用mean,其他模型的pooler采用cls.
  • "jina-embeddings-v2-base-en"模型在载入时需要trust_remote_code

2. Reranker Models

Run following cmd to evaluate your_reranker_model (e.g. "maidalun1020/bce-reranker-base_v1") in bilingual and crosslingual settings (e.g. ["en", "zh", "en-zh", "zh-en"]).

运行下面命令评测your_reranker_model(比如,maidalun1020/bce-reranker-base_v1)。评测任务将会在 双语种和跨语种(比如,["en", "zh", "en-zh", "zh-en"])模式下评测:

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

The evaluation tasks contain 12 datastes of "Reranking".

评测包含 "Reranking" 任务的 12个数据集

3. Metrics Visualization Tool

We proveide a one-click script to sumarize evaluation results of embedding and reranker models as Embedding Models Evaluation Summary and Reranker Models Evaluation Summary.


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

Evaluate RAG by LlamaIndex

LlamaIndex is a famous data framework for LLM-based applications, particularly in RAG. Recently, the LlamaIndex Blog has evaluated the popular embedding and reranker models in RAG pipeline and attract great attention. Now, we follow its pipeline to evaluate our BCEmbedding.


First, install LlamaIndex:

pip install llama-index==0.9.22

1. Metrics Definition

  • Hit Rate:

    Hit rate calculates the fraction of queries where the correct answer is found within the top-k retrieved documents. In simpler terms, it's about how often our system gets it right within the top few guesses. The larger, the better.

  • Mean Reciprocal Rank (MRR):

    For each query, MRR evaluates the system's accuracy by looking at the rank of the highest-placed relevant document. Specifically, it's the average of the reciprocals of these ranks across all the queries. So, if the first relevant document is the top result, the reciprocal rank is 1; if it's second, the reciprocal rank is 1/2, and so on. The larger, the better.

    • 命中率(Hit Rate)


    • 平均倒数排名(Mean Reciprocal Rank,MRR)


2. Reproduce LlamaIndex Blog

In order to compare our BCEmbedding with other embedding and reranker models fairly, we provide a one-click script to reproduce results of the LlamaIndex Blog, including our BCEmbedding:


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

Then, sumarize the evaluation results by:

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

Results Reproduced from the LlamaIndex Blog can be checked in Reproduced Summary of RAG Evaluation, with some obvious conclusions:

  • In WithoutReranker setting, our bce-embedding-base_v1 outperforms all the other embedding models.

  • With fixing the embedding model, our bce-reranker-base_v1 achieves the best performence.

  • The combination of bce-embedding-base_v1 and bce-reranker-base_v1 is SOTA.

    输出的指标汇总详见 ***LlamaIndex RAG评测结果复现***。从该复现结果中,可以看出:

    • WithoutReranker设置下(竖排对比),bce-embedding-base_v1比其他embedding模型效果都要好。
    • 在固定embedding模型设置下,对比不同reranker效果(横排对比),bce-reranker-base_v1比其他reranker模型效果都要好。
    • bce-embedding-base_v1bce-reranker-base_v1组合,表现SOTA。

3. Broad Domain Adaptability

The evaluation of LlamaIndex Blog is monolingual, small amount of data, and specific domain (just including "llama2" paper). In order to evaluate the broad domain adaptability, bilingual and crosslingual capability, we follow the blog to build a multiple domains evaluation dataset (includding "Computer Science", "Physics", "Biology", "Economics", "Math", and "Quantitative Finance"), named CrosslingualMultiDomainsDataset, by OpenAI gpt-4-1106-preview for high quality.

在上述的LlamaIndex博客的评测数据只用了“llama2”这一篇文章,该评测是 单语种,小数据量,特定领域 的。为了兼容更真实更广的用户使用场景,评测算法模型的 领域泛化性,双语和跨语种能力,我们按照该博客的方法构建了一个多领域(计算机科学,物理学,生物学,经济学,数学,量化金融等)的双语种、跨语种评测数据,CrosslingualMultiDomainsDataset为了保证构建数据的高质量,我们采用OpenAI的gpt-4-1106-preview

First, run following cmd to evaluate the most popular and powerful embedding and reranker models:

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

Then, run the following script to sumarize the evaluation results:

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

The summary of multiple domains evaluations can be seen in Multiple Domains Scenarios.

📈 Leaderboard

Semantic Representation Evaluations in MTEB

1. Embedding Models

Model Dimensions Pooler Instructions Retrieval (47) STS (19) PairClassification (5) Classification (21) Reranking (12) Clustering (15) AVG (119)
bge-base-en-v1.5 768 cls Need 37.14 55.06 75.45 59.73 43.00 37.74 47.19
bge-base-zh-v1.5 768 cls Need 47.63 63.72 77.40 63.38 54.95 32.56 53.62
bge-large-en-v1.5 1024 cls Need 37.18 54.09 75.00 59.24 42.47 37.32 46.80
bge-large-zh-v1.5 1024 cls Need 47.58 64.73 79.14 64.19 55.98 33.26 54.23
e5-large-v2 1024 mean Need 35.98 55.23 75.28 59.53 42.12 36.51 46.52
gte-large 1024 mean Free 36.68 55.22 74.29 57.73 42.44 38.51 46.67
gte-large-zh 1024 cls Free 41.15 64.62 77.58 62.04 55.62 33.03 51.51
jina-embeddings-v2-base-en 768 mean Free 31.58 54.28 74.84 58.42 41.16 34.67 44.29
m3e-base 768 mean Free 46.29 63.93 71.84 64.08 52.38 37.84 53.54
m3e-large 1024 mean Free 34.85 59.74 67.69 60.07 48.99 31.62 46.78
multilingual-e5-base 768 mean Need 54.73 65.49 76.97 69.72 55.01 38.44 58.34
multilingual-e5-large 1024 mean Need 56.76 66.79 78.80 71.61 56.49 43.09 60.50
bce-embedding-base_v1 768 cls Free 57.60 65.73 74.96 69.00 57.29 38.95 59.43


  • Our bce-embedding-base_v1 outperforms other opensource embedding models with comparable model size.

  • 114 datastes of "Retrieval", "STS", "PairClassification", "Classification", "Reranking" and "Clustering" in ["en", "zh", "en-zh", "zh-en"] setting.

  • The crosslingual evaluation datasets we released belong to Retrieval task.

  • More evaluation details please check Embedding Models Evaluation Summary.


    • 对比其他开源的相同规模的embedding模型,bce-embedding-base_v1 表现最好,效果比最好的large模型稍差。
    • 评测包含 "Retrieval", "STS", "PairClassification", "Classification", "Reranking"和"Clustering" 这六大类任务的共 114个数据集
    • 我们开源的跨语种语义表征评测数据属于Retrieval任务。
    • 更详细的评测结果详见Embedding模型指标汇总

2. Reranker Models

Model Reranking (12) AVG (12)
bge-reranker-base 59.04 59.04
bge-reranker-large 60.86 60.86
bce-reranker-base_v1 61.29 61.29


  • Our bce-reranker-base_v1 outperforms other opensource reranker models.

  • 12 datastes of "Reranking" in ["en", "zh", "en-zh", "zh-en"] setting.

  • More evaluation details please check Reranker Models Evaluation Summary.


    • bce-reranker-base_v1 优于其他开源reranker模型。
    • 评测包含 "Reranking" 任务的 12个数据集
    • 更详细的评测结果详见Reranker模型指标汇总

RAG Evaluations in LlamaIndex

1. Multiple Domains Scenarios



  • Evaluated in ["en", "zh", "en-zh", "zh-en"] setting.

  • In WithoutReranker setting, our bce-embedding-base_v1 outperforms all the other embedding models.

  • With fixing the embedding model, our bce-reranker-base_v1 achieves the best performence.

  • The combination of bce-embedding-base_v1 and bce-reranker-base_v1 is SOTA.


    • 评测是在["en", "zh", "en-zh", "zh-en"]设置下。
    • WithoutReranker设置下(竖排对比),bce-embedding-base_v1优于其他Embedding模型,包括开源和闭源。
    • 在固定Embedding模型设置下,对比不同reranker效果(横排对比),bce-reranker-base_v1比其他reranker模型效果都要好,包括开源和闭源。
    • bce-embedding-base_v1bce-reranker-base_v1组合,表现SOTA。

🛠 Youdao's BCEmbedding API

For users who prefer a hassle-free experience without the need to download and configure the model on their own systems, BCEmbedding is readily accessible through Youdao's API. This option offers a streamlined and efficient way to integrate BCEmbedding into your projects, bypassing the complexities of manual setup and maintenance. Detailed instructions and comprehensive API documentation are available at Youdao BCEmbedding API. Here, you'll find all the necessary guidance to easily implement BCEmbedding across a variety of use cases, ensuring a smooth and effective integration for optimal results.

对于那些更喜欢直接调用api的用户,有道提供方便的BCEmbedding调用api。该方式是一种简化和高效的方式,将BCEmbedding集成到您的项目中,避开了手动设置和系统维护的复杂性。更详细的api调用接口说明详见有道BCEmbedding API

🧲 WeChat Group

Welcome to scan the QR code below and join the WeChat group.



✏️ Citation

If you use BCEmbedding in your research or project, please feel free to cite and star it:


    title={BCEmbedding: Bilingual and Crosslingual Embedding for RAG},
    author={NetEase Youdao, Inc.},

🔐 License

BCEmbedding is licensed under Apache 2.0 License

🔗 Related Links

Netease Youdao - QAnything




LLama Index | LlamaIndex Blog

Downloads last month
Inference Examples
Inference API (serverless) does not yet support sentence-transformers models for this pipeline type.