Langcache Embed V1

🚀 基于Alibaba-NLP/gte-modernbert-base的Redis语义缓存嵌入模型

本项目是一个基于 sentence-transformers 的模型，它在 Quora 数据集上对 Alibaba-NLP/gte-modernbert-base 进行了微调。该模型可将句子和段落映射到768维的密集向量空间，用于语义文本相似度计算，以实现语义缓存。

🚀 快速开始

首先，安装 Sentence Transformers 库：

pip install -U sentence-transformers

然后，你可以加载此模型并进行推理：

from sentence_transformers import SentenceTransformer

# 从 🤗 Hub 下载
model = SentenceTransformer("redis/langcache-embed-v1")
# 进行推理
sentences = [
    'Will the value of Indian rupee increase after the ban of 500 and 1000 rupee notes?',
    'What will be the implications of banning 500 and 1000 rupees currency notes on Indian economy?',
    "Are Danish Sait's prank calls fake?",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# 获取嵌入向量的相似度分数
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)

✨ 主要特性

• 映射能力：能够将句子和段落映射到768维的密集向量空间。
• 应用场景：可用于语义文本相似度计算，实现语义缓存。

📦 安装指南

安装 Sentence Transformers 库：

pip install -U sentence-transformers

💻 使用示例

基础用法

from sentence_transformers import SentenceTransformer

# 从 🤗 Hub 下载
model = SentenceTransformer("redis/langcache-embed-v1")
# 进行推理
sentences = [
    'Will the value of Indian rupee increase after the ban of 500 and 1000 rupee notes?',
    'What will be the implications of banning 500 and 1000 rupees currency notes on Indian economy?',
    "Are Danish Sait's prank calls fake?",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# 获取嵌入向量的相似度分数
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)

📚 详细文档

模型详情

模型来源

• 文档：Sentence Transformers 文档
• 仓库：GitHub 上的 Sentence Transformers
• Hugging Face：Hugging Face 上的 Sentence Transformers

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

二分类

训练数据集

Quora

• 数据集：Quora
• 规模：323491 个训练样本
• 列：question_1、question_2 和 label

评估数据集

Quora

• 数据集：Quora
• 规模：53486 个评估样本
• 列：question_1、question_2 和 label

🔧 技术细节

该模型基于 Sentence Transformers 框架，在 Quora 数据集上对 Alibaba-NLP/gte-modernbert-base 进行微调。通过将句子和段落映射到768维的密集向量空间，利用余弦相似度计算语义文本相似度，以实现语义缓存。

📄 许可证

文档未提及相关信息。

📖 引用

BibTeX

Redis Langcache-embed 模型

@inproceedings{langcache-embed-v1,
    title = "Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Data",
    author = "Gill, Cechmanek, Hutcherson, Rajamohan, Agarwal, Gulzar, Singh, Dion",
    month = "04",
    year = "2025",
    url = "https://arxiv.org/abs/2504.02268",
}

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}