text-embedding-ada-002
A text embedding model released by OpenAI that maps text into high-dimensional continuous vector spaces. It is used for tasks such as semantic search and similarity computation, and is one of the most widely adopted commercial embedding models available.
Core Facts
Timeline (last 90 days)
Embedding models are neural network models that map discrete inputs into dense vectors, with representative examples including OpenAI's text-embedding-ada-002, Voyage AI's voyage series, and open-source BGE, E5, GTE and others.
不同模型（如 GPT-4、GPT-3.5、text-embedding-ada-002）使用的是不同的 tokenizer，同一段文本在不同模型下的 token 数量可能不同。
The embedding similarity method encodes documents and concept descriptions as high-dimensional vectors and assesses semantic closeness via metrics such as cosine similarity, relying on pretrained sentence encoders such as Sentence-BERT and text-embedding-ada-002.
Commonly used embedding models include OpenAI's text-embedding-ada-002 and the locally runnable sentence-transformers.
cl100k_base is the specific vocabulary used by models such as GPT-4 and text-embedding-ada-002.
All Facts (11)
OpenAI's text-embedding-3-small model converts text into a floating-point array of 1,536 dimensions
80%VerifiedOpenAI的text-embedding-ada-002和开源的BGE系列是常用的Embedding模型
80%Unverified知识库检索中，文档分段后每个文本块通过嵌入模型（如text-embedding-ada-002或BGE系列）转换为高维向量存储在向量数据库中
90%UnverifiedOpenAI's text-embedding-ada-002 and the open-source sentence-transformers series are commonly used embedding models.
60%UnverifiedModern Embedding models (such as OpenAI's text-embedding-ada-002 and Alibaba's Qianwen Embedding series) can encode entire sentences or paragraphs into fixed-dimension dense vectors, typically 768 or 1024 dimensions.
60%UnverifiedEmbedding models are neural network models that map discrete inputs into dense vectors, with representative examples including OpenAI's text-embedding-ada-002, Voyage AI's voyage series, and open-source BGE, E5, GTE and others.
50%Unverified不同模型（如 GPT-4、GPT-3.5、text-embedding-ada-002）使用的是不同的 tokenizer，同一段文本在不同模型下的 token 数量可能不同。
50%UnverifiedThe embedding similarity method encodes documents and concept descriptions as high-dimensional vectors and assesses semantic closeness via metrics such as cosine similarity, relying on pretrained sentence encoders such as Sentence-BERT and text-embedding-ada-002.
50%UnverifiedCommonly used embedding models include OpenAI's text-embedding-ada-002 and the locally runnable sentence-transformers.
50%Unverifiedcl100k_base is the specific vocabulary used by models such as GPT-4 and text-embedding-ada-002.
50%UnverifiedEmbedding模型本质上是Encoder-only Transformer架构，代表为BERT及其变体，通过对比学习或掩码语言模型任务预训练
50%