嵌入模型
把文本转成向量的模型。它们的维度、上下文上限和许可条款差异很大，而这个选择直接决定了建立在其上的每一个检索系统的质量。
8 technologies
- OpenAI Text Embedding 3 model Hosted embedding models with configurable output dimensions.
- Cohere Embed model Hosted multilingual embedding model with separate query and document modes.
- BGE model Embedding model family that ranks well on retrieval benchmarks.
- GTE model Embedding model family from Alibaba, trained for retrieval and ranking.
- Jina Embeddings model Embedding models designed around long inputs and multilingual coverage.
- E5 model Text embedding model family trained on weakly supervised pairs.
- Nomic Embed model Open embedding model with an auditable training set and long context.
- Instructor model Embedding model that takes a task instruction alongside the text.