liveBook · Manning

Embed

As explained in Spring AI in Action

An embedding API is an API that converts text or other inputs into numerical vector representations.

An embedding API converts text into a mathematical vector representation. Comparing these representations helps determine similarity between sets of text, supporting retrieval augmented generation (RAG). section 1.2

Embedding APIs appear among model-provider capabilities:

  • Cloud and local services may provide embedding APIs alongside text-generation models. section 1.2
  • Provider selection involves practical criteria such as price and context-window capacity. section 1.2

How Spring AI in Action covers it

How deep it goes
Defines the conversion and similarity purpose, but defers implementation details and embedding-model selection procedures.
Examples
Names Hugging Face, MiniMax, MistralAI, and Ollama as providers offering model services, with some also exposing embedding APIs.
What you can do after
Evaluate embedding-provider choices for similarity-based retrieval applications by comparing cost and context-window considerations.
How it connects
Connects embedding APIs with text generation, multimodal generation, model providers, similarity, and retrieval augmented generation.
Cover of Spring AI in Action
liveBookmanning.com
Read Spring AI in Action on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Spring AI in Action. The section links point to the parts of the book it draws on.