liveBook · Manning

Image input

As explained in Spring AI in Action

Image input is the inclusion of visual data in a model request so the model can interpret and answer questions about it.

Image input adds visual context to a model request, allowing a vision-capable model to interpret an image and answer a related question. section 8.2

Questioning a game image

A user uploads an in-progress Burger Battle photograph and asks which ingredients remain or whether a Burger Bomb can be played. The endpoint returns an answer grounded in the visible board state.

How Spring AI in Action covers it

How deep it goes
Implements service, prompt, controller, and upload configuration details without descending into model internals.
Examples
Uses Burger Battle photographs to ask about missing ingredients and whether a Burger Bomb can be played.
What it assumes
Assumes an existing Spring AI conversational service and teaches the additional image, content-type, and multipart request parameters.
What you can do after
Build it from scratch by exposing a multipart endpoint and attaching uploaded image resources to Spring AI user messages.
How it connects
Connects vision interactions to prompts, retrieval-augmented generation, MIME types, multipart form data, and conversation identifiers.
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.