# Multimodal search

Category: [AI Search & GEO](https://seo-geo-glossary.com/en/glossary/category/ai-search-geo/) › [AI search & answer engines](https://seo-geo-glossary.com/en/glossary/category/ai-search-geo/ai-search-answer-engines/)

**Multimodal search** is search that accepts and combines more than one type of input, for example a photo and a text question. The system interprets them together.

## How does it work?

Technically, models map images and text into a shared embedding space, where items with similar meaning sit close together. That makes text-to-image, image-to-image and image-to-text queries possible, as described by OpenSearch.

## How does Google use it?

In April 2025 Google announced that AI Mode lets users ask about images they upload or take with the camera, starting in Google Labs in the U.S. According to Google's AI Mode help page (as of October 2026), users can now ask with text, voice, images or files, and AI Mode is available in many countries and languages. Gemini's multimodal capabilities let AI Mode understand the entire scene, including how objects relate to each other and their materials, colors and shapes. Lens identifies the individual objects. AI Mode then uses a query fan-out technique, issuing several queries about the whole image and about the objects in it.

Google's documentation for site owners says there are no additional requirements to appear in AI Overviews or AI Mode, and no special optimizations are necessary.

## Example

Someone photographs a bookshelf and asks for similar books. According to Google's own example, AI Mode identifies each book, recommends similar ones and shows links to buy them.

## Related terms

- [AI search](https://seo-geo-glossary.com/en/glossary/ai-search/index.md)
- [Agentic search](https://seo-geo-glossary.com/en/glossary/agentic-search/index.md)
- [Grounding with Google Search](https://seo-geo-glossary.com/en/glossary/grounding-with-google-search/index.md)
- [Query fan-out](https://seo-geo-glossary.com/en/glossary/query-fan-out/index.md)
- [AI Mode](https://seo-geo-glossary.com/en/glossary/ai-mode/index.md)

## Sources

- [Bringing multimodal search to AI Mode – Google Blog (07.04.2025)](https://blog.google/products/search/ai-mode-multimodal-search/)
- [AI Mode – Google Search Help (availability, asking with images)](https://support.google.com/websearch/answer/16011537?hl=en)
- [AI features and your website – Google Search Central](https://developers.google.com/search/docs/appearance/ai-features)
- [Multimodal search – OpenSearch Blog (11.04.2024)](https://opensearch.org/blog/multimodal-semantic-search/)

---

Last updated: October 7, 2026
URL: https://seo-geo-glossary.com/en/glossary/multimodal-search/