The semantic field turns images, audio, video, PDFs and text into multimodal embeddings at ingest time. Describe a scene and find the matching image or use a video frame to surface related clips, all from one Elasticsearch field. Multimodal search in Elasticsearch now works the same way text search does: define a field, index your content, and query. The semantic field generates embeddings automatically at ingest time for images, audio, video, and PDFs.
Every modality lands in one shared vector space, so you can retrieve an image with a text description, match audio to a phrase, or find a video with a still frame, all from a single field. Available in Elasticsearch 9. 5 and serverless as a tech preview. Tech preview features are subject to change and are not covered by the support SLA of general availability features. The semantic field is a convergence of several complementary features we've introduced over the past couple of years, bringing them together to create a cohesive multimodal search experience.
Each solved an important piece of the semantic search puzzle on its own; together they enable native multimodal search. The first brushstroke was semantic_text . Before it, running semantic search meant manually configuring mappings, wiring up ingest pipelines with an ML model, manually chunking content, and generating query-time embeddings yourself. The semantic_text field folds all of that away: it performs inference automatically at ingest time, chunks long documents for you, and simplifies the queries you write against it. Introduced in Elasticsearch 8. 15 and released as GA in Elasticsearch 8.
18 , it has become the foundation for semantic search on the platform. Next came the model to power multimodal search . jina-embeddings-v5-omni is our family of multimodal embedding models, capable of embedding text, images, video, audio, and PDFs into a shared vector space. Because those embeddings are semantically compatible across modalities, you can store diverse media in a single index and query across all of it at once, such as retrieving an image via a text description or matching audio against a written phrase, all without maintaining a separate pipeline for each content type.