Beyond Text: Building Multimodal Search with pgvector in PostgreSQL

Using pgvector to Model, Query, and Combine Text and Image Embeddings in SQL

Large language models are no longer limited to text. They can also understand images and other modalities and represent them as embeddings that can be stored and queried directly in PostgreSQL. In this talk, we explore how pgvector can be used to build multimodal search features where users search using text, images, or a combination of both, all within a familiar SQL-based workflow.

We ...

@ Postgres Conference: 2026
Nasiullha Chaudhari

Apr 21 2026

Dev

No past presentaions...