Multimodal embeddings allow AI systems to search and reason across text, images, audio, and video in their native formats. This blog covers the key intuitions behind how this all works and walks through three practical implementations using Weaviate and Gemini.
Glowe is a Korean beauty recommendation app that uses domain knowledge agents, custom embedding strategies, and vector search to create personalized skincare routines. Try now: https://www.glowe.app/
Late interaction allow for semantically rich interactions that enable a precise retrieval process across different modalities of unstructured data, including text and images.
How Weaviate achieved 10x Faster Keyword Search and 90% index compression
Learn about the hybrid search feature that enables you to combine dense and sparse vectors to deliver the best of both search methods!
Master modern search capabilities by building a powerful API server with Hono.js. Learn how to implement vector, hybrid, and generative search while maintaining performance and reliability.
Dive into how AI enables better eCommerce experiences with a focus on one critical component; Search.
Dive into using Weaviate for image recognition to find the "needle in a haystack"!
Hybrid Search for curious Web Developers with the new Weaviate TypeScript client and Next.js
Learn how to fine-tune Cohere's reranker and generate synthetic data using DSPy!
We look at how to build Multimodal applications in TypeScript and dive into everything that needs to happen in between.
