HFresh is Weaviate's disk-based vector index for memory-efficient vector search, combining low heap usage with incremental background maintenance.
Part 3: We turn a messy creative archive into a searchable library using a manifest, Weaviate, and hybrid search.
PDFs full of charts and tables are notoriously hard to put through a traditional RAG pipeline. In this post, we show how late-interaction multi-vector retrieval lets you search PDFs by what the page looks like: no OCR, no chunking, no text extraction.
Part 2: Why folders, tags, and keyword search break down in real creative workflows and what retrieval needs to do instead.
Introducing medium, high, and ultrahigh effort tiers to the Query Agent's Search Mode.
Why AI won’t replace creatives, and how it can remove friction from messy workflows, lost files, and creative processes.
When a Weaviate query is slow, the first question is where the time went. Query profiling returns a per-stage, per-shard timing breakdown, making query performance issues visible.
Tokenization makes or breaks hybrid search. See how Weaviate's accent folding, custom stopwords, and /v1/tokenize endpoint power multilingual BM25.
A Researcher's Perspective on Retrieval Quality in RAG Systems
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.
