Weaviate Blog
Weaviate 1.23 Release

Weaviate 1.23 Release
Weaviate 1.23 released with AutoPQ, flat indexing + Binary Quantization, OSS LLM support through Anyscale, and more!
Multimodal Retrieval-Augmented Generation (RAG)

Multimodal Retrieval-Augmented Generation (RAG)
Learn how to build Multimodal Retrieval Augmented Generation (MM-RAG) systems that combine text, images, audio, and video. Discover contrastive learning, any-to-any search with vector databases, and practical code examples using Weaviate and OpenAI GPT-4V.
Weaviate’s re:Invent 2023 recap

Weaviate’s re:Invent 2023 recap
Recap the first Weaviate visit to Amazon re:Invent in Las Vegas
Achieve Zero-Downtime Upgrades with Weaviate’s Multi-Node Setup

Achieve Zero-Downtime Upgrades with Weaviate’s Multi-Node Setup
Learn about high-availability setups with Weaviate, which can allow upgrades and other maintenance with zero downtime.
An Overview on RAG Evaluation

An Overview on RAG Evaluation
Learn about new trends in RAG evaluation and the current state of the art.
Building an AI-Powered Shopping Copilot with Weaviate

Building an AI-Powered Shopping Copilot with Weaviate
UK-based startup Moonsift is harnessing the power of AI with Weaviate.
Weaviate 1.22 Release

Weaviate 1.22 Release
Weaviate 1.22 released with nest object storage, async indexing, further gRPC support, and more!
Hacktoberfest 2023 - Celebrating Open Source with Weaviate

Hacktoberfest 2023 - Celebrating Open Source with Weaviate
Join us in celebrating Hacktoberfest, a month-long celebration of open source!
Shape the Future - Try Our New Python Client API

Shape the Future - Try Our New Python Client API
A preview release of our new Python client is now available! Help us make it better by trying it out and providing your feedback.
Make Real-Time AI a Reality with Weaviate + Confluent

Make Real-Time AI a Reality with Weaviate + Confluent
Learn how to build an application using Weaviate and Confluent
How to Reduce Memory Requirements by up to 90%+ using Product Quantization

How to Reduce Memory Requirements by up to 90%+ using Product Quantization
The details behind how you can compress vectors using PQ with little loss of recall!
