Weaviate 1.15 release
Weaviate 1.15 introduces Cloud-native Backups, Memory Optimizations, faster Filtered Aggregations and Ordered Imports, new Distance Metrics and new Weaviate modules.
Release
Release
Weaviate introduces an all-new business model for vector search
Press Release: Pay-as-you-grow comes to Vector Search.
Research
Research Insights – Learning to Retrieve Passages without Supervision
Self-Supervised Retrieval can surpass BM25 and Supervised techniques. This technique also pairs very well alongside BM25 in Hybrid Retrieval. Learn more about it.
Engineering
GOMEMLIMIT is a game changer for high-memory applications
Go 1.19 introduced GOMEMLIMIT, which completely changes how you can manage memory limits in Go. Learn how it helps Weaviate be more reliable.
Search
Using Cross-Encoders as reranker in multistage vector search
Learn about bi-encoder and cross-encoder machine learning models, and why combining them could improve the vector search experience.
Release
Weaviate 1.14 release
Learn what is new in Weaviate 1.14, the most reliable and observable Weaviate release yet!
concepts
The AI-First Database Ecosystem
Learn about the vision of the AI-First Database Ecosystem, which drives the R&D of the databases of the future.
concepts
Docker and Containers with Weaviate
What Weaviate users should know about Docker & Containers.
Release
Weaviate 1.2 release – transformer models
Weaviate v1.2 introduced support for transformers (DistilBERT, BERT, RoBERTa, Sentence-BERT, etc) to vectorize and semantically search through your data.