Vector Database Stories
From company news to technical tutorials – explore the most popular content on the Zilliz blog.
Paper Reading
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
The Goldfish Loss technique prevents the verbatim reproduction of training data in LLM output by modifying the standard next-token prediction training objective.
Community
Prover-Verifier Games Improve Legibility of LLM Outputs
We discussed the checkability training approach to help LLMs generate accurate answers that humans can easily understand and verify.
Product
Deliver RAG Applications 10x Faster with Zilliz and Vectorize
Zilliz Cloud delivers reliable vector storage and search, while Vectorize automates your RAG pipelines and keeps your embeddings up-to-date.
Paper Reading
Next-Gen Retrieval: How Cross-Encoders and Sparse Matrix Factorization Redefine k-NN Search
AXN (Adaptive Cross-Encoder Nearest Neighbor Search) uses a sparse matrix of CE scores to approximate k-NN results, reducing computation while maintaining high accuracy.
Product
Designing Multi-Tenancy RAG with Milvus: Best Practices for Scalable Enterprise Knowledge Bases
We’ve explored how multi-tenancy frameworks play a critical role in the scalability, security, and performance of RAG-powered knowledge bases.
Community
Evaluating Retrieval-Augmented Generation (RAG): Everything You Should Know
An overview of various RAG pipeline architectures, retrieval and evaluation frameworks, and examples of biases and failures in LLMs.
Engineering
Elasticsearch Was Great, But Vector Databases Are the Future
Purpose-built vector databases outperform dual-system setups by unifying Sparse-BM25 and semantic search in a single, efficient implementation.
Community
GLiNER: Generalist Model for Named Entity Recognition Using Bidirectional Transformer
GLiNER is an open-source NER model using a bidirectional transformer encoder.
Community
Mixture-of-Agents (MoA): How Collective Intelligence Elevates LLM Performance
Mixture-of-Agents (MoA) is a framework where multiple specialized LLMs, or "agents," collaborate to solve tasks by leveraging their unique strengths.