Vector Database Stories
From company news to technical tutorials – explore the most popular content on the Zilliz blog.
Community
What is Voyager?
Voyager is an Approximate Nearest Neighbor (ANN) search library optimized for high-dimensional vector data.
Engineering
Leveraging Milvus and Friendli Serverless Endpoints for Advanced RAG and Multi-Modal Queries
This tutorial has demonstrated how to leverage Milvus and Friendli Serverless Endpoints to implement advanced RAG and multi-modal queries.
Product
Introducing Milvus 2.5: Built-in Full-Text Search, Advanced Query Optimization, and More 🚀
We're thrilled to announce the release of Milvus 2.5, a significant step in our journey to build the world's most complete solution for all search workloads.
Paper Reading
Unlocking the Power of Many-Shot In-Context Learning in LLMs
Many-Shot In-Context Learning is an NLP technique where a model generates predictions by observing multiple examples within the input context.
Community
Build RAG with LangChain, Milvus, and Strapi
A step-by-step guide to building an AI-powered FAQ system using Milvus as the vector database, LangChain for workflow coordination, and Strapi for content management
Community
Matryoshka Representation Learning Explained: The Method Behind OpenAI’s Efficient Text Embeddings
Matryoshka Representation Learning (MRL) is a method for generating hierarchical, nested embeddings that capture information at multiple levels of abstraction.
Community
Introducing IBM Data Prep Kit for Streamlined LLM Workflows
The Data Prep Kit (DPK) is an open-source toolkit by IBM Research designed to streamline unstructured data preparation for building AI applications.
Community
Building a RAG Application with Milvus and Databricks DBRX
In this tutorial, we will explore how to build a robust RAG application by combining the capabilities of Milvus, a scalable vector database optimized for similarity search, and DBRX.
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.