Vector Database Stories
From company news to technical tutorials – explore the most popular content on the Zilliz blog.
Engineering
Text as Data, From Anywhere to Anywhere
Whether you prefer a no-code or minimal-code approach, Airbyte and PyAirbyte offer robust solutions for integrating both structured and unstructured data. AJ Steers' painted a good picture of the potential of these tools in revolutionizing data workflows.
Product
How to Connect to Milvus Lite Using LangChain and LlamaIndex
Milvus Lite is now the default method for third-party connectors like LangChain and LlamaIndex to connect to Milvus, the popular open-source vector database.
Engineering
Are CPUs Enough? A Review Of Vector Search Running On Novel Hardware
The rapid advancements in hardware technology are paving the way for more efficient and powerful vector search capabilities. As illustrated by the NeurIPS BigANN competition and Zilliz's contributions, the intersection of advanced hardware and innovative algorithms is key to the future of data retrieval technologies.
Product
Expanding Our Reach: Zilliz Cloud Now Available in 11 Regions across 3 Major Cloud Providers
This expansion means you can deploy Zilliz Cloud closer to where your users are, reducing latency and improving performance.
Engineering
Elevating User Experience with Image-based Fashion Recommendations
This article explores the concepts and architecture, highlighting how AI can transform the fashion industry. We'll begin by explaining visual embeddings, which are crucial for understanding the article. Next, we'll detail how Joan built and stored images in a vector database like Milvus. Finally, we'll outline the step-by-step process of how the model generates recommendations.
Engineering
Advanced Retrieval Augmented Generation (RAG) Apps with LlamaIndex
Laurie’s presentation showcases basic and advanced application frameworks for RAG, which we can build with minimal lines of code using LlamaIndex. LlamaIndex also provides us with LlamaParse, which can help us index our data into our favorite vector databases like Milvus locally or on the cloud. It’s ultimately up to the user to choose what best fits their use cases. This presentation also showcased various RAG strategies that one can opt for to optimize Retrieval and Generation.
Vector Database 101
An Introduction to Vector Embeddings: What They Are and How to Use Them
In this blog post, we will understand the concept of vector embeddings and explore its applications, best practices, and tools for working with embeddings.
Engineering
The Path to Production: LLM Application Evaluations and Observability
A recap of Hakan Tekgul’s talk about LLM Evaluation and Troubleshooting at the SF Unstructured Data Meetup.
Case Study
Improving Behavior Science Experiments with LLMs and Milvus
this is a meetup recap blog covering how LLMs and Milvus help improve the results of behavior science experiments.