Christy Bergman

Developer Advocate

Christy Bergman is a passionate Developer Advocate at Zilliz. She previously worked in distributed computing at Anyscale and as a Specialist AI/ML Solutions Architect at AWS. Christy studied applied math, is a self-taught coder, and has published papers, including one with ACM Recsys. She enjoys hiking and bird watching.

Engineering

Building RAG with Milvus, vLLM, and Llama 3.1

vLLM is a fast and easy-to-use library for LLM inference and serving. We’ll share how to build a high-performance RAG with vLLM, Milvus, and Llama3.1.

Aug 04, 20248 min read

Engineering

Building a Multimodal Product Recommender Demo Using Milvus and Streamlit

A step-by-step guide on how to build and run the Multimodal recommendation system with Milvus, Streamlit, MagicLens, and GPT-4o.

Jul 30, 20245 min read

Engineering

Setting up Milvus on Amazon EKS

This blog provides step-by-step guidance on deploying a Milvus cluster using EKS and other services.

Jul 16, 202415 min read

Engineering

Exploring Three Key Strategies for Building Efficient Retrieval Augmented Generation (RAG)

Three key strategies to get the most out of RAG: smart text chunking, iterating on different embedding models, and experimenting with different LLMs

Jul 03, 20245 min read

Engineering

Clearing Up Misconceptions about Data Insertion Speed in Milvus

Around 97% of the "Milvus insert" time in LangChain or LlamaIndex is spent on embedding generation, while about 3% on the actual database insertion step.

Jun 18, 20245 min read

Engineering

🚀 What’s New with Metadata Filtering in Milvus v2.4.3

Milvus introduced powerful string metadata matching! Now, you can match strings using prefix, postfix, infix, and even fuzzy searches.

Jun 16, 20244 min read

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.

Jun 07, 20244 min read

Engineering

Choosing the Right Embedding Model for Your Data

This blog touched on some popular embedding models used in RAG applications.

May 22, 20246 min read

Engineering

Running Llama 3, Mixtral, and GPT-4o

This article will show a few ways to run some of the hottest contenders in the space: Llama 3 from Meta, Mixtral from Mistral, and the recently announced GPT-4o from OpenAI.

May 15, 20249 min read