Christy Bergman
Zilliz
San Francisco, California, United States
Actions
Christy Bergman is a passionate AI Developer Advocate. She previously worked in vector databases, 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.
Area of Expertise
Topics
Milvus Vector Database: Unlocking the Future of Open Source Vector Databases
In this invited, conference talk, Charles will describe the factors that drove him to create Milvus, the world's most popular open-source vector database (measured in github stars). He'll give some background on how the use cases for vector data are different from traditional databases, and how those use cases drove him to design Milvus, an open-source project for unstructured data. The architecture uses "logs as data", is "shared-something", at a high level with four layers that are independent in terms of scalability and disaster recovery.
Fine-tune RAG embeddings with HuggingFace, PyTorch, and Milvus
You’ve heard good data matters in Machine Learning, but does it matter for Generative AI applications? Corporate data often differs significantly from the general Internet data used to train most foundation models. Join me for a demo building a customizable RAG (Retrieval Augmented Generation) stack using OSS HuggingFace embedding models, fine tuning using PyTorch, retrieval using Milvus vector database, evaluation using Ragas, and optional Zilliz cloud and OpenAI.
Customizable RAG workflows with your own Data
Ground your chatbot with your internal knowledge base, leveraging fully open-source Milvus vector database, LangChain, Ragas, and HuggingFace models; utilizing OpenAI only when you want it.
Pain Points and Lessons Learned building a conversational AI Chat App on GitHub docs pages
In my talk, I'll dive into the world of semantic search using vector embeddings from modern LLMs. I'll lightly cover the three primary classes of transformer architectures and their role in Retrieval Augmented Generation (RAG). Then I'll give a quick demo showcasing how to utilize the open-source Milvus vector database to store, index, and search these embeddings as part of a live product demonstration. The product is live at https://osschat.io/.
Unlocking the Power of Unstructured Data Queries with Milvus Vector Database
AI applications are proliferating with more new apps every day, spanning AI dating, fitness, investing, medicine, mental health, PII-sensitive internal document searches, and viral video shorts generation. One thing all of these new AI-generated applications have in common is unstructured data - web pages, medical records, psychology notes, PDF forms, images, or videos. In this context, it is becoming increasingly important to be able to efficiently utilize vector databases for unstructured data querying.
In this lightning talk, I will give a quick overview of key concepts essential for utilizing vector databases and vector search. I’ll cover unstructured data embeddings, vector indexing, search algorithms, and distance measures. Listen to this talk to discover best practices for querying vector databases using open-source Milvus!
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top