Webinar
Accelerate AI Agents with Multimodal RAG powered by Friendli Endpoints and Milvus
Join the Webinar
Loading...
About this webinar:
AI agents are transforming industries, especially with recent vision-language models like Llama 3.2 Vision that enable AI agents to go beyond text-based understanding by integrating multimodal capabilities. Building such advanced AI agents can feel complex, but FriendliAI simplifies the process by offering end-to-end solutions, from creating your own custom models to deploying them in production. In this webinar, we’ll learn about the AI developer workflow from model fine-tuning to inference serving. We’ll also work through building a simple AI agent with advanced multimodal RAG capabilities using Friendli Serverless Endpoints and Milvus DB. This session is ideal for those looking to learn more about large-language model inference serving, start building AI agents with RAG capabilities, or explore multimodal RAG queries in greater depth
Topics covered:
- Fundamentals of large-language model fine-tuning and inference serving
- Key challenges in building AI agents
- Implementing advanced RAG with multimodal queries
- Step-by-step guide to building a simple AI agent complete with RAG and tool-calling
Meet the Speaker
Join the session for live Q&A with the speaker
Soomin Chun
Software Engineer, FriendliAI
Soomin Chun is a software engineer at FriendliAI, a generative AI inference platform company. She is dedicated to making AI more accessible by lowering both technical and financial barriers. During her time studying computer science at MIT, she discovered a love for building great machine learning software, and enjoys optimizing code from the algorithmic level down to hardware. Her diverse experience includes working as a founding engineer at an edtech startup, working on an ML Ads team at Meta, dabbling in quantitative finance, and conducting data visualization research at MIT CSAIL.