AI Workshop (SF): Self-hosted LLMs Agent and Build Scalable Workflows for LLMs

May 15, 05:00 PM PDT
  • San Francisco (Microsoft SF, 555 California Street, Suite 200 San...) AICamp
  • 218 RSVP

Welcome to the AI workshop in San Francisco. Join us for hands-on workshop on AI, GenAI, LLMs and machine learning, food/drink, networking with speakers and fellow developers.

Workshop 1: Self-hosted LLM agent on your own laptop or edge device
Speaker/Instructor: Michael Yuan (Creator of LlamaEdge), Sydney Lai (GaiaNet)
Outline: In this workshop, we will show you how to build a complete AI agent service using an open-source LLM and a personal knowledge base. We will use the open-source WasmEdge + Rust stack for LLM inference, which is very fast and lightweight without complex Python dependencies. As Elon Musk once tweeted: “AGI will be built in Rust. Let that sink in”. It is cross-platform and achieves native performance on a variety of popular OSes, CPUs, and GPUs, including personal and edge devices. No prior Rust knowledge is needed.
You will walk out of this workshop with your personal agent running on your own laptop. We will explore topics such as how to select an open-source LLM, how to finetune the model for your needs, how to build a RAG vector database from proprietary knowledge, how to customize prompts, and how to handle LLM responses for further steps such as function calling and tool use.

Workshop 2: Build Scalable Workflows for LLMs
Speaker/Instructor: Sage Elliott (Union)
Outline: Training today's complex AI models requires combining various steps into an interconnected workflow. Modern MLOps tooling helps you scale your AI training by orchestrating these workflows. Great tooling provides a reliable framework for your machine learning operations by streamlining processes, increasing efficiency, and adding reproducibility.
This workshop will equip you with the skills to harness these benefits effectively and show you how to build AI workflows for LLMs using, Hugging Face, and Weights and Biases. This workshop will cover:
* Fine-tune a Hugging Face LLM model.
* Build a scalable workflow using (powered by Flyte).
* Integrate with Weights & Biases for experiment management.
What you'll need to follow along: A free account (Link provided at workshop), a free Weights & Biases account for logging metrics, a GitHub account, and a google account to follow along in Colab.

Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

Microsoft SF, 555 California Street, Suite 200 San Francisco, CA 94104
Note: Building security requires first name, last name, and email address. Registrants will receive a QR Code from Microsoft Corporation at VORNADO sent via two days before the event. Check your spam folder.
By registering for this in person event you are agreeing to have your e-mail shared with building security for building access. Your privacy is important to us. This privacy statement explains the personal data Microsoft processes, how Microsoft processes it, and for what purposes. You can view our full privacy statement here.

We are actively seeking sponsors to support AI developers community.  Whether it is by offering venue spaces, providing food, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 30,000+ AI developers in San Francisco Bay Area or 350K+ worldwide.

Community on Slack/Discord
- Event chat: chat and connect with speakers and attendees
- Sharing blogs, events, job openings, projects collaborations
Join Slack (search and join the #sanfrancisco channel) | Join Discord

Michael Yuan, Sydney Lai, Sage Elliott

The event ended.
Watch Recording
*Recordings hosted on Youtube, click the link will open the Youtube page.
Contact Organizer