Cover Image for [In-person] LLM Stack Hackathon // SF #TechWeek

[In-person] LLM Stack Hackathon // SF #TechWeek

Register to See Address
San Francisco, California
Past Event
Welcome! To join the event, please register below.
About Event

Join us on June 3rd, 2023 in San Francisco for a 12-hour Large Language Model (LLM) Stack Hackathon with the where you can use LLMs to solve a Question-Answering challenge using a large corpus of community Slack and Videos!

💪 Collaborate with and learn from other MLOps practitioners who work in AI, ML, and Data Science roles in the industry.

🤝 This event is open to anyone who is interested in building an LLM Stack and not limited to existing members. You’re free to join though 🙌.

💻 Get access to tools and credits from Redis and Relevance AI to build end-to-end solutions.

💰 Chance to win cash prizes!

♥️ As a community event, this hackathon is organized for participants to work and learn together with like-minded individuals. So, bring your authentic self, be kind, respectful, and have fun building something awesome together.

📣 Selected teams will be invited to share their solutions with an audience of over 4000 global attendees as a lightning talk at the LLM in Production #2 conference taking place on June 15th and 16th 2023!!

🦾 The Challenge: is a 17K+ member community, primarily online in a thriving slack channel and through virtual and in-person events. There is a lot of tribal knowledge in the community where experts answer questions from other MLOps practitioners both in Slack as well as via in-person meetups and online videos. We want you to build an LLM-powered application (Web/Mobile/Slack) to answer MLOps and other ML/DS/AI questions that community members may have using the historical knowledge in Slack, videos, etc. For example - you may implement the solution as a chatbot that uses embeddings and a vector datastore to generate the answers.

🔨 What you’ll be building:

We’d love to see your creativity in designing your LLM Stack and showcase how useful your app can be to help MLOps practitioners learn from the experience of others. We encourage participants to discover, experiment, and build high-impact solutions using the dataset during this hackathon, and improve their skills to build powerful LLM Stacks! That being said, here are a few dimensions you could consider when creating your LLM Stack solution:

  • Correctness of the answers (and explainability/citations)

  • LLM chains

  • Data pipelines

  • User Interfaces

  • System Design tradeoffs

  • Security

  • Bonus points for transparently sharing your solution so that the community can learn (e.g. OSS, documentation, etc.)

  • etc.

💽 The Data:

  • Slack data from public MLOps Community channels

  • Transcripts of videos from Youtube page

  • Other data from the communities’ past events, blogs, etc. (make sure you share the sources used)

  • Starter Kit

🗺️ Location:

  • SoMa, San Francisco (exact location will be shared with participants on sign-up)

💫 Why we’re having this hackathon: As part of enhancing our community, we are looking to provide the opportunity to our members and other participants to learn to improve their knowledge on building LLM-powered solutions to a common problem of knowledge discovery by designing and building an app that uses LLMs to answer community member questions, just like the human experts.

Here’s everything you need to know to get started:

👷 You can work individually or in groups of up to 4 people

🔨 You can use Redis, RelevanceAI, or any other tools to build your solutions.

💽 The data provided for the purposes of this hackathon is under the CC-BY-NC 4.0 license, intended for non-commercial use only.

📅 Projects should be started at the event kick-off to maintain fairness across projects

🔢 Credits: To be announced.

💸 Cash prizes: To be announced.

💫 Looking for creative solutions in the LLM App Stack (UI, System Design, Microservices) that solve real-world problems using emergent LLM technologies.

About our Sponsors

Redis, appreciated for its adaptable in-memory database and diverse data structures, is excited to fuel creativity at the frontier of generative AI. At the LLM Stack Hackathon, participants will have the opportunity to explore Redis as a low-latency vector database for streamlined context retrieval or LLM caching. Sponsoring this event, Redis is wholeheartedly championing the advancement of solutions that will invigorate and empower the vibrant MLOps Community.

Relevance AI, appreciated by developers and industry leaders for its managed LLM chains API that allows developers to quickly build and deploy secure and scalable chains. Relevance AI is excited to help provide the capability to help everyone overcome limitations that comes out of the box with LLMs, like hallucination, quality control and more via chaining. At the LLM Stack Hackathon, participants will have the opportunity to explore Relevance as a chaining platform to connect various pieces like vector database, unstructured data transformations, guardrails and more. Relevance can also be used by low-code users via our notebook experience. Sponsoring this event, Relevance is looking forward to see what the amazing MLOps community will invent and build!

Essence VC, an early-stage venture fund focused on developer and data infrastructure companies, backing companies like MotherDuck, Modal,, and others. Essence will love to highlight winners and fun projects out of this hackathon on our social channels! 

Disclaimers: Any of the details of this event are subject to change at the discretion of the organizer. The organizer of this event is not responsible for any damages, injuries, or legal consequences resulting from your attendance or behavior during the event. We reserve the right to update or modify this disclaimer at any time without prior notice. Your continued attendance at the event following any changes to the disclaimer constitutes your acceptance of those changes.

This event is a part of #TechWeek - a week of events hosted by VCs and startups to bring together the tech ecosystem.