What We'll Build

In this workshop, we will create a production-ready MVP for securely chatting with your documents. Here’s a peek of the features we’ll build:

1.** Interactive Chat Interface:** Interact your documentation, leveraging the capabilities of OpenAI’s GPT models and retrieval augmented generation (RAG). 2. Login With <3rd Party>: Integrate one-click 3rd party login with any of our 18 auth providers and user/password. 3. Document Storage: Securely upload, store, and retrieve user uploaded documents. (Optionally) BYO bucket. 4. REST API: Expose a flexible REST API that we’ll consume to build the interactive front-end. 5. Row-level Security: Secure all of your user data user data with production-ready row-level security. 6. In 2023 the question on many entrepreneurs’ minds is: how do I rapidly build an AI application while maintaining control over my tech stack? The answer lies within our workshop, where we unveil Supabase’s role in this process - a tool perfectly aligned with the mantra “Build in a weekend, scale to millions.”

In this workshop, we delve into the intricacies of Supabase, showcasing how to store and query embeddings within Postgres using pgvector. We will explore its speed advantage, taking full benefit of pgvector’s latest updates, including HNSW indexes that promise up to 5x faster performance than previous strategies.

Building with Supabase is akin to a rapid construction process - authentication is free, you get a built-in REST API, integrated object/file storage, and more. The best part? It’s all open source.

Retrieval Augmented Generation (RAG)

Our workshop’s highlight is an immersion into retrieval augmented generation (RAG) that combines the industry’s top embedding models (open source) with OpenAI’s GPT models. We will guide you on enhancing the interaction by adding memory to these conversations.

By the end of this workshop, you’ll be armed with the knowledge to transform your mundane file storage into dynamic conversation handlers. More importantly, this hands-on experience will equip you with tools to rapidly develop AI applications that are ready to scale, embracing the ethos of “fast development, exponential growth.” Join us and influence the next generation of AI applications, where speed, control, and scalability are the keystones to your next significant breakthrough.