Рет қаралды 2,405
Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models. In this video we'll look at how we can get started with Amazon Bedrock and Supabase Vector in Python using the Amazon Titan multimodal model and the vecs Python client.
- Find the code: supabase.link/edgy-bedrock-code
- Get started with Amazon Bedrock: supabase.link/aws-bedrock
Presented by Thor Schaeff (@thorwebdev go.thor.bio/x)
CHAPTERS:
00:00 Intro
00:12 AI in Edge Functions recap
00:36 Using LLMs within Edge Functions
01:55 Amazon Bedrock JavaScript SDK
02:09 Available models within Amazon Bedrock
02:52 Import npm modules in Deno
03:26 Load Bedrock Client configuration files
04:26 Initialise Bedrock JavaScript Client
05:07 Enable Models in the AWS Console
05:40 Enable Amazon Titan Image Generator G1
06:19 Construct the Model Invoke Command
07:30 Handle the Bedrock API response
08:15 Upload the image to Supabase Storage
08:45 Decode base64 image to arraybuffer
09:47 Test out image generation locally
10:35 Serve Supabase Edge Functions locally
💻 Videos to watch next:
▶ • Why you should use Edg...
▶ • AI Image Search with A...
▶ • Llama 3 with Vercel AI
👇 Learn more about Supabase 👇
🕸 Website: supabase.com/
🏁 Get started: app.supabase.com/
📄 Docs: supabase.com/docs
🔔 Subscribe for more tutorials and feature updates from Supabase: / @supabase
📱 Connect with Us:
🐙 Github: www.github.com/supabase
💬 Discord: www.discord.supabase.com/
🐦 Twitter: / supabase
▶ Instagram (follow for memes): / supabasecom
ABOUT SUPABASE:
Supabase is the open source Firebase alternative. Supabase provides a full Postgres database for every project with pgvector, backups, realtime, and more. Add and manage email and password, passwordless, OAuth, and mobile logins to your project through a suite of identity providers and APIs.
Build in a weekend, scale to millions.
#Supabase #AppDevelopment #DeveloperTools #ai #edge