
Sponsored by: NVIDIA
Gapi: the Integration Engine for Generative AI
Parts list
Qty | Product | Part number | |
---|---|---|---|
1 | OStream GenRunner Node Single Board Computer for use with Generative AI | 267-4907 | |
1 | NVIDIA Jetson AGX Orin 64GB Development Kit | 253-9662 | |
1 | NVIDIA Jetson Orin Nano Developer Kit | 264-7384 | |
1 | OStream ROCK 5 AIO Development Kit for use with Edge AI | 267-4908 | |
The project's goal is to accelerate the speed of creating pilots and demos of Jetson AI Lab achievements into real world environments.
"On Device" generative AI is more private, can be more responsive and will cost less than an all cloud-based solution. The idea is to simplify how all the great GenAI achievements can be leveraged by every day technocrats. We've bundled a ton of the leading models and allow you to connect it to real-world systems like Slack (IM), Twilio (SMS), SendGrid (Email), ticketing systems etc. etc.
It was recently adopted by NVIDIA's Jetson AI Lab
- Gapi Hosted Demo (You will need to create an account)
- Gapi is an integration engine designed for non-AI experts. Leverage the leading, open GenAI models you hear about everyday.
- Workflows with low code UI including dozens of open integrations and customizable clients for mobile web and desktop.
- Micro service framework for wrapping Jetson containers (Ollama, Whisper, Piper TTS, etc. are done, with more coming). Or wrap your own models/code and integrate it into Workflows.
- Real-time, hybrid, binary+json messaging smoothens intra-service calls and reduced latency.
- A fast path to proving generative AI value to stakeholders in their actual environment.
Workflows
Workflows visually connect the execution and flow of data between Nodes.
A Transaction (or single firing) has "Rolling Input" data it accumulates as Node to Node steps each talk to Micro Services and APIs. All Nodes enjoy variables and flow control using familiar json and javascript concepts.
Each Node can append or reference the rolling data in the Transaction while making decisions along the way.
Watch live Transactions as they start from clients, webhooks and published messages from Micro Services with visual feedback and debugging.
Comments