Table of Contents
Trainer AI is an LLM assistant agent with the goal of helping you workout more efficiently, and spend less time preparing workout sets, and analyzing data. You talk to it like a personal coach, and it records your efforts, and lays plans for you to reach your goals.
- You require Docker to be installed on your machine.
- You require an API key for OpenAI & LangSmith - OpenAI requires you to pay. Get a key from Cogito CTO if you're a member. - Langsmith doesn't require payment.
Create a .env file inside the folder 'AI_System' Add the api keys: OPENAI_API_KEY = "" LANGSMITH_API_KEY = ""
cd into the AI_system folder. Make sure there's a compose.yaml file there. Run this in your terminal (Granted you have Docker on your system)
docker compose up --build
The UI is accessible at https://localhost:3000
We're using 4 backend services. Mongodb server - Running on port 27017 - providing storage for chatlogs Timeseries analysis - Running a python flask server, using tensorflow LLM service - Running a python flask server, using langchain Main endpoint : Nodejs - Providing static file hosting for the user interface, as well as rerouting to other services via API calls.
1: CORS 2: Node is better suited for exposing directly to web.
Distributed under the MIT License. See LICENSE for more information.
Template by @JonRodtang for @CogitoNTNU