Quickstart

Quickly start deploying a production-ready core infrastructure stack for your LLM applications

This guide will walk you through setting up a production-ready core infrastructure stack for your LLM Application with minimal effort. In just a few steps, you’ll be able to setup Universal API, AI routing, AI Gateway and Observablity to track and analyze the performance and usage of your Large Language Model (LLM) applications.

1

Deploy AI studio

Preparing docker environment

docker-compose.yml

  version: '3.8'

  services:
    postgres:
      image: postgres:13
      environment:
        - POSTGRES_DB=aistudio
        - POSTGRES_USER=aistudio
        - POSTGRES_HOST_AUTH_METHOD=trust
      volumes:
        - postgres:/var/lib/postgresql/data
      ports:
        - 5432:5432
      healthcheck:
        test: [ "CMD-SHELL", "pg_isready -U aistudio" ]
        interval: 30s
        timeout: 30s
        retries: 3
      restart: always

    redis:
      image: redis:7.2-alpine
      ports:
        - 6379:6379
      command: redis-server --save 20 1 --loglevel warning
      volumes:
        - redis:/data
      healthcheck:
        test: ["CMD", "redis-cli", "ping"]
        interval: 1s
        timeout: 3s
        retries: 30
      restart: always

    clickhouse:
      image: clickhouse/clickhouse-server:24.1.5
      volumes:
        - clickhouse:/var/lib/clickhouse
      ports:
        - 9000:9000
        - 8123:8123
      restart: always

    migrate:
      image: missingstudio/ai:dev
      command: ["migrate"]
      environment:
        - GATEWAY_POSTGRES_URL=postgres://aistudio@postgres:5432/aistudio?sslmode=disable
      depends_on:
        - postgres

    aistudio:
      image: missingstudio/ai:dev
      environment:
        - GATEWAY_APP_HOST=0.0.0.0
        - GATEWAY_APP_PORT=8080
        - GATEWAY_REDIS_HOST=redis
        - GATEWAY_REDIS_PORT=6379
        - GATEWAY_POSTGRES_URL=postgres://aistudio@postgres:5432/aistudio?sslmode=disable
      command: ["start"]
      ports:
        - 8080:8080
      depends_on:
        - redis
        - postgres
        - clickhouse
        - migrate

  volumes:
    redis: {}
    postgres: {}
    clickhouse: {}

Launch AI studio gateway server

  docker-compose up -d

2

Generate an API Key

With AI studio running, the next step is to generate an API key for resource access from AI studio

To generate your first API key, you can use the following command:

shell

curl --request POST \
  --url http://127.0.0.1:8080/api/v1/keys \
  --header 'Content-Type: application/json' \
  --data '{
    "name": "Base"
  }'

Save the API Key Remember to include this API key in the X-Ms-Api-Key header for all future API interactions

You’re geared up and ready to go! 🚀

Following these steps should have you AI studio up and running to power up LLMOps for your LLM appplications. If you have any questions or need support, reach out to our Discord Community.

---

Providers

Integrate your LLM Provider with AI studio

Connections

Connect to your existing Observablity Platform