Quick Start

Run the full ollmo stack locally in 5 minutes.

Prerequisites

• Docker + Docker Compose
• Go 1.26+
• Node.js 20+
• Make (optional, for convenience targets)

1. Clone & configure

git clone https://github.com/ollmo-go/ollmo.git
cd ollmo
cp .env.example .env

2. Start infrastructure

make up

Starts MySQL, Redis, MinIO, Milvus, and the Asynqmon dashboard:

Service	URL	Credentials
MySQL	localhost:3306	ollmo / ollmo_dev_pwd
MinIO Console	http://localhost:9001	minioadmin / minioadmin
Milvus	localhost:19530	—
Asynqmon UI	http://localhost:8081	—

3. Run database migrations

make migrate

4. Start backend (API + worker)

# Terminal 1: API server
make server

# Terminal 2: Asynq worker (document parsing & embedding)
make worker

5. Start frontend

make web          # http://localhost:3001

Open http://localhost:3001 and register an account to get started.

Full stack via Docker

make up-full      # Builds & starts everything (infra + server + worker + web)

First Steps

1. Configure models — Settings → Model Settings: add chat / embedding / rerank models and set defaults
2. Create a knowledge base — Embedding model is optional; pure-chat KBs need none
3. Upload documents — Drag & drop, wait for parsing and embedding to finish
4. Start chatting — Ask questions; answers come with source citations

:::tip Auto-Memory Once a conversation reaches 10 messages, ollmo automatically summarizes it in the background; new conversations get these summaries injected, carrying context across sessions. Can be disabled in System Settings. :::