I self-hosted an AI support bot with FastGPT + Docker — 3 gotchas that will break your install

Description and use

FastGPT installation on Linux with Docker fails due to missing MinIO image, incorrect CSV FAQ format, and lack of an embedding model.

Problem

Installing FastGPT v4.15 on a fresh Linux box with Docker fails due to missing MinIO image, incorrect CSV FAQ format, and lack of an embedding model.

Outcome

FastGPT runs on a 4 GB VPS with proper MinIO image, CSV FAQ format, and embedding model, avoiding common installation pitfalls.

Workflow

• Pull FastGPT Docker images
• Replace MinIO image with registry.cn-hangzhou.aliyuncs.com/fastgpt/minio
• Ensure CSV FAQ header is "q,a,indexes"
• Configure an embedding model (e.g., DeepSeek)
• Start FastGPT containers
• Verify knowledge‑base creation

Evidence

The MinIO image no longer pulls from Docker Hub.

Source

The header must be q,a,indexes, not q,a, or the import is rejected with a format error.

Source

You need an embedding model, not just a chat model. Without one, you can't even create a knowledge base.

Source