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

Description and use

Deploying FastGPT in Docker requires a mirrored MinIO image, a correctly formatted CSV FAQ, and an embedding model.

Problem

Installing FastGPT v4.15 on a fresh Linux box with Docker fails due to MinIO image pull error, CSV FAQ import format error, and missing embedding model.

Outcome

FastGPT deployment succeeded after addressing three critical issues: using a mirrored MinIO image, formatting CSV FAQ with a third column, and providing an embedding model.

Workflow

• Pull FastGPT Docker images
• Replace minio/minio with registry.cn-hangzhou.aliyuncs.com/fastgpt/minio
• Create CSV FAQ with header q,a,indexes
• Configure embedding model (e.g., DeepSeek) in FastGPT settings
• Bind FastGPT ports to 127.0.0.1 and set up reverse proxy
• Allocate at least 4 GB RAM for the VPS

Evidence

The MinIO image no longer pulls from Docker Hub.

Source

CSV FAQ import needs a third column. 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 (System not embedding model). DeepSeek alone isn't enough.

Source