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

说明与用途

FastGPT v4.15 在 Linux 上使用 Docker 安装时会因三大问题中断：MinIO 镜像拉取失败、CSV FAQ 标题不完整以及缺少嵌入模型。解决方案包括使用镜像 MinIO、在 CSV 中添加第三列以及配置嵌入模型。建议至少 4 GB RAM 以保证稳定运行。

问题

Installing FastGPT v4.15 on a fresh Linux box with Docker fails due to three specific issues.

结果

FastGPT v4.15 was successfully deployed on a Linux VPS using Docker, with a functional MinIO mirror, correctly formatted FAQ CSV, and an embedding model, enabling full chatbot operation.

工作流

• Pull FastGPT Docker images from the official registry.
• Replace the MinIO image with the mirror image registry.cn-hangzhou.aliyuncs.com/fastgpt/minio to avoid Docker Hub pull errors.
• Prepare FAQ CSV with header "q,a,indexes"; ensure a third column exists to satisfy import requirements.
• Configure and launch an embedding model (e.g., DeepSeek) alongside the chat model to allow knowledge base creation.
• Bind FastGPT ports to 127.0.0.1 and set up a reverse proxy to avoid firewall issues.
• Allocate at least 4 GB RAM to the VPS to accommodate FastGPT’s memory usage (~2.1 GB idle).

证据

The MinIO image no longer pulls from Docker Hub. pull access denied for minio/minio — MinIO pulled their public images.

来源

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.

来源

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.

来源

Idle memory on my test box was ~2.1 GB, so 2 GB RAM VPSes won't cut it — plan for 4 GB.

来源