
Deploy Dify (w/Plugins) 1.7.2
Deploy and Host Dify (w/Plugins) 1.7.2 with Railway
plugin-daemon
langgenius/dify-plugin-daemon:0.2.0-local
Just deployed
/app/storage
Storage
minio/minio:RELEASE.2025-02-28T09-55-16Z
Just deployed
/data
Redis
redis:6-alphine
Just deployed
/data
Sandbox
langgenius/dify-sandbox:0.2.12
Just deployed
/dependencies
Web
langgenius/dify-web:1.7.2
Just deployed
Worker
langgenius/dify-api:1.7.2
Just deployed
Postgres
postgres:15-alpine
Just deployed
/var/lib/postgresql/data
Api
langgenius/dify-api:1.7.2
Just deployed
Weaviate
semitechnologies/weaviate:1.19.0
Just deployed
/var/lib/weaviate
Storage provision
minio/mc:RELEASE.2025-02-21T16-00-46Z
Just deployed
Deploy and Host Dify on Railway
Dify is an open-source platform for building production-grade LLM apps. It blends agentic workflows, RAG pipelines, model management, observability, and a visual builder so teams can go from prototype to production fast, while keeping full control in self-hosted setups. (GitHub, Dify Docs)
About Hosting Dify
Hosting Dify on Railway is straightforward: provision a service from this template, set environment variables, and connect core services. Dify runs well via Docker Compose or Helm; for production you’ll typically wire up PostgreSQL, Redis, an object store (S3/Azure/OSS/GCS), and a vector database. Configure public URLs (console and API), enable HTTPS on a custom domain, and monitor logs as you scale resources. If you choose local file storage, mount a persistent Volume; otherwise point Dify to external object storage. This mirrors Dify’s self-hosting guidance and common K8s/Docker setups. (Dify Docs, Dify, Artifact Hub)
Common Use Cases
- Build agentic assistants and workflow-driven AI apps for support, ops, and internal tools. (GitHub)
- Create RAG pipelines and knowledge bases with vector search and observability. (Dify Docs)
- Extend with plugins and integrate multiple model providers securely via environment variables. (Dify Docs)
Dependencies for Dify Hosting
- Core services: PostgreSQL and Redis; File storage: local or S3-compatible backends (S3, Azure Blob, OSS, etc.). (Dify, Artifact Hub)
- Vector database: Weaviate, Qdrant, Milvus, pgvector and many others (configurable via
VECTOR_STORE
). (GitHub)
Deployment Dependencies
Dify self-hosted install: https://docs.dify.ai/getting-started/install-self-hosted
Docker Compose guide: https://docs.dify.ai/getting-started/install-self-hosted/docker-compose
Environment variables: https://docs.dify.ai/getting-started/install-self-hosted/environments
Helm chart (ArtifactHub): https://artifacthub.io/packages/helm/dify/dify
GitHub repo: https://github.com/langgenius/dify
Railway Variables: https://docs.railway.com/guides/variables
Railway Volumes: https://docs.railway.app/reference/volumes
Public Networking & Domains: https://docs.railway.app/guides/public-networking#custom-domains
Why Deploy Dify on Railway?
Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.
By deploying Dify on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.
Template Content
plugin-daemon
langgenius/dify-plugin-daemon:0.2.0-localRedis
redis:6-alphinePostgres
postgres:15-alpineWeaviate
semitechnologies/weaviate:1.19.0Storage provision
minio/mc:RELEASE.2025-02-21T16-00-46Z