Langflow
Langflow is a visual framework for building multi-agent and RAG applications with a Python-based drag-and-drop flow builder. It provides a rich library of components for connecting to LLMs (OpenAI, Anthropic, Google, Ollama), vector stores, document loaders, embeddings, and custom Python code. This stack deploys Langflow backed by PostgreSQL 16 for reliable storage of flows, credentials, and conversation history. Langflow supports API deployment of your flows, a built-in playground for testing, custom component development, and integration with LangChain, LangGraph, and CrewAI. The visual editor makes it easy to prototype complex AI pipelines, while the generated Python code can be exported for production deployment. After deployment, access the web UI on port 7860 to start building your AI flows. The first user to sign up becomes the admin.
Enthaltene Services
langflow
langflowai/langflow:latest
Umgebungsvariablen:
postgres
postgres:16-alpine
Umgebungsvariablen:
Generiertes YAML
# Generated by ComposeHub (composehub.dev)
name: langflow
services:
langflow:
image: langflowai/langflow:latest
restart: always
ports:
- 7860:7860
volumes:
- langflow_data:/app/langflow
environment:
LANGFLOW_DATABASE_URL: postgresql://${POSTGRES_USER:-langflow}:${POSTGRES_PASSWORD:-changeme}@postgres:5432/${POSTGRES_DB:-langflow}
LANGFLOW_CONFIG_DIR: /app/langflow
LANGFLOW_AUTO_LOGIN: ${LANGFLOW_AUTO_LOGIN:-false}
LANGFLOW_SUPERUSER: ${LANGFLOW_SUPERUSER:-admin}
LANGFLOW_SUPERUSER_PASSWORD: ${LANGFLOW_SUPERUSER_PASSWORD:-changeme}
LANGFLOW_LOG_LEVEL: ${LANGFLOW_LOG_LEVEL:-info}
LANGFLOW_WORKERS: ${LANGFLOW_WORKERS:-1}
networks:
- langflow
depends_on:
postgres:
condition: service_healthy
healthcheck:
test:
- CMD-SHELL
- curl -f http://localhost:7860/api/v1/version || exit 1
interval: 30s
timeout: 10s
retries: 5
start_period: 90s
deploy:
resources:
limits:
cpus: "2.00"
memory: 2048M
reservations:
cpus: "0.50"
memory: 512M
labels:
com.composehub.description: Langflow visual AI agent and RAG pipeline builder
postgres:
image: postgres:16-alpine
restart: always
volumes:
- langflow_db:/var/lib/postgresql/data
environment:
POSTGRES_DB: ${POSTGRES_DB:-langflow}
POSTGRES_USER: ${POSTGRES_USER:-langflow}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-changeme}
networks:
- langflow
healthcheck:
test:
- CMD-SHELL
- pg_isready -U ${POSTGRES_USER:-langflow} -d ${POSTGRES_DB:-langflow}
interval: 5s
timeout: 5s
retries: 10
start_period: 30s
deploy:
resources:
limits:
cpus: "1.00"
memory: 512M
reservations:
cpus: "0.25"
memory: 128M
labels:
com.composehub.description: PostgreSQL 16 database for Langflow
networks:
langflow:
driver: bridge
volumes:
langflow_data:
driver: local
langflow_db:
driver: local
Kurzinfo
- Services
- 2
- Netzwerke
- 1
- Volumes
- 2
Wann verwenden
Dieses Template ist ideal für die Einrichtung einer langflow Umgebung. Alle Services sind mit Healthchecks, Ressourcenlimits und sinnvollen Standardwerten vorkonfiguriert. Passen Sie die Umgebungsvariablen an, bevor Sie in Produktion gehen.
Tipps
- Ändern Sie alle Standardpasswörter vor dem Deployment
- Überprüfen Sie die Ressourcenlimits für Ihre Hardware
- Fügen Sie einen Reverse Proxy für HTTPS in Produktion hinzu
- Konfigurieren Sie Backup-Strategien für Daten-Volumes