Flowise
Flowise is an open-source, low-code tool for building customized LLM orchestration flows and AI agents using a visual drag-and-drop interface. Built on top of LangChain and LlamaIndex, it allows you to create chatbots, RAG pipelines, multi-agent systems, and complex AI workflows without writing code. Flowise supports connections to OpenAI, Anthropic, Google, Ollama, HuggingFace, and many other LLM providers, as well as vector stores like Pinecone, Weaviate, Chroma, and PostgreSQL with pgvector. It provides built-in chat interface embedding, API endpoints for integration, conversation memory, document loaders, and credential management. All chatflows, credentials, and data are persisted in a named volume using SQLite by default. After deployment, access the visual builder on port 3001 to start creating your AI workflows by dragging and connecting nodes.
Services Inclus
flowise
flowiseai/flowise:latest
Variables d'Environnement :
YAML Généré
# Generated by ComposeHub (composehub.dev)
name: flowise
services:
flowise:
image: flowiseai/flowise:latest
restart: always
ports:
- 3001:3000
volumes:
- flowise_data:/root/.flowise
environment:
PORT: "3000"
FLOWISE_USERNAME: ${FLOWISE_USERNAME:-}
FLOWISE_PASSWORD: ${FLOWISE_PASSWORD:-}
APIKEY_PATH: /root/.flowise
SECRETKEY_PATH: /root/.flowise
LOG_PATH: /root/.flowise/logs
LOG_LEVEL: ${LOG_LEVEL:-info}
DATABASE_PATH: /root/.flowise
TOOL_FUNCTION_BUILTIN_DEP: ${TOOL_FUNCTION_BUILTIN_DEP:-}
TOOL_FUNCTION_EXTERNAL_DEP: ${TOOL_FUNCTION_EXTERNAL_DEP:-}
networks:
- flowise
healthcheck:
test:
- CMD-SHELL
- wget --no-verbose --tries=1 --spider http://localhost:3000 || exit 1
interval: 30s
timeout: 10s
retries: 5
start_period: 30s
deploy:
resources:
limits:
cpus: "2.00"
memory: 2048M
reservations:
cpus: "0.25"
memory: 256M
labels:
com.composehub.description: Flowise AI workflow builder with drag-and-drop interface
networks:
flowise:
driver: bridge
volumes:
flowise_data:
driver: local
Informations Rapides
- Services
- 1
- Réseaux
- 1
- Volumes
- 1
Quand l'Utiliser
Ce modèle est idéal pour mettre en place un environnement flowise Tous les services sont préconfigurés avec des healthchecks, des limites de ressources et des valeurs par défaut raisonnables. Personnalisez les variables d'environnement avant de déployer en production.
Conseils
- Changez tous les mots de passe par défaut avant le déploiement
- Vérifiez les limites de ressources pour votre matériel
- Ajoutez un reverse proxy pour le HTTPS en production
- Configurez des stratégies de sauvegarde pour les volumes de données