Flowise ist ein Open-Source Visual Node Editor für LLM-Anwendungen. Mit Drag-and-Drop-Interface lassen sich komplexe Workflows schnell aufbauen.

Installation

docker run -d \
  -p 3000:3000 \
  -v flowise:/root/.flowise \
  flowiseai/flowise:latest

Zugang: http://localhost:3000

Core Nodes

LLM Nodes

  • OpenAI, Claude, Ollama, Local LLM

Memory Nodes

  • Chat History, Buffer Memory

Vector Store Nodes

  • Weaviate, Qdrant, Pinecone, ChromaDB

Tool Nodes

  • Google Search, Calculator, Database Query

Workflow Beispiel

User Input
  ↓
Chat Memory Retrieve
  ↓
Vector Store Similarity Search
  ↓
LLM Process
  ↓
Output

Integration

REST API

curl -X POST http://localhost:3000/api/v1/prediction/workflow-id \
  -H "Content-Type: application/json" \
  -d '{"question": "Hello"}'

Self-Hosting

services:
  flowise:
    image: flowiseai/flowise:latest
    ports:
      - "3000:3000"
    environment:
      FLOWISE_USERNAME: admin
      FLOWISE_PASSWORD: secure
      DATABASE_PATH: /root/.flowise/flowise.db
    volumes:
      - flowise-data:/root/.flowise

Quellen