D2O

Use Dify on your favorite OpenAI client.

This project converts the Dify API to the OpenAI API format, giving you access to Dify's LLMs, knowledge base, tools, and workflows within your preferred OpenAI clients.

Features

• Convert Dify API into an OpenAI API
• Support streaming and blocking
• Support Chat, Completion, Agent and Workflow bots API on dify

Deployment

Zeabur

Vercel

Note: Vercel's serverless functions have a 10-second timeout limit.

Local Deployment

1. Set the environment variable in the .env file

DIFY_API_URL=https://api.dify.ai/v1

2. Install dependencies

3. Run the project

Usage

1. OpenAI Clients

2. Code

const response = await fetch('http://localhost:3000/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer YOUR_DFIY_API_KEY',
  },
  body: JSON.stringify({
    model: 'dify',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Hello, how are you?' },
    ],
  }),
});

const data = await response.json();
console.log(data);

Docker Deployment

• Build the image

docker build -t dify2openai:latest .

• Run the container

docker run -d -name dify2openai \
    --network bridge \
    -p 3000:3000 \
    -e DIFY_API_URL=https://api.dify.ai/v1 \
    -e BOT_TYPE=Chat \
    --restart always
    dify2openai:latest

• You can also use Docker Compose to build the image and run the container:

version: '3.5'
services:
  dify2openai:
    container_name: dify2openai
    build:
      context: .
      dockerfile: Dockerfile
    network_mode: bridge
    ports:
      - "3000:3000"
    restart: always
    environment: 
      - DIFY_API_URL=https://api.dify.ai/v1
      - BOT_TYPE=Chat

Docker Image Deployment

Prepared a Docker image for those who find it difficult to build.

• Run the containerb

docker run -d  \
    --network=bridge \
    -p 3000:3000 \
    -e DIFY_API_URL=https://api.dify.ai/v1 \
    -e BOT_TYPE=Chat \
    --restart always
    fatwang2/dify2openai:latest

• Run the container with docker-compose-image.yml

docker compose -f docker-compose-image.yml up -d

Please change the environment variables according to your needs.See Environment Variable for more information.

Environment Variable

This project provides some additional configuration items set with environment variables:

Roadmap

Coming Soon

• Image support
• Audio-to-text
• Text-to-audio
• Docker support

Available Now

• Workflow Bot
• Variables support
• Continuous dialogue
• Zeabur & Vercel deployment
• Streaming & Blocking
• Agent & Chat bots

Contact

Feel free to reach out for any questions or feedback

X
telegram

License

This project is licensed under the MIT License.