dify/api
2023-06-13 14:49:40 +08:00
..
constants
controllers feat: optimize api language support (#344) 2023-06-13 10:06:49 +08:00
core feat: add WEAVIATE_BATCH_SIZE (#349) 2023-06-13 14:49:40 +08:00
docker
events
extensions
libs
migrations
models
services Fix: the bug that allows regular users to add unregistered users to the workspace. (#328) 2023-06-09 16:07:53 +08:00
tasks
tests
.dockerignore
.env.example feat: add WEAVIATE_BATCH_SIZE (#349) 2023-06-13 14:49:40 +08:00
app.py
commands.py
config.py feat: add WEAVIATE_BATCH_SIZE (#349) 2023-06-13 14:49:40 +08:00
Dockerfile
README.md
requirements.txt

Dify Backend API

Usage

  1. Start the docker-compose stack

    The backend require some middleware, including PostgreSQL, Redis, and Weaviate, which can be started together using docker-compose.

    cd ../docker
    docker-compose -f docker-compose.middleware.yaml up -d
    cd ../api
    
  2. Copy .env.example to .env

  3. Generate a SECRET_KEY in the .env file.

    openssl rand -base64 42
    
  4. Install dependencies

    pip install -r requirements.txt
    
  5. Run migrate

    Before the first launch, migrate the database to the latest version.

    flask db upgrade
    
  6. Start backend:

    flask run --host 0.0.0.0 --port=5001 --debug
    
  7. Setup your application by visiting http://localhost:5001/console/api/setup or other apis...

  8. If you need to debug local async processing, you can run celery -A app.celery worker, celery can do dataset importing and other async tasks.