dify/api
2023-07-20 13:52:54 +08:00
..
constants
controllers Feat/clean vector dataset (#605) 2023-07-19 21:30:25 +08:00
core fix: azure openai embedding model name error (#612) 2023-07-20 13:52:54 +08:00
docker
events feat: claude api support (#572) 2023-07-17 00:14:19 +08:00
extensions feat: member invitation and activation (#535) 2023-07-14 11:19:26 +08:00
libs Feature/use jwt in web (#533) 2023-07-11 15:21:20 +08:00
migrations Feat/chat support voice input (#532) 2023-07-07 17:50:42 +08:00
models feat: member invitation and activation (#535) 2023-07-14 11:19:26 +08:00
services feat: claude api support (#572) 2023-07-17 00:14:19 +08:00
tasks index add to db when dataset updated (#588) 2023-07-18 15:02:33 +08:00
tests
.dockerignore
.env.example feat: member invitation and activation (#535) 2023-07-14 11:19:26 +08:00
app.py fix: account check in runtime (#569) 2023-07-15 23:58:15 +08:00
commands.py add clean unused dataset command (#609) 2023-07-20 11:08:28 +08:00
config.py Feat/clean vector dataset (#605) 2023-07-19 21:30:25 +08:00
Dockerfile feat: add bash before entrypoint.sh in Dockerfile (#592) 2023-07-18 16:22:34 +08:00
README.md
requirements.txt feat: claude api support (#572) 2023-07-17 00:14:19 +08:00

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
    

3.5 If you use annaconda, create a new environment and activate it

conda create --name dify python=3.10
conda activate dify
  1. Install dependencies

    pip install -r requirements.txt
    
  2. Run migrate

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

    flask db upgrade
    
  3. Start backend:

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

  5. 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.