dify/api

Dify Backend API

Usage

[!IMPORTANT] In the v0.6.12 release, we deprecated pip as the package management tool for Dify API Backend service and replaced it with poetry.

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
   cp middleware.env.example middleware.env
   # change the profile to other vector database if you are not using weaviate
   docker compose -f docker-compose.middleware.yaml --profile weaviate -p dify up -d
   cd ../api

1. Copy .env.example to .env

   cp .env.example .env 

1. Generate a SECRET_KEY in the .env file.

bash for Linux

   sed -i "/^SECRET_KEY=/c\SECRET_KEY=$(openssl rand -base64 42)" .env

bash for Mac

   secret_key=$(openssl rand -base64 42)
   sed -i '' "/^SECRET_KEY=/c\\
   SECRET_KEY=${secret_key}" .env

1. Create environment.

Dify API service uses Poetry to manage dependencies. First, you need to add the poetry shell plugin, if you don’t have it already, in order to run in a virtual environment. [Note: Poetry shell is no longer a native command so you need to install the poetry plugin beforehand]

   poetry self add poetry-plugin-shell

Then, You can execute poetry shell to activate the environment.

1. Install dependencies

   poetry env use 3.12
   poetry install

1. Run migrate

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

   poetry run python -m flask db upgrade

1. Start backend

   poetry run python -m flask run --host 0.0.0.0 --port=5001 --debug

1. Start Dify web service.
2. Setup your application by visiting http://localhost:3000…
3. If you need to handle and debug the async tasks (e.g. dataset importing and documents indexing), please start the worker service.

   poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion

Testing

1. Install dependencies for both the backend and the test environment

   poetry install -C api --with dev

1. Run the tests locally with mocked system environment variables in tool.pytest_env section in pyproject.toml

   poetry run -P api bash dev/pytest/pytest_all_tests.sh