You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
twwu 386614951f Merge branch 'main' into feat/rag-2 hace 2 meses
..
.idea fix nltk averaged_perceptron_tagger download and fix score limit is none (#7582) hace 1 año
.vscode feat/enhance the multi-modal support (#8818) hace 1 año
configs Merge branch 'main' into feat/rag-2 hace 2 meses
constants fix video and audio extension, keep consistent with the web page. (#23287) hace 3 meses
contexts Merge branch 'main' into feat/r2 hace 5 meses
controllers Merge branch 'main' into feat/rag-2 hace 2 meses
core Merge branch 'main' into feat/rag-2 hace 2 meses
docker feat: Add an asynchronous repository to improve workflow performance (#20050) hace 2 meses
events Update mypy.ini (#24014) hace 2 meses
extensions Merge branch 'main' into feat/rag-2 hace 2 meses
factories Merge branch 'main' into feat/rag-2 hace 2 meses
fields merge main hace 2 meses
libs fix: resolve Windows path separator issue in Huawei OBS operations (#23475) hace 2 meses
migrations Merge branch 'main' into feat/rag-2 hace 2 meses
models Merge branch 'main' into feat/rag-2 hace 2 meses
repositories chore: remove debug log statements from DifyAPIRepositoryFactory (#23734) hace 2 meses
schedule fix: optimize dataset cleanup task (#23828) hace 2 meses
services Merge branch 'main' into feat/rag-2 hace 2 meses
tasks Merge branch 'main' into feat/rag-2 hace 2 meses
templates Feat: add notification for change email completed (#22812) hace 3 meses
tests Merge branch 'main' into feat/rag-2 hace 2 meses
.dockerignore Enhance Code Consistency Across Repository with `.editorconfig` (#19023) hace 6 meses
.env.example feat: add Redis SSL/TLS certificate authentication support (#23624) hace 2 meses
.ruff.toml make logging not use f-str, change others to f-str (#22882) hace 3 meses
Dockerfile chore: update uv to 0.8.9 (#23833) hace 2 meses
README.md feat: Add an asynchronous repository to improve workflow performance (#20050) hace 2 meses
app.py r2 hace 5 meses
app_factory.py feat: integrate flask-orjson for improved JSON serialization performance (#23935) hace 2 meses
commands.py Merge branch 'main' into feat/rag-2 hace 2 meses
dify_app.py refactor: assembling the app features in modular way (#9129) hace 11 meses
installed_plugins.jsonl r2 hace 6 meses
mypy.ini Update mypy.ini (#24014) hace 2 meses
pyproject.toml feat: integrate flask-orjson for improved JSON serialization performance (#23935) hace 2 meses
pytest.ini Refactor/remove db from cycle manager (#20455) hace 5 meses
uv.lock feat: integrate flask-orjson for improved JSON serialization performance (#23935) hace 2 meses

README.md

Dify Backend API

Usage

[!IMPORTANT]

In the v1.3.0 release, poetry has been replaced with uv as the package manager for Dify API backend service.

  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 UV to manage dependencies. First, you need to add the uv package manager, if you don’t have it already.

   pip install uv
   # Or on macOS
   brew install uv
  1. Install dependencies
   uv sync --dev
  1. Run migrate

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

   uv run flask db upgrade
  1. Start backend
   uv run 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.
   uv run celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion,plugin,workflow_storage

Addition, if you want to debug the celery scheduled tasks, you can use the following command in another terminal:

   uv run celery -A app.celery beat 

Testing

  1. Install dependencies for both the backend and the test environment
   uv sync --dev
  1. Run the tests locally with mocked system environment variables in tool.pytest_env section in pyproject.toml
   uv run -P api bash dev/pytest/pytest_all_tests.sh