Bowen Liang 27f0ae8416 build: support Poetry for depencencies tool in api's Dockerfile (#5105) před 1 rokem
..
.vscode f62f71a81a build: initial support for poetry build tool (#4513) před 1 rokem
configs 65d34ebb96 refactor: extract vdb configs into pydantic-setting based dify configs (#5426) před 1 rokem
constants 6ccde0452a feat: Added hindi translation i18n (#5240) před 1 rokem
controllers 92ddb410cd feat: option to hide workflow steps (#5436) před 1 rokem
core 91d38a535f fix: max_tokens of qwen-plus & qwen-plus-chat (#5480) před 1 rokem
docker 5f0ce5811a feat: add `flask upgrade-db` command for running db upgrade with redis lock (#5333) před 1 rokem
events d160d1ed02 feat: support opensearch approximate k-NN (#5322) před 1 rokem
extensions 3cc6093e4b feat: introduce pydantic-settings for config definition and validation (#5202) před 1 rokem
fields 92ddb410cd feat: option to hide workflow steps (#5436) před 1 rokem
libs 1336b844fd feat(api/auth): switch-to-stateful-authentication (#5438) před 1 rokem
migrations 92ddb410cd feat: option to hide workflow steps (#5436) před 1 rokem
models 92ddb410cd feat: option to hide workflow steps (#5436) před 1 rokem
schedule 6c4e6bf1d6 Feat/dify rag (#2528) před 1 rokem
services 1336b844fd feat(api/auth): switch-to-stateful-authentication (#5438) před 1 rokem
tasks ba5f8afaa8 Feat/firecrawl data source (#5232) před 1 rokem
templates 3d92784bd4 fix: email template style (#1914) před 1 rokem
tests 142dc0afd7 refactor: Remove unused code in large_language_model.py (#5433) před 1 rokem
.dockerignore 27f0ae8416 build: support Poetry for depencencies tool in api's Dockerfile (#5105) před 1 rokem
.env.example 147a39b984 feat: support tencent cos storage (#5297) před 1 rokem
Dockerfile 27f0ae8416 build: support Poetry for depencencies tool in api's Dockerfile (#5105) před 1 rokem
README.md bdf3ea4369 docs(api/README): Remove unnecessary `=` (#5380) před 1 rokem
app.py 1336b844fd feat(api/auth): switch-to-stateful-authentication (#5438) před 1 rokem
commands.py d160d1ed02 feat: support opensearch approximate k-NN (#5322) před 1 rokem
config.py 65d34ebb96 refactor: extract vdb configs into pydantic-setting based dify configs (#5426) před 1 rokem
poetry.lock aed56b1a8f fix: Revert "feat: initial support for Milvus 2.4.x (#3795)" downgrading to 2.3.x for Linux arm64 installation failure (#5414) před 1 rokem
poetry.toml f62f71a81a build: initial support for poetry build tool (#4513) před 1 rokem
pyproject.toml aed56b1a8f fix: Revert "feat: initial support for Milvus 2.4.x (#3795)" downgrading to 2.3.x for Linux arm64 installation failure (#5414) před 1 rokem
requirements-dev.txt 23498883d4 chore: skip explicit installing jinja2 as testing dependency (#4845) před 1 rokem
requirements.txt aed56b1a8f fix: Revert "feat: initial support for Milvus 2.4.x (#3795)" downgrading to 2.3.x for Linux arm64 installation failure (#5414) před 1 rokem

README.md

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 -p dify up -d
   cd ../api
  1. Copy .env.example to .env
  2. Generate a SECRET_KEY in the .env file.

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

Dify API service uses Poetry to manage dependencies. You can execute poetry shell to activate the environment.

Using pip can be found below.

  1. Install dependencies

    poetry env use 3.10
    poetry install
    

In case of contributors missing to update dependencies for pyproject.toml, you can perform the following shell instead.

   poetry shell                                               # activate current environment
   poetry add $(cat requirements.txt)           # install dependencies of production and update pyproject.toml
   poetry add $(cat requirements-dev.txt) --group dev    # install dependencies of development and update pyproject.toml
  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
    
  2. Start Dify web service.

  3. Setup your application by visiting http://localhost:3000...

  4. If you need to debug local async processing, please start the worker service.

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

The started celery app handles the async tasks, e.g. dataset importing and documents indexing.

Testing

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

    poetry install --with dev
    
  2. Run the tests locally with mocked system environment variables in tool.pytest_env section in pyproject.toml

    cd ../
    poetry run -C api bash dev/pytest/pytest_all_tests.sh
    

Usage with pip

[!NOTE]
In the next version, we will deprecate pip as the primary package management tool for dify api service, currently Poetry and pip coexist.

  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 -p dify up -d
   cd ../api
  1. Copy .env.example to .env
  2. Generate a SECRET_KEY in the .env file.

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

If you use Anaconda, 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
  1. Start backend:

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

  3. If you need to debug local async processing, please start the worker service.

    celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail
    

The started celery app handles the async tasks, e.g. dataset importing and documents indexing.