takatost 8fd75e6965 bump to 0.6.12-fix1 (#5743) преди 10 месеца
..
configs 8fd75e6965 bump to 0.6.12-fix1 (#5743) преди 10 месеца
constants 2e718b85e9 fix(api): language list (#5649) преди 10 месеца
controllers 906857b28a fix: couldn't log in or resetup after a failed setup (#5739) преди 10 месеца
core 0bf4817474 fix: _convert_prompt_message_to_dict parameters err (#5716) преди 10 месеца
docker e8b8f6c6dd Feat/fix ops trace (#5672) преди 10 месеца
events d160d1ed02 feat: support opensearch approximate k-NN (#5322) преди 10 месеца
extensions 3cc6093e4b feat: introduce pydantic-settings for config definition and validation (#5202) преди 10 месеца
fields 4c0a31d38b FR: #4048 - Add color customization to the chatbot (#4885) преди 10 месеца
libs dcb72e0067 chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652) преди 10 месеца
migrations e8b8f6c6dd Feat/fix ops trace (#5672) преди 10 месеца
models d30c13891b feat: add fix-app-site-missing command (#5711) преди 10 месеца
schedule 6c4e6bf1d6 Feat/dify rag (#2528) преди 1 година
services 906857b28a fix: couldn't log in or resetup after a failed setup (#5739) преди 10 месеца
tasks e8b8f6c6dd Feat/fix ops trace (#5672) преди 10 месеца
templates 3d92784bd4 fix: email template style (#1914) преди 1 година
tests dcb72e0067 chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652) преди 10 месеца
.dockerignore 27f0ae8416 build: support Poetry for depencencies tool in api's Dockerfile (#5105) преди 10 месеца
.env.example 964f0e1400 fix: Modify the incorrect configuration name for Google storage (#5595) преди 10 месеца
Dockerfile 73ce945d40 Feat/add json process tool (#5555) преди 10 месеца
README.md f9e4b4e74c Fix docker command (#5681) преди 10 месеца
app.py 017d2c804b fix: do not remove (#5706) преди 10 месеца
commands.py 8e5569f773 fix: fix-app-site-missing command (#5714) преди 10 месеца
poetry.lock 73ce945d40 Feat/add json process tool (#5555) преди 10 месеца
poetry.toml f62f71a81a build: initial support for poetry build tool (#4513) преди 10 месеца
pyproject.toml 73ce945d40 Feat/add json process tool (#5555) преди 10 месеца

README.md

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
   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
  1. Create environment.

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

  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
  1. Start Dify web service.
  2. Setup your application by visiting http://localhost:3000...
  3. 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,ops_trace

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
  1. 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