kurokobo ef6034abfd fix: allow the name and icon of the web app to be set independently of that of the bot itself (#5225) vor 1 Jahr
..
.vscode f62f71a81a build: initial support for poetry build tool (#4513) vor 1 Jahr
constants b399e8a359 fixed a typo and grammar error in sampled app (#5061) vor 1 Jahr
controllers ef6034abfd fix: allow the name and icon of the web app to be set independently of that of the bot itself (#5225) vor 1 Jahr
core 8d1386df0f feat(Tools): Add Feishu multi-dimensional table operation function (#5213) vor 1 Jahr
docker c32c177e15 improvement: introduce Super-Linter actions to check style for shell script, dockerfile and yaml files (#1966) vor 1 Jahr
events 0391282b5e fix: initialize site with customized icon and icon_background (#5227) vor 1 Jahr
extensions d7fbae286a add aws s3 iam check (#5174) vor 1 Jahr
fields 43c19007e0 fix: workspace member's last_active should be last_active_time, but not last_login_time (#4906) vor 1 Jahr
libs a325a294bd feat: opportunistic tls flag for smtp (#4794) vor 1 Jahr
migrations 25b0a97851 build: use Poetry as default build system for dependency installation in CI jobs (#5088) vor 1 Jahr
models 8bcc5a36bb feat: new editor user permission profile (#4435) vor 1 Jahr
schedule 6c4e6bf1d6 Feat/dify rag (#2528) vor 1 Jahr
services 7f98c2ea3f refactor: Delete the dataset to verify whether it is in use (#5112) vor 1 Jahr
tasks d1dbbc1e33 feat: backend model load balancing support (#4927) vor 1 Jahr
templates 3d92784bd4 fix: email template style (#1914) vor 1 Jahr
tests 8bcc5a36bb feat: new editor user permission profile (#4435) vor 1 Jahr
.dockerignore 220f7c81e9 build: fix .dockerignore file (#800) vor 2 Jahren
.env.example 4080f7b8ad feat: support tencent vector db (#3568) vor 1 Jahr
Dockerfile 55fc46c707 improvement: speed up dependency installation in docker image rebuilds by mounting cache layer (#3218) vor 1 Jahr
README.md f87f11e92c chore: make the Celery command more noticeable (#5203) vor 1 Jahr
app.py 8bca908f15 refactor: config file (#3852) vor 1 Jahr
commands.py 4080f7b8ad feat: support tencent vector db (#3568) vor 1 Jahr
config.py 4080f7b8ad feat: support tencent vector db (#3568) vor 1 Jahr
poetry.lock 4080f7b8ad feat: support tencent vector db (#3568) vor 1 Jahr
poetry.toml f62f71a81a build: initial support for poetry build tool (#4513) vor 1 Jahr
pyproject.toml 4080f7b8ad feat: support tencent vector db (#3568) vor 1 Jahr
requirements-dev.txt 23498883d4 chore: skip explicit installing jinja2 as testing dependency (#4845) vor 1 Jahr
requirements.txt 4080f7b8ad feat: support tencent vector db (#3568) vor 1 Jahr

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
  1. Create environment.
    • Anaconda
      If you use Anaconda, create a new environment and activate it bash conda create --name dify python=3.10 conda activate dify
    • Poetry
      If you use Poetry, you don't need to manually create the environment. You can execute poetry shell to activate the environment.
  2. Install dependencies
    • Anaconda
      bash pip install -r requirements.txt
    • Poetry
      bash poetry install In case of contributors missing to update dependencies for pyproject.toml, you can perform the following shell instead. base 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
  3. Run migrate

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

   flask db upgrade

⚠️ If you encounter problems with jieba, for example

   > flask db upgrade
   Error: While importing 'app', an ImportError was raised:

Please run the following command instead.

   pip install -r requirements.txt --upgrade --force-reinstall
  1. Start backend: bash 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. bash 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

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

    dev/pytest/pytest_all_tests.sh