sino dfb6f4fec6 fix: extract tool calls correctly while arguments is empty (#6503) 1 an în urmă
..
configs 2ba05b041f refactor(myscale):Set the default value of the myscale vector db in DifyConfig. (#6441) 1 an în urmă
constants 6ef401a9f0 feat:add tts-streaming config and future (#5492) 1 an în urmă
controllers c57b3931d5 refactor(api): switch to dify_config in controllers/console (#6485) 1 an în urmă
core dfb6f4fec6 fix: extract tool calls correctly while arguments is empty (#6503) 1 an în urmă
docker 5236cb1888 fix: kill signal is not passed to the main process (#6159) 1 an în urmă
events d320d1468d Feat/delete file when clean document (#5882) 1 an în urmă
extensions 7c397f5722 update celery beat scheduler time to env (#6352) 1 an în urmă
fields 9622fbb62f feat: app rate limit (#5844) 1 an în urmă
libs 9622fbb62f feat: app rate limit (#5844) 1 an în urmă
migrations 1e0e573165 update clean embedding cache query logic (#6483) 1 an în urmă
models 1e0e573165 update clean embedding cache query logic (#6483) 1 an în urmă
schedule f73a3a58ae update delete embeddings by id (#6489) 1 an în urmă
services 57729823a0 fix wrong method using (#6459) 1 an în urmă
tasks 443e96777b update empty document caused delete exist collection (#6392) 1 an în urmă
templates 00b4cc3cd4 feat: implement forgot password feature (#5534) 1 an în urmă
tests 4a026fa352 Enhancement: add model provider - Amazon Sagemaker (#6255) 1 an în urmă
.dockerignore 27f0ae8416 build: support Poetry for depencencies tool in api's Dockerfile (#5105) 1 an în urmă
.env.example 7c397f5722 update celery beat scheduler time to env (#6352) 1 an în urmă
Dockerfile 9b7c74a5d9 chore: skip pip upgrade preparation in api dockerfile (#5999) 1 an în urmă
README.md 2d6624cf9e typo: Update README.md (#5987) 1 an în urmă
app.py d7f75d17cc Chore/remove-unused-code (#5917) 1 an în urmă
commands.py 7c70eb87bc feat: support AnalyticDB vector store (#5586) 1 an în urmă
poetry.lock 4e2fba404d WebscraperTool bypass cloudflare site by cloudscraper (#6337) 1 an în urmă
poetry.toml f62f71a81a build: initial support for poetry build tool (#4513) 1 an în urmă
pyproject.toml 4e2fba404d WebscraperTool bypass cloudflare site by cloudscraper (#6337) 1 an în urmă

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
   cp middleware.env.example middleware.env
   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.

  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,ops_trace,app_deletion
    

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