-LAN- 223a30401c fix: LLM invoke error should not be raised (#11141) 1 год назад
..
.idea 7ae728a9a3 fix nltk averaged_perceptron_tagger download and fix score limit is none (#7582) 2 лет назад
.vscode e61752bd3a feat/enhance the multi-modal support (#8818) 2 лет назад
configs 208d6d6d94 chore: bump to 0.12.1 (#11122) 1 год назад
constants db1d2aaff5 Feat/add Slovensko (Slovenija) (#10731) 2 лет назад
contexts e61752bd3a feat/enhance the multi-modal support (#8818) 2 лет назад
controllers 90d5765fb6 fix: app copy raise error (#11108) 2 лет назад
core 223a30401c fix: LLM invoke error should not be raised (#11141) 1 год назад
docker 931e76e3d1 fix: remove unused queue `generation` (#10532) 2 лет назад
events 6c8e208ef3 chore: bump minimum supported Python version to 3.11 (#10386) 2 лет назад
extensions 6c8e208ef3 chore: bump minimum supported Python version to 3.11 (#10386) 2 лет назад
factories 3eb51d85da fix(workflow_entry): Support receive File and FileList in single step run. (#10947) 2 лет назад
fields 5172f0bf39 feat: Check and compare the DSL version before import an app (#10969) 2 лет назад
libs 0f85e3557b fix: site icon not showing (#11094) 2 лет назад
migrations 128efc3193 Feat/clean message records (#10588) 2 лет назад
models 8d5a1be227 fix: Cannot use files in the user inputs. (#11112) 2 лет назад
schedule 128efc3193 Feat/clean message records (#10588) 2 лет назад
services 2927493cf3 fix: better way to handle github dsl url close #11113 (#11125) 1 год назад
tasks 40a5f1c80a fix: wrong param name (#11039) 2 лет назад
templates 4fd2743efa Feat/new login (#8120) 2 лет назад
tests 6c8e208ef3 chore: bump minimum supported Python version to 3.11 (#10386) 2 лет назад
.dockerignore 27f0ae8416 build: support Poetry for depencencies tool in api's Dockerfile (#5105) 2 лет назад
.env.example 8ff65abbc6 ext_redis.py support redis clusters --- Fixes #9538 (#9789) 2 лет назад
Dockerfile da601f0bef chore: update base image to Python 3.12 in Dockerfile (#10358) 2 лет назад
README.md da601f0bef chore: update base image to Python 3.12 in Dockerfile (#10358) 2 лет назад
app.py 6c8e208ef3 chore: bump minimum supported Python version to 3.11 (#10386) 2 лет назад
app_factory.py 0e8ab0588f fix: (#10437 followup) fix conditions with DEBUG config (#10438) 2 лет назад
commands.py 51db59622c chore(lint): cleanup repeated cause exception in logging.exception replaced by helpful message (#10425) 2 лет назад
poetry.lock b791a80b75 chore: update chromadb version to 0.5.20 (#11038) 2 лет назад
poetry.toml f62f71a81a build: initial support for poetry build tool (#4513) 2 лет назад
pyproject.toml b791a80b75 chore: update chromadb version to 0.5.20 (#11038) 2 лет назад
pytest.ini 096c0ad564 feat: Add support for TEI API key authentication (#11006) 2 лет назад

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
   # 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 Poetry to manage dependencies. You can execute poetry shell to activate the environment.

  1. Install dependencies
   poetry env use 3.12
   poetry install
  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 handle and debug the async tasks (e.g. dataset importing and documents indexing), 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

Testing

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