dify/api
2024-10-30 16:23:12 +08:00
..
.idea fix nltk averaged_perceptron_tagger download and fix score limit is none (#7582) 2024-08-26 15:14:05 +08:00
.vscode feat/enhance the multi-modal support (#8818) 2024-10-21 10:43:49 +08:00
configs chore: improve validation and handler of logging timezone with TimezoneName (#9595) 2024-10-30 11:18:23 +08:00
constants nltk security issue and upgrade unstructured (#9558) 2024-10-23 16:23:55 +08:00
contexts feat/enhance the multi-modal support (#8818) 2024-10-21 10:43:49 +08:00
controllers fix update_by_api batch field issue (#10001) 2024-10-30 11:17:46 +08:00
core fix(workflow): refine variable type checks in LLMNode (#10051) 2024-10-30 16:23:12 +08:00
docker fix: use LOG_LEVEL for celery startup (#7628) 2024-08-26 14:44:58 +08:00
events feat/enhance the multi-modal support (#8818) 2024-10-21 10:43:49 +08:00
extensions chore: improve validation and handler of logging timezone with TimezoneName (#9595) 2024-10-30 11:18:23 +08:00
factories refactor(file_factory): improve filename and mime type determination (#9784) 2024-10-24 17:07:20 +08:00
fields feat: /conversations api response add 'update_at' field,and update api docs add sort_by parameter (#10043) 2024-10-30 15:41:15 +08:00
libs refactor: use dify_config to replace legacy usage of flask app's config (#9089) 2024-10-22 11:01:32 +08:00
migrations add tidb on qdrant type (#9831) 2024-10-25 13:57:03 +08:00
models fix(api): add signature generation for image previews (#9893) 2024-10-26 15:35:57 +08:00
schedule add tidb on qdrant type (#9831) 2024-10-25 13:57:03 +08:00
services fix: allow external knowledge api use simple host (#9966) 2024-10-29 10:33:15 +08:00
tasks Feat/new login (#8120) 2024-10-21 10:03:40 +08:00
templates Feat/new login (#8120) 2024-10-21 10:03:40 +08:00
tests fix(workflow): refine variable type checks in LLMNode (#10051) 2024-10-30 16:23:12 +08:00
.dockerignore build: support Poetry for depencencies tool in api's Dockerfile (#5105) 2024-06-22 01:34:08 +08:00
.env.example chore: add tidb-on-qdrant configuration in env and docker-compose file (#10015) 2024-10-29 21:11:10 +08:00
app_factory.py refactor: use dify_config to replace legacy usage of flask app's config (#9089) 2024-10-22 11:01:32 +08:00
app.py refactor: use dify_config to replace legacy usage of flask app's config (#9089) 2024-10-22 11:01:32 +08:00
commands.py Added OceanBase as an option for the vector store in Dify (#10010) 2024-10-29 21:10:18 +08:00
Dockerfile chore(docker): correct package version for expat and perl in Dockerfile (#9801) 2024-10-24 19:07:03 +08:00
poetry.lock Added OceanBase as an option for the vector store in Dify (#10010) 2024-10-29 21:10:18 +08:00
poetry.toml build: initial support for poetry build tool (#4513) 2024-06-11 13:11:28 +08:00
pyproject.toml Added OceanBase as an option for the vector store in Dify (#10010) 2024-10-29 21:10:18 +08:00
pytest.ini feat: add models for gitee.ai (#9490) 2024-10-28 16:52:12 +08:00
README.md fix: poetry installation in CI jobs (#9336) 2024-10-14 22:22:03 +08:00

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
    
  2. Copy .env.example to .env

  3. 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
    
  4. Create environment.

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

  5. 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
    
  6. Run migrate

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

    poetry run python -m flask db upgrade
    
  7. Start backend

    poetry run python -m flask run --host 0.0.0.0 --port=5001 --debug
    
  8. Start Dify web service.

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

  10. 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 --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