You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
John Wang 8b39e48957
fix REDIS_USERNAME format (#414)
2 jaren geleden
..
constants Initial commit 2 jaren geleden
controllers Feature/self host notion import (#397) 2 jaren geleden
core fix chinese encoding (#411) 2 jaren geleden
docker Initial commit 2 jaren geleden
events Initial commit 2 jaren geleden
extensions feat: add redis ssl support (#65) 2 jaren geleden
libs Feature/self host notion import (#397) 2 jaren geleden
migrations Feat/dataset notion import (#392) 2 jaren geleden
models Feat/dataset notion import (#392) 2 jaren geleden
services Fix/dataset init (#409) 2 jaren geleden
tasks Feat/dataset notion import (#392) 2 jaren geleden
tests Initial commit 2 jaren geleden
.dockerignore Initial commit 2 jaren geleden
.env.example fix REDIS_USERNAME format (#414) 2 jaren geleden
Dockerfile Initial commit 2 jaren geleden
README.md doc: add annaconda info (#402) 2 jaren geleden
app.py Feat/dataset notion import (#392) 2 jaren geleden
commands.py feat: add reset-encrypt-key-pair cmd for self hosted mode (#325) 2 jaren geleden
config.py feat: bump version to 0.3.4 (#406) 2 jaren geleden
requirements.txt Fix the issue of decoding a non-UTF-8 encoded file using UTF-8 (#389) 2 jaren geleden

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 up -d
   cd ../api
  1. Copy .env.example to .env
  2. Generate a SECRET_KEY in the .env file.
   openssl rand -base64 42

3.5 If you use annaconda, create a new environment and activate it

   conda create --name dify python=3.10
   conda activate dify
  1. Install dependencies bash pip install -r requirements.txt
  2. Run migrate

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

   flask db upgrade
  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, you can run celery -A app.celery worker, celery can do dataset importing and other async tasks.