Jyong 52c84da051 add clean unused dataset command (#609) 1 rok pred
..
constants db896255d6 Initial commit 1 rok pred
controllers 026f0bfce9 Feat/clean vector dataset (#605) 1 rok pred
core eff115267f fix: anthropic completion error in blocking mode (#591) 1 rok pred
docker db896255d6 Initial commit 1 rok pred
events 7599f79a17 feat: claude api support (#572) 1 rok pred
extensions cd51d3323b feat: member invitation and activation (#535) 1 rok pred
libs d49ac1e4ac Feature/use jwt in web (#533) 1 rok pred
migrations a03a92e9db Feat/chat support voice input (#532) 1 rok pred
models cd51d3323b feat: member invitation and activation (#535) 1 rok pred
services 7599f79a17 feat: claude api support (#572) 1 rok pred
tasks 9f28a48a92 index add to db when dataset updated (#588) 1 rok pred
tests db896255d6 Initial commit 1 rok pred
.dockerignore db896255d6 Initial commit 1 rok pred
.env.example cd51d3323b feat: member invitation and activation (#535) 1 rok pred
Dockerfile b0091452ca feat: add bash before entrypoint.sh in Dockerfile (#592) 1 rok pred
README.md 82d07ed2a8 doc: add annaconda info (#402) 1 rok pred
app.py 24f3456990 fix: account check in runtime (#569) 1 rok pred
commands.py 52c84da051 add clean unused dataset command (#609) 1 rok pred
config.py 026f0bfce9 Feat/clean vector dataset (#605) 1 rok pred
requirements.txt 7599f79a17 feat: claude api support (#572) 1 rok pred

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

    pip install -r requirements.txt
    
    1. Run migrate

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

    flask db upgrade
    
  2. Start backend:

    flask run --host 0.0.0.0 --port=5001 --debug
    
    1. Setup your application by visiting http://localhost:5001/console/api/setup or other apis...
    2. 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.