dify/api
2024-03-20 14:57:13 +08:00
..
.vscode
constants feat: add Vietnamese vi-VN (#2807) 2024-03-13 15:54:47 +08:00
controllers Fix/compatible to old tool config (#2839) 2024-03-15 11:44:24 +08:00
core fix: init qdrant vector max recursion (#2909) 2024-03-20 14:57:13 +08:00
docker
events fix: The generate conversation name was not saved (#2836) 2024-03-14 17:53:55 +08:00
extensions
fields
libs
migrations add tenant id index for document and document_segment table (#2873) 2024-03-18 14:34:32 +08:00
models add tenant id index for document and document_segment table (#2873) 2024-03-18 14:34:32 +08:00
schedule
services Feat/support tool credentials bool schema (#2875) 2024-03-18 16:55:26 +08:00
tasks fix enable annotation reply when collection is None (#2877) 2024-03-18 17:18:52 +08:00
templates
tests
.dockerignore
.env.example
app.py
commands.py fix: typo $ mark in logs of vdb migrate command (#2901) 2024-03-19 22:21:58 +08:00
config.py bump version to 0.5.10 (#2902) 2024-03-19 21:35:58 +08:00
Dockerfile
pyproject.toml
README.md
requirements.txt Bump tiktoken to 0.6.0 to support text-embedding-3-* in encoding_for_model (#2891) 2024-03-19 16:31:46 +08:00

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 -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
    

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
    
  2. Run migrate

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

    flask db upgrade
    

    ⚠️ If you encounter problems with jieba, for example

    > flask db upgrade
    Error: While importing 'app', an ImportError was raised:
    

    Please run the following command instead.

    pip install -r requirements.txt --upgrade --force-reinstall
    
  3. Start backend:

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

  5. If you need to debug local async processing, you can run celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail, celery can do dataset importing and other async tasks.