docapi 0.0.10

DocAPI is a Python package that automatically generates API documentation using LLM.

[ English | 中文 ]

DocAPI is a Python package that automatically generates API documentation using a large model. It automatically scans the API routing structure, generates or updates API documentation, gives code call examples, and deploys and displays documentation using web pages.

Installation

pip install docapi

or

pip install -U docapi -i https://pypi.org/simple

GitHub source code installation

pip install git+https://github.com/Shulin-Zhang/docapi

Usage

Method 1 (Recommended)

Automatically scan the routing structure. This is only valid for flask projects and must be used in the environment of api projects.

export OPENAI_API_KEY=your_key

# Generate API documentation
docapi generate server.py

# Update API documentation
docapi update server.py

# Start the web service
docapi serve

or

export OPENAI_API_KEY=your_key

export OPENAI_API_BASE=api_base_url

export OPENAI_API_MODEL=model_name

# 生成文档
docapi generate server.py

# 更新文档
docapi update server.py

# 启动web服务
docapi serve

Method 2

Generate the configuration file

docapi init

Edit the config.yaml file

# API file list

api_files: 
  - 'flask_server.py'
  - 'flask_api.py'

# OpenAI

openai_api_key: xxx

openai_base_url: 'http://ip:port/v1'

openai_model: 'qwen-plus'

# Azure OpenAI

azure_api_key: null

azure_endpoint: null

azure_api_version: null

azure_model: null

# Generate API documentation
docapi generate --doc_dir ./docs --lang zh --config config.yaml

# Update API documentation
docapi update --doc_dir ./docs --lang zh --config config.yaml

# Start the web service
docapi serve ./docs -h 127.0.0.1 -p 9000

Supported Models

• OpenAI

• AzureOpenAI

• Tongyi Qianwen

Supported API Frameworks

• Flask

Automatic scanning is only valid for the Flask framework and is recommended for use on Flask services.

API Web Page

TODO

• Supports large models such as Wenxin Yiyan and Zhipu AI.

• Supports automatic scanning of frameworks such as fastapi and Django.

• Supports online web page display of documents.

• Supports custom document templates.

• Multithreading accelerates requests.

• Import to postman.