Initial commit: AI Shell v0.1.0

- AI-powered shell command generator using DeepSeek V3
- Support for natural language to shell command conversion
- Secure configuration management with .env files
- Package structure with uv tool installation support
- Chinese and English language support
- Configuration validation and error handling
This commit is contained in:
2025-07-12 22:06:15 +08:00
commit 644071850a
21 changed files with 3252 additions and 0 deletions

11
.env.example Normal file
View File

@ -0,0 +1,11 @@
# AI Shell 配置文件模板
# 复制此文件为 .env 并填入您的实际配置
# API 配置(必填)
AI_SHELL_API_KEY=your_api_key_here
AI_SHELL_BASE_URL=https://your-api-endpoint.com/v3/
AI_SHELL_MODEL=your_model_name
# 可选配置
# AI_SHELL_TIMEOUT=30
# AI_SHELL_MAX_RETRIES=3

272
.gitignore vendored Normal file
View File

@ -0,0 +1,272 @@
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.env.local
.env.*.local
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be added to the global gitignore or merged into this project gitignore. For a PyCharm
# project, it is recommended to include the following files in version control:
# *.iml
# modules.xml
# .idea/misc.xml
# .idea/modules.xml
# .idea/vcs.xml
# .idea/workspace.xml
# .idea/tasks.xml
# .idea/dictionaries
# .idea/shelf
#
# # AWS User-specific
# .idea/**/aws.xml
#
# # Generated files
# .idea/**/contentModel.xml
#
# # Sensitive or high-churn files
# .idea/**/dataSources/
# .idea/**/dataSources.ids
# .idea/**/dataSources.local.xml
# .idea/**/sqlDataSources.xml
# .idea/**/dynamic.xml
# .idea/**/uiDesigner.xml
# .idea/**/dbnavigator.xml
#
# # Gradle
# .idea/**/gradle.xml
# .idea/**/libraries
#
# # Gradle and Maven with auto-import
# # When using Gradle or Maven with auto-import, you should exclude module files,
# # since they will be recreated, and may cause churn. Uncomment if using
# # auto-import.
# # .idea/artifacts
# # .idea/compiler.xml
# # .idea/jarRepositories.xml
# # .idea/modules.xml
# # .idea/*.iml
# # .idea/modules
# # *.iml
# # *.ipr
# CMake
cmake-build-*/
# Mongo Explorer plugin
.idea/**/mongoSettings.xml
# File-based project format
*.iws
# IntelliJ
out/
# mpeltonen/sbt-idea plugin
.idea_modules/
# JIRA plugin
atlassian-ide-plugin.xml
# Cursive Clojure plugin
.idea/replstate.xml
# SonarLint plugin
.idea/sonarlint/
# Crashlytics plugin (for Android Studio and IntelliJ)
com_crashlytics_export_strings.xml
crashlytics.properties
crashlytics-build.properties
fabric.properties
# Editor-based Rest Client
.idea/httpRequests
# Android studio 3.1+ serialized cache file
.idea/caches/build_file_checksums.ser
# UV specific
.uv_cache/
# macOS
.DS_Store
.AppleDouble
.LSOverride
# Thumbnails
._*
# Files that might appear in the root of a volume
.DocumentRevisions-V100
.fseventsd
.Spotlight-V100
.TemporaryItems
.Trashes
.VolumeIcon.icns
.com.apple.timemachine.donotpresent
# Directories potentially created on remote AFP share
.AppleDB
.AppleDesktop
Network Trash Folder
Temporary Items
.apdisk
# Project specific
dist/
build/
*.egg-info/
.venv/
.python-version
~

64
Makefile Normal file
View File

@ -0,0 +1,64 @@
.PHONY: help install upgrade uninstall build clean test bump-patch bump-minor bump-major
help:
@echo "AI Shell Development Commands:"
@echo ""
@echo " install - Install AI Shell globally using uv tool"
@echo " upgrade - Upgrade existing AI Shell installation"
@echo " uninstall - Uninstall AI Shell"
@echo " build - Build the package"
@echo " clean - Clean build artifacts"
@echo " test - Test the installation"
@echo " bump-patch - Bump patch version (0.1.0 -> 0.1.1)"
@echo " bump-minor - Bump minor version (0.1.0 -> 0.2.0)"
@echo " bump-major - Bump major version (0.1.0 -> 1.0.0)"
install:
@echo "🚀 Installing AI Shell..."
@uv build
@uv tool install . --force
@echo "✅ AI Shell installed successfully!"
upgrade: bump-patch install
@echo "✅ AI Shell upgraded successfully!"
quick-upgrade:
@echo "🔄 Quick upgrade (patch version)..."
@./quick_upgrade.sh
uninstall:
@echo "🗑️ Uninstalling AI Shell..."
@uv tool uninstall ai-shell || true
@echo "✅ AI Shell uninstalled"
build:
@echo "📦 Building package..."
@uv build
clean:
@echo "🧹 Cleaning build artifacts..."
@rm -rf dist/
@rm -rf build/
@rm -rf *.egg-info/
@echo "✅ Clean complete"
test:
@echo "🧪 Testing AI Shell installation..."
@ai --version
@ai --config
@echo "✅ Test complete"
bump-patch:
@echo "📈 Bumping patch version..."
@python scripts/bump_version.py patch
@echo "✅ Version bumped"
bump-minor:
@echo "📈 Bumping minor version..."
@python scripts/bump_version.py minor
@echo "✅ Version bumped"
bump-major:
@echo "📈 Bumping major version..."
@python scripts/bump_version.py major
@echo "✅ Version bumped"

42
README.md Normal file
View File

@ -0,0 +1,42 @@
# AI Shell
AI-powered shell command generator using DeepSeek V3 model via OpenAI-compatible API.
## Features
- Generate shell commands from natural language descriptions
- Interactive execution confirmation (Enter to execute, n to cancel)
- Supports multiple languages for prompts and responses
- Uses DeepSeek V3 model for high-quality command generation
- User-friendly interface with default execution on Enter
## Usage
```bash
uv run python ai.py "your command description here"
```
## Setup
1. Install dependencies:
```bash
uv sync
```
2. Run the tool:
```bash
uv run python ai.py "list all files in current directory"
uv run python ai.py "show disk usage"
uv run python ai.py "find all Python files"
```
## Configuration
- **Model**: DeepSeek V3 (deepseek-v3-250324)
- **API**: Volces (ByteDance) OpenAI-compatible interface
- **Base URL**: https://ark.cn-beijing.volces.com/api/v3/
## Requirements
- Python 3.12+
- UV package manager with configured Chinese mirrors for fast downloads

14
ai_shell/__init__.py Normal file
View File

@ -0,0 +1,14 @@
"""
AI Shell - AI-powered shell command generator using DeepSeek V3
A command-line tool that generates shell commands from natural language descriptions.
"""
__version__ = "0.1.0"
__author__ = "AI Shell Team"
__email__ = "ai-shell@example.com"
__description__ = "AI-powered shell command generator using DeepSeek V3"
from .main import main
__all__ = ["main"]

74
ai_shell/agent.py Normal file
View File

@ -0,0 +1,74 @@
"""
AI Agent module for shell command generation
"""
from textwrap import dedent
from pydantic_ai import Agent
from pydantic_ai.models.openai import OpenAIModel
from .config import get_model, setup_environment
from .models import Answer
# System prompt for the AI agent
SYSTEM_PROMPT = dedent(
"""\
You are a professional developer specializing in shell commands.
Your task is to generate the correct shell commands based on the
user's request.
IMPORTANT: ALWAYS USE THE SAME LANGUAGE AS THE USER PROMPT IN
YOUR RESPONSE.
Process:
1. Think Aloud: Use the `think` function to explain your reasoning.
Justify why you chose a particular command, considering efficiency,
safety, and best practices.
2. Provide the Final Command: Use the `answer` function to present
the final shell command concisely.
"""
)
def create_agent() -> Agent:
"""Create and configure the AI agent"""
# Setup environment variables
setup_environment()
# Create OpenAI compatible model
model = OpenAIModel(get_model())
# Create agent
agent = Agent(
model=model,
system_prompt=SYSTEM_PROMPT,
output_type=Answer,
)
# Register tools
@agent.tool_plain
def think(s: str) -> None:
"""Communicate your thought process to the user.
Args:
s (str): A description of your reasoning or decision-making process.
"""
print(f"(AI Thinking): {s}\n")
@agent.tool_plain
def answer(success: bool, cmd: str | None, failure: str | None) -> Answer:
"""Provide the final shell command or explain why it couldn't be generated.
Args:
success (bool): Indicates whether a shell command was successfully generated.
cmd (str | None): The generated shell command if `success` is True.
It must be a single-line command. If `success` is False, this should be None.
failure (str | None): If `success` is False, provide a reason why the command
could not be generated. If `success` is True, this should be None.
Returns:
Answer: A structured response that will be processed for the user.
"""
return Answer(success, cmd, failure)
return agent

77
ai_shell/config.py Normal file
View File

@ -0,0 +1,77 @@
"""
Configuration module for AI Shell
"""
import os
from pathlib import Path
try:
from dotenv import load_dotenv
except ImportError:
load_dotenv = None
# Load .env file if it exists
def load_env_file() -> None:
"""Load environment variables from .env file"""
if load_dotenv is None:
return
# Try to find .env file in current directory or package directory
env_paths = [
Path.cwd() / ".env",
Path(__file__).parent.parent / ".env",
Path.home() / ".ai-shell" / ".env",
]
for env_path in env_paths:
if env_path.exists():
load_dotenv(env_path)
break
# Load .env file on import
load_env_file()
# Default API configuration (fallback values)
DEFAULT_API_KEY = "your_api_key_here"
DEFAULT_BASE_URL = "https://api.openai.com/v1/"
DEFAULT_MODEL = "gpt-3.5-turbo"
def get_api_key() -> str:
"""Get API key from environment or use default"""
api_key = os.getenv("AI_SHELL_API_KEY", DEFAULT_API_KEY)
if api_key == DEFAULT_API_KEY:
raise ValueError(
"API key not configured. Please set AI_SHELL_API_KEY in .env file or environment variable."
)
return api_key
def get_base_url() -> str:
"""Get base URL from environment or use default"""
return os.getenv("AI_SHELL_BASE_URL", DEFAULT_BASE_URL)
def get_model() -> str:
"""Get model name from environment or use default"""
return os.getenv("AI_SHELL_MODEL", DEFAULT_MODEL)
def get_timeout() -> int:
"""Get request timeout from environment"""
return int(os.getenv("AI_SHELL_TIMEOUT", "30"))
def get_max_retries() -> int:
"""Get max retries from environment"""
return int(os.getenv("AI_SHELL_MAX_RETRIES", "3"))
def setup_environment() -> None:
"""Setup environment variables for OpenAI client"""
os.environ["OPENAI_API_KEY"] = get_api_key()
os.environ["OPENAI_BASE_URL"] = get_base_url()
def validate_config() -> bool:
"""Validate configuration"""
try:
get_api_key()
get_base_url()
get_model()
return True
except ValueError:
return False

140
ai_shell/main.py Normal file
View File

@ -0,0 +1,140 @@
"""
Main entry point for AI Shell
"""
import os
import sys
import argparse
from typing import List, Optional
from .agent import create_agent
from . import __version__
def execute_command(command: str) -> None:
"""Execute a shell command"""
os.system(command)
def get_user_confirmation(command: str) -> bool:
"""Get user confirmation before executing command"""
print(f"(AI Answer): {command}")
response = input("Execute? [Y/n]: ").strip().lower()
return response in ["", "y", "yes"]
def process_prompt(prompt: str) -> None:
"""Process user prompt and generate shell command"""
if not prompt.strip():
print("Error: No prompt provided")
sys.exit(1)
# Create AI agent
agent = create_agent()
try:
# Generate response
resp = agent.run_sync(prompt)
answer = resp.output
if answer.success and answer.cmd is not None:
if get_user_confirmation(answer.cmd):
execute_command(answer.cmd)
else:
print(f"(AI Answer): {answer.failure}")
print("Command generation failed")
sys.exit(1)
except Exception as e:
print(f"Error: {e}")
sys.exit(1)
def create_parser() -> argparse.ArgumentParser:
"""Create command line argument parser"""
parser = argparse.ArgumentParser(
prog="ai",
description="AI-powered shell command generator using DeepSeek V3",
epilog="Examples:\n"
" ai list files\n"
" ai \"show disk usage\"\n"
" ai 显示当前目录\n",
formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument(
"prompt",
nargs="*",
help="Natural language description of the command you want"
)
parser.add_argument(
"--version",
action="version",
version=f"ai-shell {__version__}"
)
parser.add_argument(
"--config",
action="store_true",
help="Show current configuration"
)
return parser
def show_config() -> None:
"""Show current configuration"""
from .config import get_api_key, get_base_url, get_model, get_timeout, get_max_retries, validate_config
print("AI Shell Configuration:")
print(f" Model: {get_model()}")
print(f" Base URL: {get_base_url()}")
try:
api_key = get_api_key()
print(f" API Key: {api_key[:8]}...{api_key[-4:]}")
except ValueError as e:
print(f" API Key: ❌ {e}")
print(f" Timeout: {get_timeout()}s")
print(f" Max Retries: {get_max_retries()}")
print(f"\nConfiguration Status: {'✅ Valid' if validate_config() else '❌ Invalid'}")
print("\nConfiguration Sources (in priority order):")
print(" 1. Environment variables")
print(" 2. .env file in current directory")
print(" 3. .env file in package directory")
print(" 4. ~/.ai-shell/.env file")
print(" 5. Default values")
print("\nEnvironment Variables:")
print(" AI_SHELL_API_KEY - API key")
print(" AI_SHELL_BASE_URL - API base URL")
print(" AI_SHELL_MODEL - Model name")
print(" AI_SHELL_TIMEOUT - Request timeout (seconds)")
print(" AI_SHELL_MAX_RETRIES - Maximum retry attempts")
def main() -> None:
"""Main entry point"""
parser = create_parser()
args = parser.parse_args()
if args.config:
show_config()
return
if not args.prompt:
parser.print_help()
sys.exit(1)
# Validate configuration before processing
from .config import validate_config
if not validate_config():
print("❌ Configuration error: API key not configured.")
print("Please set AI_SHELL_API_KEY in .env file or environment variable.")
print("Run 'ai --config' to see current configuration.")
sys.exit(1)
# Join all prompt arguments into a single string
prompt = " ".join(args.prompt)
process_prompt(prompt)
if __name__ == "__main__":
main()

13
ai_shell/models.py Normal file
View File

@ -0,0 +1,13 @@
"""
Data models for AI Shell
"""
from dataclasses import dataclass
from typing import Optional
@dataclass
class Answer:
"""Response model for AI-generated shell commands"""
success: bool
cmd: Optional[str]
failure: Optional[str]

46
pyproject.toml Normal file
View File

@ -0,0 +1,46 @@
[project]
name = "ai-shell"
version = "0.1.0"
description = "AI-powered shell command generator using DeepSeek V3"
authors = [
{name = "AI Shell Team", email = "ai-shell@example.com"}
]
readme = "README.md"
license = {text = "MIT"}
keywords = ["ai", "shell", "command", "generator", "deepseek"]
classifiers = [
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"License :: OSI Approved :: MIT License",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.12",
"Topic :: Software Development :: Libraries :: Python Modules",
"Topic :: System :: Shells",
]
requires-python = ">=3.12"
dependencies = [
"pydantic-ai",
"openai",
"requests>=2.32.4",
"python-dotenv>=1.0.0",
]
[project.scripts]
ai = "ai_shell.main:main"
[project.urls]
Homepage = "https://github.com/your-username/ai-shell"
Repository = "https://github.com/your-username/ai-shell"
Issues = "https://github.com/your-username/ai-shell/issues"
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["ai_shell"]
[tool.hatch.version]
path = "ai_shell/__init__.py"
# UV 配置已移至 uv.toml 文件

36
quick_upgrade.sh Executable file
View File

@ -0,0 +1,36 @@
#!/bin/bash
# AI Shell 快速升级脚本
set -e
echo "🔄 AI Shell 快速升级..."
# 检查是否在项目目录
if [ ! -f "pyproject.toml" ]; then
echo "❌ 请在 ai-shell 项目目录中运行此脚本"
exit 1
fi
# 升级补丁版本
echo "📈 升级版本..."
python scripts/bump_version.py patch
# 重新构建
echo "📦 重新构建..."
uv build
# 重新安装
echo "🔧 重新安装..."
uv tool install . --force
# 验证
echo "✅ 升级完成!"
echo ""
echo "新版本信息:"
ai --version
echo ""
echo "🧪 可以测试以下命令:"
echo " ai --config"
echo " ai \"echo test\""
echo " ai \"list files\""

64
scripts/bump_version.py Executable file
View File

@ -0,0 +1,64 @@
#!/usr/bin/env python3
"""
Version bumping script for ai-shell
"""
import re
import sys
from pathlib import Path
def bump_version(version_type: str = "patch") -> None:
"""Bump version in __init__.py and pyproject.toml"""
# Read current version from __init__.py
init_file = Path("ai_shell/__init__.py")
init_content = init_file.read_text()
# Extract current version
version_match = re.search(r'__version__ = "([^"]+)"', init_content)
if not version_match:
print("Error: Could not find version in __init__.py")
sys.exit(1)
current_version = version_match.group(1)
major, minor, patch = map(int, current_version.split('.'))
# Bump version
if version_type == "major":
major += 1
minor = 0
patch = 0
elif version_type == "minor":
minor += 1
patch = 0
elif version_type == "patch":
patch += 1
else:
print(f"Error: Invalid version type '{version_type}'. Use 'major', 'minor', or 'patch'")
sys.exit(1)
new_version = f"{major}.{minor}.{patch}"
# Update __init__.py
new_init_content = re.sub(
r'__version__ = "[^"]+"',
f'__version__ = "{new_version}"',
init_content
)
init_file.write_text(new_init_content)
# Update pyproject.toml
pyproject_file = Path("pyproject.toml")
pyproject_content = pyproject_file.read_text()
new_pyproject_content = re.sub(
r'version = "[^"]+"',
f'version = "{new_version}"',
pyproject_content
)
pyproject_file.write_text(new_pyproject_content)
print(f"Version bumped from {current_version} to {new_version}")
if __name__ == "__main__":
version_type = sys.argv[1] if len(sys.argv) > 1 else "patch"
bump_version(version_type)

1237
uv.lock generated Normal file

File diff suppressed because it is too large Load Diff

33
uv.toml Normal file
View File

@ -0,0 +1,33 @@
# uv 项目配置文件
# 配置国内镜像源加速下载
# 主要的 PyPI 镜像源
index-url = "https://pypi.tuna.tsinghua.edu.cn/simple"
# 额外的镜像源
extra-index-url = [
"https://mirrors.aliyun.com/pypi/simple/",
"https://mirrors.cloud.tencent.com/pypi/simple/",
]
# 索引策略 - 允许从所有索引中选择最佳版本
index-strategy = "unsafe-best-match"
# 缓存目录(移除此配置,使用 uv 默认缓存位置)
# cache-dir = "~/.cache/uv"
# 并发下载数
concurrent-downloads = 10
# Python 解释器下载镜像源配置
# 注意uv 使用的是 python-build-standalone 项目的构建版本
# 暂时注释掉镜像源配置,使用默认源确保兼容性
# python-install-mirror = "https://mirror.nju.edu.cn/github-release/indygreg/python-build-standalone/"
# 可尝试的镜像源(需要验证路径格式):
# python-install-mirror = "https://mirrors.tuna.tsinghua.edu.cn/python-release/"
# python-install-mirror = "https://mirrors.aliyun.com/python-release/"
# python-install-mirror = "https://mirrors.ustc.edu.cn/python/"
# 如果需要加速,可以设置代理或使用以下环境变量:
# export UV_PYTHON_INSTALL_MIRROR="镜像源URL"

119
使用示例.md Normal file
View File

@ -0,0 +1,119 @@
# AI Shell 使用示例
## 🚀 基本使用流程
### 示例 1查看当前日期按 Enter 执行)
```bash
$ uv run python ai.py "show current date"
(AI Thinking): To display the current date, the `date` command is the most straightforward and commonly used tool in Unix-like systems.
(AI Answer): date
Execute? [Y/n]: ⏎ # 直接按 Enter 键
2025年 7月12日 星期六 16时08分00秒 CST
```
### 示例 2危险命令输入 n 取消)
```bash
$ uv run python ai.py "remove all files"
(AI Thinking): To remove all files in the current directory, we can use the `rm` command. However, we need to be cautious because this action is irreversible.
(AI Answer): rm -rf *
Execute? [Y/n]: n # 输入 n 取消执行
```
### 示例 3中文命令按 Enter 执行)
```bash
$ uv run python ai.py "显示当前目录下的文件"
(AI Thinking): 用户想要显示当前目录下的文件。最常用和直接的命令是 `ls`,它会列出当前目录中的所有文件和文件夹。
(AI Answer): ls
Execute? [Y/n]: ⏎ # 直接按 Enter 键
README.md ai.py pyproject.toml uv.lock uv.toml
```
## 📋 交互选项说明
### 执行命令的方式:
- **直接按 Enter**: 执行命令(默认选择)
- **输入 y 或 yes**: 执行命令
- **输入 n 或 no**: 取消执行
### 提示符说明:
- `Execute? [Y/n]:`
- `[Y/n]` 表示默认选择是 Y执行
- 大写的 Y 表示这是默认选项
- 直接按 Enter 等同于选择 Y
## 🎯 使用技巧
### 1. 快速执行常用命令
对于安全的查看类命令,可以直接按 Enter 快速执行:
```bash
uv run python ai.py "list files" # Enter 执行
uv run python ai.py "show disk usage" # Enter 执行
uv run python ai.py "current directory" # Enter 执行
```
### 2. 谨慎处理危险命令
对于可能造成数据丢失的命令,建议仔细检查后再决定:
```bash
uv run python ai.py "delete old logs" # 检查命令后再决定
uv run python ai.py "format disk" # 输入 n 取消
uv run python ai.py "remove directory" # 仔细确认
```
### 3. 中英文混合使用
```bash
# 英文命令
uv run python ai.py "find Python files"
# 中文命令
uv run python ai.py "查找Python文件"
# 混合使用
uv run python ai.py "find all .py files in current directory"
```
## 🔧 常用命令示例
### 文件操作
```bash
uv run python ai.py "create a backup directory"
uv run python ai.py "copy all text files to backup"
uv run python ai.py "find files larger than 100MB"
```
### 系统信息
```bash
uv run python ai.py "show system information"
uv run python ai.py "check memory usage"
uv run python ai.py "list running processes"
```
### 网络相关
```bash
uv run python ai.py "check network connectivity"
uv run python ai.py "show network interfaces"
uv run python ai.py "test connection to google.com"
```
### 开发相关
```bash
uv run python ai.py "find all Python files"
uv run python ai.py "count lines of code"
uv run python ai.py "start a simple HTTP server"
```
## ⚠️ 安全提醒
1. **仔细阅读 AI 生成的命令**:在执行前确保理解命令的作用
2. **危险命令要谨慎**:涉及删除、格式化等操作时要特别小心
3. **测试环境优先**:在重要系统上使用前,建议先在测试环境验证
4. **备份重要数据**:执行可能影响数据的命令前,确保有备份
---
💡 **提示**:现在直接按 Enter 键就能执行命令,让您的工作流程更加流畅!

157
修改完成总结.md Normal file
View File

@ -0,0 +1,157 @@
# AI Shell 项目修改完成总结
## ✅ 已完成的修改
### 1. 模型接口更换
- **原来**: Gemini AI (Google)
- **现在**: DeepSeek V3 (通过 OpenAI 兼容接口)
### 2. API 配置更新
```python
# 新的配置
API_KEY = "f8370a60-fe0a-455f-9167-411d476123d2"
BASE_URL = "https://ark.cn-beijing.volces.com/api/v3/"
MODEL = "deepseek-v3-250324"
```
### 3. 依赖包更新
- **移除**: `google-genai`
- **添加**: `openai` (用于 OpenAI 兼容接口)
### 4. 代码修改详情
#### 主要变更:
1. **导入模块**:
```python
# 原来
from pydantic_ai.models.gemini import GeminiModel
# 现在
from pydantic_ai.models.openai import OpenAIModel
```
2. **模型初始化**:
```python
# 原来
model = GeminiModel("gemini-2.0-flash")
# 现在
os.environ["OPENAI_API_KEY"] = API_KEY
os.environ["OPENAI_BASE_URL"] = BASE_URL
model = OpenAIModel("deepseek-v3-250324")
```
3. **修复弃用警告**:
```python
# 原来
result_type=Answer
resp.data
# 现在
output_type=Answer
resp.output
```
## 🧪 测试结果
### 功能测试
✅ **英文命令**: `"list files in current directory"` → `ls`
✅ **中文命令**: `"创建一个新目录叫test"` → `mkdir test`
✅ **复杂命令**: `"show disk usage"` → `df -h`
### 性能表现
- ✅ 响应速度快
- ✅ 命令准确性高
- ✅ 支持中英文交互
- ✅ 思考过程清晰
## 📁 最终项目结构
```
ai-shell/
├── ai.py # ✅ 主程序(已更新为 DeepSeek V3
├── pyproject.toml # ✅ 项目配置(已更新依赖)
├── uv.toml # ✅ UV 配置(国内镜像源)
├── uv.lock # ✅ 依赖锁定文件(已更新)
├── .python-version # ✅ Python 版本文件
├── .venv/ # ✅ 虚拟环境
├── README.md # ✅ 项目说明(已更新)
├── 配置总结.md # ✅ 配置总结
├── 项目配置说明.md # ✅ 详细配置说明(已更新)
└── 修改完成总结.md # ✅ 本文件
```
## 🚀 使用方法
### 基本命令
```bash
# 英文命令
uv run python ai.py "list all Python files"
uv run python ai.py "show current directory size"
uv run python ai.py "find files modified today"
# 中文命令
uv run python ai.py "显示当前目录下的所有文件"
uv run python ai.py "查看磁盘使用情况"
uv run python ai.py "创建一个名为backup的目录"
```
### 交互流程
1. **AI 思考**: 显示推理过程
2. **AI 回答**: 提供具体命令
3. **用户确认**: `[Y/n]` 选择是否执行
- **Enter 键** 或 **y/yes**: 执行命令
- **n/no**: 取消执行
4. **自动执行**: 确认后自动运行命令
## 🎯 核心优势
### 1. 模型优势
- **DeepSeek V3**: 最新的开源大模型,性能优异
- **中文友好**: 对中文指令理解更准确
- **成本效益**: 通过 Volces API 使用,性价比高
### 2. 技术优势
- **OpenAI 兼容**: 标准接口,易于维护
- **快速部署**: 国内镜像源,依赖安装快速
- **环境隔离**: UV 虚拟环境,避免冲突
### 3. 用户体验
- **双语支持**: 中英文命令都能准确理解
- **安全确认**: 执行前需要用户确认
- **便捷操作**: 直接按 Enter 键即可执行(默认为 Y
- **思考透明**: 显示 AI 的推理过程
## 📋 配置验证
### 检查配置是否正确
```bash
# 1. 检查依赖
uv pip list | grep -E "(pydantic-ai|openai)"
# 2. 测试连接
uv run python ai.py "echo hello"
# 3. 验证中文支持
uv run python ai.py "显示当前时间"
```
## 🔧 故障排除
### 常见问题
1. **API 连接失败**: 检查网络连接和 API 密钥
2. **模型不响应**: 确认 BASE_URL 和模型名称正确
3. **依赖问题**: 运行 `uv sync` 重新同步依赖
### 调试方法
```bash
# 查看详细错误信息
uv run python ai.py "test command" 2>&1
# 检查环境变量
uv run python -c "import os; print(os.environ.get('OPENAI_BASE_URL'))"
```
---
🎉 **修改完成!** 现在您可以使用 DeepSeek V3 模型通过 Volces API 来生成 shell 命令了!

215
升级指南.md Normal file
View File

@ -0,0 +1,215 @@
# AI Shell 升级和更新指南
## 🚀 快速升级方法
### 方法一:直接重新安装(推荐)
```bash
# 在项目目录中
cd /path/to/ai-shell
# 重新构建并安装
uv build
uv tool install . --force
# 验证安装
ai --version
```
### 方法二:使用 uv tool upgrade
```bash
# 如果项目已发布到 PyPI
uv tool upgrade ai-shell
# 或者从本地项目升级
cd /path/to/ai-shell
uv tool upgrade ai-shell --from .
```
## 🔧 开发和版本管理
### 1. 修改代码后的升级流程
```bash
# 1. 修改代码(如 ai_shell/main.py, ai_shell/config.py 等)
# 2. 更新版本号
python scripts/bump_version.py patch # 0.1.0 -> 0.1.1
# 或
python scripts/bump_version.py minor # 0.1.0 -> 0.2.0
# 或
python scripts/bump_version.py major # 0.1.0 -> 1.0.0
# 3. 重新构建和安装
uv build
uv tool install . --force
# 4. 测试新版本
ai --version
ai --config
ai "test command"
```
### 2. 使用 Makefile 简化操作
```bash
# 查看所有可用命令
make help
# 升级补丁版本并重新安装
make bump-patch
make install
# 升级次版本并重新安装
make bump-minor
make install
# 清理构建文件
make clean
# 测试安装
make test
```
## 📝 常见升级场景
### 场景 1修改 API 配置
```bash
# 编辑配置文件
vim ai_shell/config.py
# 升级并重新安装
python scripts/bump_version.py patch
uv build
uv tool install . --force
```
### 场景 2添加新功能
```bash
# 编辑主程序
vim ai_shell/main.py
# 升级次版本
python scripts/bump_version.py minor
uv build
uv tool install . --force
```
### 场景 3修改依赖
```bash
# 编辑依赖
vim pyproject.toml
# 同步依赖
uv sync
# 重新安装
uv build
uv tool install . --force
```
## 🔍 验证升级
### 检查安装状态
```bash
# 查看已安装的工具
uv tool list
# 查看版本信息
ai --version
# 查看配置
ai --config
# 测试功能
ai "echo hello"
```
### 故障排除
```bash
# 如果命令不存在,检查 PATH
echo $PATH | grep -o ~/.local/bin
# 如果 PATH 中没有 ~/.local/bin添加到 shell 配置
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc
# 完全重新安装
uv tool uninstall ai-shell
uv tool install .
```
## 📦 版本管理最佳实践
### 1. 语义化版本控制
- **补丁版本** (0.1.0 -> 0.1.1): 修复 bug小改动
- **次版本** (0.1.0 -> 0.2.0): 新功能,向后兼容
- **主版本** (0.1.0 -> 1.0.0): 重大变更,可能不兼容
### 2. 升级前的检查清单
- [ ] 代码修改完成
- [ ] 测试功能正常
- [ ] 更新版本号
- [ ] 重新构建包
- [ ] 重新安装工具
- [ ] 验证新版本
### 3. 配置文件管理
```bash
# 查看当前配置
ai --config
# 如果需要修改 API 配置,编辑:
vim ai_shell/config.py
# 或者使用环境变量覆盖:
export AI_SHELL_API_KEY="new_api_key"
export AI_SHELL_BASE_URL="new_base_url"
export AI_SHELL_MODEL="new_model"
```
## 🎯 自动化升级脚本
创建一个一键升级脚本:
```bash
#!/bin/bash
# 保存为 quick_upgrade.sh
echo "🔄 AI Shell 快速升级..."
# 检查是否在项目目录
if [ ! -f "pyproject.toml" ]; then
echo "❌ 请在 ai-shell 项目目录中运行此脚本"
exit 1
fi
# 升级补丁版本
echo "📈 升级版本..."
python scripts/bump_version.py patch
# 重新构建
echo "📦 重新构建..."
uv build
# 重新安装
echo "🔧 重新安装..."
uv tool install . --force
# 验证
echo "✅ 升级完成!"
ai --version
echo "🧪 测试命令:"
echo "ai --config"
echo "ai \"echo test\""
```
使用方法:
```bash
chmod +x quick_upgrade.sh
./quick_upgrade.sh
```
---
💡 **总结**:最简单的升级方法就是在项目目录中运行 `uv build && uv tool install . --force`

157
配置修复总结.md Normal file
View File

@ -0,0 +1,157 @@
# 配置修复总结
## 🐛 问题描述
每次运行 `uv sync` 时,都会在项目目录中创建一个名为 `~` 的文件夹。
## 🔍 问题原因
`uv.toml` 配置文件中,`cache-dir = "~/.cache/uv"``~` 符号没有被正确展开uv 将其当作字面量处理,导致在当前目录创建了名为 `~` 的文件夹。
## ✅ 解决方案
### 1. 修复项目配置文件
**修改前** (`uv.toml`)
```toml
# 缓存目录
cache-dir = "~/.cache/uv"
```
**修改后** (`uv.toml`)
```toml
# 缓存目录(移除此配置,使用 uv 默认缓存位置)
# cache-dir = "~/.cache/uv"
```
### 2. 清理重复配置
**问题**`pyproject.toml``uv.toml` 中有重复的 uv 配置,导致警告信息。
**解决**:删除 `pyproject.toml` 中的 `[tool.uv]` 配置段,只保留 `uv.toml` 中的配置。
**修改前** (`pyproject.toml`)
```toml
[tool.uv]
# 使用国内镜像源加速下载
index-url = "https://pypi.tuna.tsinghua.edu.cn/simple"
extra-index-url = [
"https://mirrors.aliyun.com/pypi/simple/",
"https://mirrors.cloud.tencent.com/pypi/simple/",
]
index-strategy = "unsafe-best-match"
concurrent-downloads = 10
cache-dir = "~/.cache/uv"
```
**修改后** (`pyproject.toml`)
```toml
# UV 配置已移至 uv.toml 文件
```
### 3. 完善全局配置
创建正确的全局 uv 配置文件 `~/.config/uv/uv.toml`
```toml
# UV 全局配置文件
# 配置国内镜像源加速下载
# PyPI 镜像源配置
index-url = "https://pypi.tuna.tsinghua.edu.cn/simple"
extra-index-url = [
"https://mirrors.aliyun.com/pypi/simple/",
"https://mirrors.cloud.tencent.com/pypi/simple/",
]
# 性能优化配置
index-strategy = "unsafe-best-match"
concurrent-downloads = 10
# 注意:不要设置 cache-dir让 uv 使用默认位置
```
## 🧹 清理操作
1. **删除错误创建的目录**
```bash
rm -rf ./~
```
2. **验证修复效果**
```bash
uv sync
ls -la | grep "~" # 应该没有输出
```
## 📋 最佳实践
### 1. uv 缓存配置
- ✅ **推荐**:不设置 `cache-dir`,让 uv 使用默认位置
- ❌ **避免**:使用 `~` 符号,因为可能不被正确展开
- ✅ **替代**:如果必须自定义,使用绝对路径
### 2. 配置文件优先级
- `uv.toml` > `pyproject.toml` 中的 `[tool.uv]`
- 避免在两个文件中重复配置相同选项
### 3. 全局 vs 项目配置
- **全局配置** (`~/.config/uv/uv.toml`):适用于所有项目的通用设置
- **项目配置** (`项目目录/uv.toml`):特定项目的配置,会覆盖全局配置
## 🔧 当前配置状态
### 项目配置 (`uv.toml`)
```toml
# uv 项目配置文件
# 配置国内镜像源加速下载
# 主要的 PyPI 镜像源
index-url = "https://pypi.tuna.tsinghua.edu.cn/simple"
# 额外的镜像源
extra-index-url = [
"https://mirrors.aliyun.com/pypi/simple/",
"https://mirrors.cloud.tencent.com/pypi/simple/",
]
# 索引策略 - 允许从所有索引中选择最佳版本
index-strategy = "unsafe-best-match"
# 缓存目录(移除此配置,使用 uv 默认缓存位置)
# cache-dir = "~/.cache/uv"
# 并发下载数
concurrent-downloads = 10
```
### 全局配置 (`~/.config/uv/uv.toml`)
```toml
# UV 全局配置文件
# 配置国内镜像源加速下载
# PyPI 镜像源配置
index-url = "https://pypi.tuna.tsinghua.edu.cn/simple"
extra-index-url = [
"https://mirrors.aliyun.com/pypi/simple/",
"https://mirrors.cloud.tencent.com/pypi/simple/",
]
# 性能优化配置
index-strategy = "unsafe-best-match"
concurrent-downloads = 10
# 注意:不要设置 cache-dir让 uv 使用默认位置
```
## ✅ 验证结果
修复后运行 `uv sync`
- ✅ 不再创建 `~` 目录
- ✅ 没有重复配置警告
- ✅ 国内镜像源正常工作
- ✅ 依赖同步正常
---
💡 **总结**问题已完全解决uv 配置现在更加清晰和规范。

117
配置总结.md Normal file
View File

@ -0,0 +1,117 @@
# UV 国内源加速配置总结
## ✅ 配置完成状态
### 核心配置文件
- **uv.toml** - 主要配置文件 ⭐
- 清华大学镜像(主源)+ 阿里云、腾讯云(备源)
- 10个并发下载智能版本选择策略
- 已优化缓存配置
- **pyproject.toml** - 项目配置文件
- Python 版本:>=3.12(当前使用 3.12.11
- 核心依赖pydantic-ai, google-genai, requests
### 2. 配置的镜像源
| 镜像源 | URL | 状态 |
|--------|-----|------|
| 清华大学 | https://pypi.tuna.tsinghua.edu.cn/simple | 主源 ✅ |
| 阿里云 | https://mirrors.aliyun.com/pypi/simple/ | 备用 ✅ |
| 腾讯云 | https://mirrors.cloud.tencent.com/pypi/simple/ | 备用 ✅ |
### 3. 性能测试结果
- ✅ PyPI 包解析速度0.02秒(极快)
- ✅ 包安装速度:显著提升(使用国内镜像源)
- ✅ 配置文件检测:全部通过
- ✅ Python 版本3.12.11(已正确配置)
- ⚠️ Python 解释器下载:仍需要优化(建议使用系统包管理器)
## 🚀 使用方法
### 基本命令
```bash
# 安装依赖
uv sync
# 添加新包
uv add package-name
# 运行脚本
uv run python script.py
# 激活虚拟环境
uv shell
```
### 验证配置
```bash
# 运行测试脚本
uv run python test_uv_config.py
```
## 📁 当前项目结构
```
ai-shell/
├── ai.py # 主程序AI shell 命令生成器)
├── pyproject.toml # 项目配置文件
├── uv.toml # UV 配置文件(核心)
├── uv.lock # 依赖锁定文件(自动生成)
├── .python-version # Python 版本文件(自动生成)
├── .venv/ # 虚拟环境(自动生成)
├── README.md # 项目说明
├── 配置总结.md # 本文件
└── 项目配置说明.md # 详细配置说明
```
## 🎯 配置优势
1. **PyPI 包速度提升**:使用国内镜像源,包下载速度显著提升
2. **稳定性**:多个备用镜像源,确保可用性
3. **兼容性**:支持所有 uv 功能
4. **易维护**:配置文件清晰,易于修改
5. **版本管理**:正确配置 Python 版本要求,避免兼容性问题
## 🔧 故障排除
如果遇到问题:
1. **网络问题**:检查网络连接,尝试切换镜像源
2. **缓存问题**:运行 `uv cache clean` 清除缓存
3. **配置冲突**:确保 uv.toml 配置正确
## 📝 注意事项
- uv.toml 文件优先级高于 pyproject.toml 中的 [tool.uv] 配置
- 使用 unsafe-best-match 策略可能有安全风险,但提供更好的包版本选择
- 定期更新镜像源地址以确保最佳性能
## 🐍 关于 Python 解释器下载
**重要说明**
-**PyPI 包下载**:已成功配置国内镜像源,速度很快
- ⚠️ **Python 解释器下载**:镜像源配置复杂,建议使用以下替代方案:
### 推荐的 Python 版本管理方案:
1. **使用系统包管理器**`brew install python@3.12` (macOS)
2. **使用 pyenv**`pyenv install 3.12.0`
3. **使用 conda**`conda install python=3.12`
4. **使用现有版本**:您已有 Python 3.12.11,完全可用
### 如果必须用 uv 下载 Python
- 考虑使用代理:`export HTTPS_PROXY=your_proxy`
- 或者耐心等待Python 解释器文件较大,首次下载需要时间
---
🎉 **配置完成!现在您可以享受快速的 Python 包管理体验了!**
📋 **当前状态**
- ✅ PyPI 包下载:极快(国内镜像源)
- ✅ Python 版本3.12.11(已配置)
- ✅ 项目依赖:已同步完成

199
配置管理说明.md Normal file
View File

@ -0,0 +1,199 @@
# AI Shell 配置管理说明
## 🔐 敏感配置管理
### 1. 使用 .env 文件
项目现在使用 `.env` 文件来管理敏感配置,确保 API 密钥等信息不会被意外提交到代码库。
#### 配置文件结构:
```
ai-shell/
├── .env # 实际配置文件(已在 .gitignore 中排除)
├── .env.example # 配置模板文件(会被提交到代码库)
└── ai_shell/config.py # 配置加载逻辑
```
### 2. 配置文件内容
#### `.env` 文件(实际配置):
```bash
# AI Shell 配置文件
AI_SHELL_API_KEY=f8370a60-fe0a-455f-9167-411d476123d2
AI_SHELL_BASE_URL=https://ark.cn-beijing.volces.com/api/v3/
AI_SHELL_MODEL=deepseek-v3-250324
# 可选配置
AI_SHELL_TIMEOUT=30
AI_SHELL_MAX_RETRIES=3
```
#### `.env.example` 文件(模板):
```bash
# AI Shell 配置文件模板
AI_SHELL_API_KEY=your_api_key_here
AI_SHELL_BASE_URL=https://your-api-endpoint.com/v3/
AI_SHELL_MODEL=your_model_name
# 可选配置
AI_SHELL_TIMEOUT=30
AI_SHELL_MAX_RETRIES=3
```
## 🔧 配置加载优先级
配置系统按以下优先级加载配置:
1. **环境变量**(最高优先级)
2. **当前目录的 .env 文件**
3. **包目录的 .env 文件**
4. **~/.ai-shell/.env 文件**
5. **默认值**(最低优先级)
## 📋 配置项说明
| 配置项 | 环境变量 | 说明 | 默认值 |
|--------|----------|------|--------|
| API Key | `AI_SHELL_API_KEY` | API 密钥(必填) | 无 |
| Base URL | `AI_SHELL_BASE_URL` | API 基础 URL | `https://api.openai.com/v1/` |
| Model | `AI_SHELL_MODEL` | 模型名称 | `gpt-3.5-turbo` |
| Timeout | `AI_SHELL_TIMEOUT` | 请求超时时间(秒) | `30` |
| Max Retries | `AI_SHELL_MAX_RETRIES` | 最大重试次数 | `3` |
## 🚀 使用方法
### 1. 查看当前配置
```bash
ai --config
```
输出示例:
```
AI Shell Configuration:
Model: deepseek-v3-250324
Base URL: https://ark.cn-beijing.volces.com/api/v3/
API Key: f8370a60...123d2
Timeout: 30s
Max Retries: 3
Configuration Status: ✅ Valid
Configuration Sources (in priority order):
1. Environment variables
2. .env file in current directory
3. .env file in package directory
4. ~/.ai-shell/.env file
5. Default values
```
### 2. 修改配置
#### 方法 1编辑 .env 文件
```bash
# 编辑项目目录中的 .env 文件
vim .env
# 或创建全局配置
mkdir -p ~/.ai-shell
cp .env ~/.ai-shell/.env
vim ~/.ai-shell/.env
```
#### 方法 2使用环境变量
```bash
# 临时设置
export AI_SHELL_API_KEY="new_api_key"
export AI_SHELL_MODEL="gpt-4"
# 永久设置(添加到 shell 配置文件)
echo 'export AI_SHELL_API_KEY="new_api_key"' >> ~/.zshrc
```
### 3. 配置验证
程序启动时会自动验证配置:
```bash
ai "test command"
```
如果配置无效,会显示错误信息:
```
❌ Configuration error: API key not configured.
Please set AI_SHELL_API_KEY in .env file or environment variable.
Run 'ai --config' to see current configuration.
```
## 🔄 升级后的配置管理
### 升级流程:
1. **修改代码**
2. **更新版本**: `python scripts/bump_version.py patch`
3. **重新安装**: `uv build && uv tool install . --force`
4. **配置自动保留**`.env` 文件不会被覆盖
### 配置迁移:
如果需要迁移配置到新环境:
```bash
# 复制配置文件
cp .env /path/to/new/environment/
# 或设置环境变量
export AI_SHELL_API_KEY="your_key"
export AI_SHELL_BASE_URL="your_url"
export AI_SHELL_MODEL="your_model"
```
## 🛡️ 安全最佳实践
### 1. 保护 .env 文件
-`.env` 文件已在 `.gitignore` 中排除
- ✅ 不要将 `.env` 文件提交到代码库
- ✅ 使用 `.env.example` 作为模板
### 2. API 密钥管理
- 🔐 定期轮换 API 密钥
- 🔐 不要在代码中硬编码密钥
- 🔐 使用环境变量或配置文件
### 3. 权限控制
```bash
# 设置 .env 文件权限(仅所有者可读写)
chmod 600 .env
# 检查权限
ls -la .env
```
## 🔍 故障排除
### 常见问题:
1. **API 密钥未配置**
```bash
# 检查配置
ai --config
# 设置密钥
echo 'AI_SHELL_API_KEY=your_key' >> .env
```
2. **配置文件未找到**
```bash
# 创建配置文件
cp .env.example .env
vim .env
```
3. **权限问题**
```bash
# 检查文件权限
ls -la .env
# 修复权限
chmod 600 .env
```
---
💡 **总结**:现在 AI Shell 使用 `.env` 文件管理敏感配置,确保了安全性和可维护性。配置会在升级时自动保留,无需重新设置。

165
项目配置说明.md Normal file
View File

@ -0,0 +1,165 @@
# AI Shell 项目配置说明
## 📁 项目结构
```
ai-shell/
├── ai.py # 主程序文件
├── pyproject.toml # 项目配置文件
├── uv.toml # UV 包管理器配置文件
├── uv.lock # 依赖锁定文件(自动生成)
├── .python-version # Python 版本固定文件(自动生成)
├── .venv/ # 虚拟环境目录(自动生成)
├── README.md # 项目说明文档
├── 配置总结.md # 配置总结文档
└── 项目配置说明.md # 本文件
```
## 🔧 核心配置文件详解
### 1. `ai.py` - 主程序文件
**作用**AI 驱动的 shell 命令生成器
**功能**
- 使用 Gemini AI 模型生成 shell 命令
- 支持多语言提示和响应
- 交互式执行确认
**关键配置**
```python
# OpenAI 兼容接口配置
API_KEY = "f8370a60-fe0a-455f-9167-411d476123d2"
BASE_URL = "https://ark.cn-beijing.volces.com/api/v3/"
# 使用 DeepSeek V3 模型
model = OpenAIModel("deepseek-v3-250324")
```
### 2. `pyproject.toml` - 项目配置文件
**作用**:定义项目元数据和依赖关系
**内容解析**
```toml
[project]
name = "ai-shell" # 项目名称
version = "0.1.0" # 版本号
description = "AI-powered shell command generator" # 项目描述
requires-python = ">=3.12" # Python 版本要求
dependencies = [ # 项目依赖
"pydantic-ai", # AI 框架
"openai", # OpenAI 兼容 API 客户端
"requests>=2.32.4", # HTTP 请求库
]
```
### 3. `uv.toml` - UV 包管理器配置文件 ⭐
**作用**:配置 UV 包管理器的行为和镜像源
**重要性**:这是加速包下载的核心配置文件
**详细配置解析**
```toml
# PyPI 镜像源配置
index-url = "https://pypi.tuna.tsinghua.edu.cn/simple" # 主镜像源(清华大学)
extra-index-url = [ # 备用镜像源
"https://mirrors.aliyun.com/pypi/simple/", # 阿里云镜像
"https://mirrors.cloud.tencent.com/pypi/simple/", # 腾讯云镜像
]
# 性能优化配置
index-strategy = "unsafe-best-match" # 允许从所有镜像源选择最佳版本
concurrent-downloads = 10 # 并发下载数量
cache-dir = "~/.cache/uv" # 缓存目录
# Python 解释器镜像源(已注释,使用默认源)
# python-install-mirror = "镜像源URL"
```
### 4. `uv.lock` - 依赖锁定文件(自动生成)
**作用**:锁定所有依赖的精确版本
**特点**
- 自动生成,不需要手动编辑
- 确保在不同环境中安装相同版本的依赖
- 包含所有传递依赖的版本信息
### 5. `.python-version` - Python 版本固定文件(自动生成)
**作用**:指定项目使用的 Python 版本
**内容**`3.12`
**用途**:确保项目在正确的 Python 版本下运行
### 6. `.venv/` - 虚拟环境目录(自动生成)
**作用**:隔离的 Python 环境
**包含**
- 项目特定的 Python 解释器
- 安装的所有依赖包
- 环境配置文件
## 🚀 配置优势
### 1. 国内镜像源加速
- **主源**:清华大学镜像(教育网友好)
- **备源**:阿里云、腾讯云(商业网络友好)
- **效果**:包下载速度从几十秒降到秒级
### 2. 智能版本选择
- `index-strategy = "unsafe-best-match"`
- 从所有镜像源中选择最佳版本
- 避免版本冲突和依赖问题
### 3. 性能优化
- 10 个并发下载
- 本地缓存机制
- 快速依赖解析
## 📋 使用指南
### 基本命令
```bash
# 安装/更新依赖
uv sync
# 添加新依赖
uv add package-name
# 运行程序
uv run python ai.py "your command description"
# 激活虚拟环境
uv shell
```
### 环境管理
```bash
# 查看 Python 版本
uv python pin
# 查看已安装包
uv pip list
# 清理缓存
uv cache clean
```
## ⚠️ 注意事项
1. **配置优先级**`uv.toml` > `pyproject.toml` 中的 `[tool.uv]` 配置
2. **镜像源策略**:使用 `unsafe-best-match` 可能有安全风险,但提供更好的包选择
3. **Python 解释器**:下载新 Python 版本仍然较慢,建议使用系统包管理器
4. **API 配置**:已内置 Volces (ByteDance) API 配置,使用 DeepSeek V3 模型
## 🔍 故障排除
### 常见问题
1. **包下载慢**:检查网络连接,尝试切换镜像源
2. **版本冲突**:运行 `uv sync` 重新解析依赖
3. **缓存问题**:运行 `uv cache clean` 清理缓存
### 验证配置
```bash
# 测试依赖解析速度
time uv sync --dry-run
# 检查镜像源连通性
curl -I https://pypi.tuna.tsinghua.edu.cn/simple/
```
---
🎯 **总结**:这个配置实现了 Python 包的快速下载和管理,同时保持了项目的可移植性和稳定性。