refactor: 精简agent代码，移除冗余的main入口，添加API文档和note_agent
- root_agent/note_agent: 移除main()函数及不再需要的import（asyncio/Runner/SessionService/types） - root_agent: 更新agent名称为huiyu_agent，优化instruction - agents/__init__.py: 添加root_agent导出，供adk web/api_server注册 - 新增 API_DOC.md: 完整的API接口文档，供外部项目集成参考 - 新增 note_agent: 多模态笔记助手agent
This commit is contained in:
@@ -3,3 +3,8 @@ Agent 模块
|
||||
|
||||
每个 Agent 是一个独立的子目录，包含 agent.py 和 __init__.py。
|
||||
"""
|
||||
|
||||
# 导出所有 Agent，供 adk web 服务注册
|
||||
from .root_agent import agent as root_agent
|
||||
|
||||
__all__ = ["root_agent"]
|
||||
|
||||
8
agents/note_agent/__init__.py
Normal file
8
agents/note_agent/__init__.py
Normal file
@@ -0,0 +1,8 @@
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
|
||||
|
||||
from . import agent
|
||||
|
||||
__all__ = ["agent"]
|
||||
77
agents/note_agent/agent.py
Normal file
77
agents/note_agent/agent.py
Normal file
@@ -0,0 +1,77 @@
|
||||
import os
|
||||
|
||||
from base.agent import HuiYuBaseAgent
|
||||
from google.adk.models.lite_llm import LiteLlm
|
||||
from .note_formatter import NoteFormatter
|
||||
|
||||
# ============================================================
|
||||
# MiniMax 模型配置（从 .env 文件读取）
|
||||
# ============================================================
|
||||
MINIMAX_API_KEY = os.getenv("MINIMAX_API_KEY")
|
||||
MINIMAX_API_BASE = os.getenv("MINIMAX_API_BASE")
|
||||
MINIMAX_MODEL = os.getenv("MINIMAX_MODEL")
|
||||
|
||||
# ============================================================
|
||||
# 创建 LiteLlm 模型适配器
|
||||
# ============================================================
|
||||
model = LiteLlm(
|
||||
model=MINIMAX_MODEL,
|
||||
api_base=MINIMAX_API_BASE,
|
||||
api_key=MINIMAX_API_KEY,
|
||||
)
|
||||
|
||||
# ============================================================
|
||||
# 笔记格式化器
|
||||
# ============================================================
|
||||
_formatter = NoteFormatter()
|
||||
|
||||
|
||||
# ============================================================
|
||||
# Tool: 生成文本笔记
|
||||
# ============================================================
|
||||
def generate_text_note(title: str, content: str) -> str:
|
||||
"""将文本内容整理为 Markdown 笔记。
|
||||
|
||||
Args:
|
||||
title: 笔记标题
|
||||
content: 笔记正文内容
|
||||
"""
|
||||
return _formatter.format_to_markdown(title=title, text_content=content)
|
||||
|
||||
|
||||
# ============================================================
|
||||
# Tool: 生成图片笔记
|
||||
# ============================================================
|
||||
def generate_image_note(title: str, description: str) -> str:
|
||||
"""将图片描述整理为 Markdown 笔记。
|
||||
|
||||
Args:
|
||||
title: 笔记标题
|
||||
description: 图片描述或相关文字说明
|
||||
"""
|
||||
return _formatter.format_to_markdown(title=title, text_content=description)
|
||||
|
||||
|
||||
# ============================================================
|
||||
# 定义 Agent（继承 HuiYuBaseAgent）
|
||||
# ============================================================
|
||||
note_agent = HuiYuBaseAgent(
|
||||
name="note_agent",
|
||||
model=model,
|
||||
description="一个多模态笔记助手，能够将图片、文字等内容转换为结构化的 Markdown 笔记。",
|
||||
instruction=(
|
||||
"你是一个专业的笔记助手，帮助用户将各种内容整理成 Markdown 笔记。\n"
|
||||
"你的能力包括：\n"
|
||||
"1. 接收用户输入的文字内容，整理成结构化的笔记\n"
|
||||
"2. 接收用户上传的图片，生成图片描述并整理为笔记\n"
|
||||
"3. 将混合内容（文字+图片）整合为一份完整的笔记\n\n"
|
||||
"工作流程：\n"
|
||||
"- 当用户发送文字时，整理内容并调用 generate_text_note 生成笔记\n"
|
||||
"- 当用户发送图片时，描述图片内容并调用 generate_image_note 生成笔记\n"
|
||||
"- 当用户发送混合内容时，整合所有内容后生成笔记\n"
|
||||
"- 笔记标题由你根据内容自动生成，要简洁准确\n"
|
||||
"- 生成笔记后，直接将 Markdown 内容输出给用户\n"
|
||||
"- 回复时使用中文"
|
||||
),
|
||||
tools=[generate_text_note, generate_image_note],
|
||||
)
|
||||
208
agents/note_agent/note_formatter.py
Normal file
208
agents/note_agent/note_formatter.py
Normal file
@@ -0,0 +1,208 @@
|
||||
"""
|
||||
笔记格式化模块
|
||||
|
||||
将多模态内容（图片、文本等）转换为 Markdown 笔记格式。
|
||||
支持可扩展的处理器架构，方便后续添加音频、视频、PDF 等格式。
|
||||
"""
|
||||
|
||||
import base64
|
||||
import hashlib
|
||||
import logging
|
||||
from abc import ABC, abstractmethod
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
logger = logging.getLogger("adk.agent")
|
||||
|
||||
|
||||
# ============================================================
|
||||
# 内容处理器基类
|
||||
# ============================================================
|
||||
class BaseContentHandler(ABC):
|
||||
"""内容处理器基类，所有格式处理器继承此类。"""
|
||||
|
||||
@abstractmethod
|
||||
def can_handle(self, mime_type: str) -> bool:
|
||||
"""判断是否能处理该 MIME 类型"""
|
||||
...
|
||||
|
||||
@abstractmethod
|
||||
def process(self, data: bytes, mime_type: str, filename: str = "") -> str:
|
||||
"""
|
||||
处理内容并返回 Markdown 片段。
|
||||
|
||||
Args:
|
||||
data: 原始字节数据
|
||||
mime_type: MIME 类型
|
||||
filename: 文件名（可选）
|
||||
|
||||
Returns:
|
||||
Markdown 格式的字符串片段
|
||||
"""
|
||||
...
|
||||
|
||||
|
||||
# ============================================================
|
||||
# 图片处理器
|
||||
# ============================================================
|
||||
class ImageHandler(BaseContentHandler):
|
||||
"""处理图片类型，保存到本地并生成 Markdown 图片引用。"""
|
||||
|
||||
SUPPORTED_TYPES = {"image/png", "image/jpeg", "image/jpg", "image/gif", "image/webp", "image/svg+xml"}
|
||||
|
||||
def can_handle(self, mime_type: str) -> bool:
|
||||
return mime_type.lower() in self.SUPPORTED_TYPES
|
||||
|
||||
def process(self, data: bytes, mime_type: str, filename: str = "") -> str:
|
||||
# 确保输出目录存在
|
||||
NOTES_OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# 生成文件名
|
||||
if not filename:
|
||||
ext = self._mime_to_ext(mime_type)
|
||||
filename = f"image_{datetime.now().strftime('%Y%m%d_%H%M%S')}_{hashlib.md5(data).hexdigest()[:8]}.{ext}"
|
||||
|
||||
filepath = NOTES_OUTPUT_DIR / filename
|
||||
filepath.write_bytes(data)
|
||||
|
||||
logger.info("图片已保存: %s", filepath)
|
||||
return f""
|
||||
|
||||
@staticmethod
|
||||
def _mime_to_ext(mime_type: str) -> str:
|
||||
return {
|
||||
"image/png": "png",
|
||||
"image/jpeg": "jpg",
|
||||
"image/jpg": "jpg",
|
||||
"image/gif": "gif",
|
||||
"image/webp": "webp",
|
||||
"image/svg+xml": "svg",
|
||||
}.get(mime_type.lower(), "bin")
|
||||
|
||||
|
||||
# ============================================================
|
||||
# 文本处理器
|
||||
# ============================================================
|
||||
class TextHandler(BaseContentHandler):
|
||||
"""处理纯文本内容。"""
|
||||
|
||||
SUPPORTED_TYPES = {"text/plain", "text/markdown", "text/csv"}
|
||||
|
||||
def can_handle(self, mime_type: str) -> bool:
|
||||
return mime_type.lower() in self.SUPPORTED_TYPES
|
||||
|
||||
def process(self, data: bytes, mime_type: str, filename: str = "") -> str:
|
||||
text = data.decode("utf-8", errors="replace")
|
||||
if mime_type.lower() == "text/markdown":
|
||||
return text # 已经是 Markdown，直接返回
|
||||
return text # 纯文本直接返回
|
||||
|
||||
|
||||
# ============================================================
|
||||
# 占位处理器（用于尚未支持的格式）
|
||||
# ============================================================
|
||||
class PlaceholderHandler(BaseContentHandler):
|
||||
"""占位处理器，为尚未支持的格式生成占位标记。"""
|
||||
|
||||
def can_handle(self, mime_type: str) -> bool:
|
||||
return True # 兜底，处理所有未匹配的类型
|
||||
|
||||
def process(self, data: bytes, mime_type: str, filename: str = "") -> str:
|
||||
name = filename or "unsupported_file"
|
||||
return f"<!-- [{name}] 格式 {mime_type} 暂不支持，待后续扩展 -->"
|
||||
|
||||
|
||||
# ============================================================
|
||||
# 笔记格式化器
|
||||
# ============================================================
|
||||
class NoteFormatter:
|
||||
"""
|
||||
笔记格式化器，管理所有内容处理器。
|
||||
|
||||
用法：
|
||||
formatter = NoteFormatter()
|
||||
md_content = formatter.format_to_markdown(
|
||||
title="会议笔记",
|
||||
text_content="讨论了项目进度",
|
||||
files=[(image_bytes, "image/png", "screenshot.png")],
|
||||
)
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self._handlers: list[BaseContentHandler] = [
|
||||
ImageHandler(),
|
||||
TextHandler(),
|
||||
PlaceholderHandler(), # 必须放最后，作为兜底
|
||||
]
|
||||
|
||||
def add_handler(self, handler: BaseContentHandler):
|
||||
"""注册新的内容处理器（插入到占位处理器之前）"""
|
||||
# 移除末尾的 PlaceholderHandler
|
||||
if self._handlers and isinstance(self._handlers[-1], PlaceholderHandler):
|
||||
self._handlers.pop()
|
||||
self._handlers.append(handler)
|
||||
# 重新添加 PlaceholderHandler 到末尾
|
||||
self._handlers.append(PlaceholderHandler())
|
||||
|
||||
def _find_handler(self, mime_type: str) -> BaseContentHandler:
|
||||
for handler in self._handlers:
|
||||
if handler.can_handle(mime_type):
|
||||
return handler
|
||||
return self._handlers[-1] # PlaceholderHandler
|
||||
|
||||
def format_to_markdown(
|
||||
self,
|
||||
title: str = "",
|
||||
text_content: str = "",
|
||||
files: Optional[list[tuple[bytes, str, str]]] = None,
|
||||
) -> str:
|
||||
"""
|
||||
将多模态内容格式化为 Markdown 笔记。
|
||||
|
||||
Args:
|
||||
title: 笔记标题
|
||||
text_content: 文本内容
|
||||
files: 文件列表，每项为 (data, mime_type, filename)
|
||||
|
||||
Returns:
|
||||
完整的 Markdown 笔记字符串
|
||||
"""
|
||||
lines: list[str] = []
|
||||
now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
|
||||
# 标题
|
||||
if title:
|
||||
lines.append(f"# {title}")
|
||||
lines.append("")
|
||||
else:
|
||||
lines.append(f"# 笔记 - {now}")
|
||||
lines.append("")
|
||||
|
||||
# 元信息
|
||||
lines.append(f"> 创建时间：{now}")
|
||||
lines.append("")
|
||||
|
||||
# 文本内容
|
||||
if text_content:
|
||||
lines.append("## 内容")
|
||||
lines.append("")
|
||||
lines.append(text_content)
|
||||
lines.append("")
|
||||
|
||||
# 附件
|
||||
if files:
|
||||
lines.append("## 附件")
|
||||
lines.append("")
|
||||
for data, mime_type, filename in files:
|
||||
handler = self._find_handler(mime_type)
|
||||
try:
|
||||
md_fragment = handler.process(data, mime_type, filename)
|
||||
lines.append(md_fragment)
|
||||
lines.append("")
|
||||
except Exception as e:
|
||||
logger.error("处理文件失败: %s, 错误: %s", filename, e)
|
||||
lines.append(f"<!-- 文件 {filename} 处理失败: {e} -->")
|
||||
lines.append("")
|
||||
|
||||
return "\n".join(lines)
|
||||
@@ -1,11 +1,7 @@
|
||||
import os
|
||||
import asyncio
|
||||
|
||||
from base.agent import HuiYuBaseAgent
|
||||
from google.adk.models.lite_llm import LiteLlm
|
||||
from google.adk.sessions import InMemorySessionService
|
||||
from google.adk.runners import Runner
|
||||
from google.genai import types
|
||||
|
||||
# ============================================================
|
||||
# MiniMax 模型配置（从 .env 文件读取）
|
||||
@@ -27,67 +23,8 @@ model = LiteLlm(
|
||||
# 定义 Agent（继承 HuiYuBaseAgent，自动获得防注入 + 日志能力）
|
||||
# ============================================================
|
||||
root_agent = HuiYuBaseAgent(
|
||||
name="minimax_agent",
|
||||
name="huiyu_agent",
|
||||
model=model,
|
||||
description="一个使用 MiniMax 模型的智能助手，能够回答用户的各种问题。",
|
||||
instruction="你是一个乐于助人的中文 AI 助手，由 MiniMax 模型驱动。请用中文回答用户的问题，回答要准确、简洁、友好。",
|
||||
description="一个智能助手，能够回答用户的各种问题。",
|
||||
instruction="你是一个乐于助人的中文 AI 助手，你的名字叫小慧，请用中文回答用户的问题，回答要准确、简洁、友好。",
|
||||
)
|
||||
|
||||
# ============================================================
|
||||
# 运行入口（用于 adk run / adk web）
|
||||
# ============================================================
|
||||
APP_NAME = "慧遇agent app"
|
||||
USER_ID = "user_001"
|
||||
SESSION_ID = "session_001"
|
||||
|
||||
|
||||
async def main():
|
||||
"""主函数：创建会话并运行 Agent 对话"""
|
||||
# 1. 创建会话服务
|
||||
session_service = InMemorySessionService()
|
||||
|
||||
# 2. 创建会话
|
||||
session = await session_service.create_session(
|
||||
app_name=APP_NAME,
|
||||
user_id=USER_ID,
|
||||
session_id=SESSION_ID,
|
||||
)
|
||||
print(f"会话已创建: App='{APP_NAME}', User='{USER_ID}', Session='{SESSION_ID}'")
|
||||
|
||||
# 3. 创建 Runner
|
||||
runner = Runner(
|
||||
agent=root_agent,
|
||||
app_name=APP_NAME,
|
||||
session_service=session_service,
|
||||
)
|
||||
print(f"Runner 已创建，Agent: '{runner.agent.name}'")
|
||||
|
||||
# 4. 交互式对话循环
|
||||
print("\n===== MiniMax Agent 对话 (输入 'exit' 退出) =====")
|
||||
while True:
|
||||
query = input("\n[user]: ").strip()
|
||||
if query.lower() in ("exit", "quit", "退出"):
|
||||
print("再见！")
|
||||
break
|
||||
if not query:
|
||||
continue
|
||||
|
||||
# 构造 ADK 消息
|
||||
content = types.Content(role="user", parts=[types.Part(text=query)])
|
||||
|
||||
# 调用 Agent
|
||||
final_response_text = ""
|
||||
async for event in runner.run_async(
|
||||
user_id=USER_ID,
|
||||
session_id=SESSION_ID,
|
||||
new_message=content,
|
||||
):
|
||||
if event.is_final_response():
|
||||
if event.content and event.content.parts:
|
||||
final_response_text = event.content.parts[0].text
|
||||
|
||||
print(f"\n[agent]: {final_response_text}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
|
||||
Reference in New Issue
Block a user