AI / ML領域相關學習筆記入口頁面

Deeplearning.ai GenAI/LLM系列課程筆記

GenAI

• Large Language Models with Semantic Search。大型語言模型與語義搜索
• LangChain for LLM Application Development。使用LangChain進行LLM應用開發
• Finetuning Large Language Models。微調大型語言模型

RAG

• Preprocessing Unstructured Data for LLM Applications。大型語言模型(LLM)應用的非結構化資料前處理
• Building and Evaluating Advanced RAG。建立與評估進階RAG
• [GenAI][RAG] Multi-Modal Retrieval-Augmented Generation and Evaluaion。多模態的RAG與評估
  

AI Agents

原理可參考這篇綜論: How Agents for LLM Perform Task Planning。大型語言模型的代理如何進行任務規劃

• 相關framework選擇
  • AI Agents in LangGraph
  • Building Agentic RAG with LlamaIndex
  • Multi AI Agent Systems with crewAI
  • Functions, Tools and Agents with LangChain
• Agent相關
  • Long-Term Agentic Memory With LangGraph

---

Long-Term Agentic Memory With LangGraph

• Introduction to Agent Memory
• Baseline Email Assistant、Email Assistant with Semantic Memory
• Email Assistant with Semantic + Episodic Memory
• Email Assistant with Semantic + Episodic + Procedural Memory

---

Baseline Email Assistant

from langgraph.graph import StateGraph, START, END
from langgraph.types import Command
from typing import Literal
from IPython.display import Image, display
email_agent = StateGraph(State)
email_agent = email_agent.add_node(triage_router)
email_agent = email_agent.add_node("response_agent", agent)
email_agent = email_agent.add_edge(START, "triage_router")
email_agent = email_agent.compile()

Define the first part of the agent - triage.

根據 Lesson 2_Baseline Email Assistant.ipynb 中的段落 ## Define the first part of the agent - triage.，以下是詳細的執行流程和參數的 mermaid 流程圖：

triage_router

def triage_router(state: State) -> Command[
    Literal["response_agent", "__end__"]
]:
    author = state['email_input']['author']
    to = state['email_input']['to']
    subject = state['email_input']['subject']
    email_thread = state['email_input']['email_thread']

    system_prompt = triage_system_prompt.format(
        full_name=profile["full_name"],
        name=profile["name"],
        user_profile_background=profile["user_profile_background"],
        triage_no=prompt_instructions["triage_rules"]["ignore"],
        triage_notify=prompt_instructions["triage_rules"]["notify"],
        triage_email=prompt_instructions["triage_rules"]["respond"],
        examples=None
    )
    user_prompt = triage_user_prompt.format(
        author=author, 
        to=to, 
        subject=subject, 
        email_thread=email_thread
    )
    result = llm_router.invoke(
        [
            {"role": "system", "content": system_prompt},
            {"role": "user", "content": user_prompt},
        ]
    )
    if result.classification == "respond":
        print("📧 Classification: RESPOND - This email requires a response")
        goto = "response_agent"
        update = {
            "messages": [
                {
                    "role": "user",
                    "content": f"Respond to the email {state['email_input']}",
                }
            ]
        }
    elif result.classification == "ignore":
        print("🚫 Classification: IGNORE - This email can be safely ignored")
        update = None
        goto = END
    elif result.classification == "notify":
        # If real life, this would do something else
        print("🔔 Classification: NOTIFY - This email contains important information")
        update = None
        goto = END
    else:
        raise ValueError(f"Invalid classification: {result.classification}")
    return Command(goto=goto, update=update)

• triage_router 的詳細工作流程：

  1. Start: 開始處理電子郵件。
  2. Extract Email Details: 提取電子郵件的詳細信息，包括作者、收件人、主題和郵件內容。
  3. Format System Prompt: 格式化系統提示，填充用戶的詳細信息和分類規則。
  4. Format User Prompt: 格式化用戶提示，填充郵件的詳細信息。
  5. Invoke LLM Router: 調用 LLM 路由器，傳遞系統提示和用戶提示。
  6. Classification Result: 根據 LLM 路由器的結果進行分類。
     • Respond: 如果分類為回應，則生成回應內容，更新消息並轉到回應代理。
     • Ignore: 如果分類為忽略，忽略消息並結束流程。
     • Notify: 如果分類為通知，通知消息並結束流程。
  7. End: 結束流程。

Main agent, define tools

根據程式碼段落 ## Main agent, define tools，以下是詳細的執行流程和參數的 mermaid 流程圖：

@tool
def write_email(to: str, subject: str, content: str) -> str:
    """Write and send an email."""
    # 實際應用中會真的發送郵件
    return f"Email sent to {to} with subject '{subject}'"

@tool
def schedule_meeting(attendees: list[str], subject: str, duration_minutes: int, preferred_day: str) -> str:
    """Schedule a calendar meeting."""
    # 實際應用中會確認行事曆並安排會議
    return f"Meeting '{subject}' scheduled for {preferred_day} with {len(attendees)} attendees"

@tool
def check_calendar_availability(day: str) -> str:
    """Check calendar availability for a given day."""
    # 實際應用中會檢查真實的行事曆
    return f"Available times on {day}: 9:00 AM, 2:00 PM, 4:00 PM"

mermaid 流程圖：

#### Main agent, define tools 的詳細執行流程和參數：

1. Define Tools: 定義工具。
2. Define write_email: 定義 write_email 工具。
   • Input: 接受 to（收件人）、subject（主題）和 content（內容）作為輸入參數。
   • Output: 返回郵件發送確認信息。
3. Define schedule_meeting: 定義 schedule_meeting 工具。
   • Input: 接受 attendees（參加者列表）、subject（主題）、duration_minutes（持續時間）和 preferred_day（首選日期）作為輸入參數。
   • Output: 返回會議安排確認信息。
4. Define check_calendar_availability: 定義 check_calendar_availability 工具。
   • Input: 接受 day（日期）作為輸入參數。
   • Output: 返回可用時間信息。

prompts

Prompt 名稱	差異	輸入	輸出
agent_system_prompt	基本代理提示，包含基本工具	{full_name}, {name}, {instructions}	格式化的系統提示
triage_system_prompt	分類郵件的提示，包含分類規則	{full_name}, {name}, {user_profile_background}, {triage_no}, {triage_notify}, {triage_email}, {examples}	格式化的系統提示，包含分類規則和示例
triage_user_prompt	用戶提示，用於分類郵件	{author}, {to}, {subject}, {email_thread}	格式化的用戶提示，包含郵件詳細信息

---

Email Assistant with Semantic Memory

在Response_Agent中加入manage_memory_tool 與create_manage_memory_tool

tools= [
    write_email, 
    schedule_meeting,
    check_calendar_availability,
    manage_memory_tool,  # 新增記憶管理工具
    search_memory_tool   # 新增記憶搜尋工具
]

create_manage_memory_tool() 與 create_search_memory_tool()

🔹 create_manage_memory_tool()

• 🔧 功能
  此工具的目的是將使用者的行為、互動、指示等資訊儲存在記憶系統中，使 Email Assistant 在未來的互動中可以參考這些記憶來提供更個人化的回應。`

def create_manage_memory_tool():
    def manage_memory(memory_type, user, data_type, content):
        """
        Stores user behavior, instructions, or profile data in memory.
        """
        # 記憶儲存邏輯
        memory_store[memory_type][user][data_type] = content
        return f"Successfully stored {data_type} in {memory_type} for {user}"
    
    return manage_memory

---

🔹 create_search_memory_tool()

• 🔧 功能
  此工具的目的是在記憶系統中搜尋與過往互動、郵件或行為相關的資料，幫助 Email Assistant 根據過去的資訊提供更智慧的回應。

def create_search_memory_tool():
    def search_memory(memory_type, user, data_type, query):
        """
        Searches stored memory for specific information.
        """
        # 搜尋邏輯
        results = memory_store[memory_type][user][data_type].get(query, "No matching record found.")
        return results
    
    return search_memory

功能/特性	create_manage_memory_tool()	create_search_memory_tool()
目的	儲存使用者資訊、行為或指示	搜尋使用者過去的資訊
輸入參數 (Parameters)	memory_type, user, data_type, content	memory_type, user, data_type, query
輸出 (Output)	儲存成功訊息或錯誤提示	搜尋結果或「無結果」提示
應用場景 (Use Case)	儲存指示、行為偏好、個人化資訊	檢索過往郵件、過往指示或互動記錄

---

agent_system_prompt 與 agent_system_prompt_memory 的差異

# Agent prompt baseline 
agent_system_prompt = """
< Role >
You are {full_name}'s executive assistant. You are a top-notch executive assistant who cares about {name} performing as well as possible.
</ Role >

< Tools >
You have access to the following tools to help manage {name}'s communications and schedule:

1. write_email(to, subject, content) - Send emails to specified recipients
2. schedule_meeting(attendees, subject, duration_minutes, preferred_day) - Schedule calendar meetings
3. check_calendar_availability(day) - Check available time slots for a given day
</ Tools >

< Instructions >
{instructions}
</ Instructions >
"""

# Agent prompt semantic memory
agent_system_prompt_memory = """
...

< Tools >
...
4. manage_memory("email_assistant", user, "collection") - Store any relevant information about contacts, actions, discussion, etc. in memory for future reference
5. manage_memory("email_assistant", user, "user_profile") - Store any relevant information about the recipient, {name}, in the user profile for future reference the current user profile is shown below
6. search_memory("email_assistant", user, "collection") - Search memory for detail from previous emails
7. manage_memory("email_assistant", user, "instructions") - Update the instructions for agent tool usage based upon the user feedback 
</ Tools >
...

特點/功能	agent_system_prompt	agent_system_prompt_memory
額外工具 (Memory Tools)	❌ 無額外的記憶管理工具。	✅ 4 個額外工具： 4. manage_memory("collection") 5. manage_memory("user_profile") 6. search_memory("collection") 7. manage_memory("instructions")
使用者檔案 (User Profile)	❌ 未包含 profile (用戶偏好、背景等個人化資訊)。	✅ 包含 profile，用於儲存使用者的背景、喜好與行為資訊。

---