使用 LangGraph 代理程式

除了使用代理程式的一般操作說明外，本頁還會說明 LanggraphAgent 專屬的功能。

事前準備

本教學課程假設您已閱讀並遵循以下說明：

支援的作業

LanggraphAgent 支援下列作業：

串流傳送查詢的回應

LangGraph 支援多種串流模式。主要原因如下：

  • values：這個模式會在呼叫每個節點後，串流傳輸圖表的完整狀態。
  • updates：這個模式會在每個節點呼叫後，將更新串流至圖表狀態。

如要串流回 values (對應於圖表的完整狀態)：

for state_values in agent.stream_query(
    input=inputs,
    stream_mode="values",
    config={"configurable": {"thread_id": "streaming-thread-values"}},
):
    print(state_values)

如要串流回 updates (對應圖表狀態的更新)：

for state_updates in agent.stream_query(
    input=inputs,
    stream_mode="updates",
    config={"configurable": {"thread_id": "streaming-thread-updates"}},
):
    print(state_updates)

人機迴圈

在 LangGraph 中，人為介入的常見做法是新增中斷點，以便中斷服務機器人執行的動作序列，並讓人為介入在稍後時間點恢復流程。

查看

呼叫 .query 或 .stream_query 時，您可以使用 interrupt_before= 或 interrupt_after= 引數設定中斷點：

response = agent.query(
    input=inputs,
    interrupt_before=["tools"], # after generating the function call, before invoking the function
    interrupt_after=["tools"], # after getting a function response, before moving on
    config={"configurable": {"thread_id": "human-in-the-loop-deepdive"}},
)

langchain_load(response['messages'][-1]).pretty_print()

輸出內容會與以下內容類似：

================================== Ai Message ==================================
Tool Calls:
  get_exchange_rate (12610c50-4465-4296-b1f3-d751ec959fd5)
 Call ID: 12610c50-4465-4296-b1f3-d751ec959fd5
  Args:
    currency_from: USD
    currency_to: SEK

核准

如要核准產生的工具呼叫，並在執行其餘部分時繼續執行，請將 None 傳入輸入內容，並在 config 中指定執行緒或檢查點：

response = agent.query(
    input=None,  # Continue with the function call
    interrupt_before=["tools"], # after generating the function call, before invoking the function
    interrupt_after=["tools"], # after getting a function response, before moving on
    config={"configurable": {"thread_id": "human-in-the-loop-deepdive"}},
)

langchain_load(response['messages'][-1]).pretty_print()

輸出內容會與下列內容類似：

================================= Tool Message =================================
Name: get_exchange_rate

{"amount": 1.0, "base": "USD", "date": "2024-11-14", "rates": {"SEK": 11.0159}}

記錄

如要列出特定執行緒的所有檢查點，請使用 .get_state_history 方法：

for state_snapshot in agent.get_state_history(
    config={"configurable": {"thread_id": "human-in-the-loop-deepdive"}},
):
    if state_snapshot["metadata"]["step"] >= 0:
        print(f'step {state_snapshot["metadata"]["step"]}: {state_snapshot["config"]}')
        state_snapshot["values"]["messages"][-1].pretty_print()
        print("\n")

回應會類似以下輸出序列：

step 3: {'configurable': {'thread_id': 'human-in-the-loop-deepdive', 'checkpoint_ns': '', 'checkpoint_id': '1efa2e95-ded5-67e0-8003-2d34e04507f5'}}
================================== Ai Message ==================================

The exchange rate from US dollars to Swedish krona is 1 USD to 11.0159 SEK.

step 2: {'configurable': {'thread_id': 'human-in-the-loop-deepdive', 'checkpoint_ns': '', 'checkpoint_id': '1efa2e95-d189-6a77-8002-5dbe79e2ce58'}}
================================= Tool Message =================================
Name: get_exchange_rate

{"amount": 1.0, "base": "USD", "date": "2024-11-14", "rates": {"SEK": 11.0159}}

step 1: {'configurable': {'thread_id': 'human-in-the-loop-deepdive', 'checkpoint_ns': '', 'checkpoint_id': '1efa2e95-cc7f-6d68-8001-1f6b5e57c456'}}
================================== Ai Message ==================================
Tool Calls:
  get_exchange_rate (12610c50-4465-4296-b1f3-d751ec959fd5)
 Call ID: 12610c50-4465-4296-b1f3-d751ec959fd5
  Args:
    currency_from: USD
    currency_to: SEK

step 0: {'configurable': {'thread_id': 'human-in-the-loop-deepdive', 'checkpoint_ns': '', 'checkpoint_id': '1efa2e95-c2e4-6f3c-8000-477fd654cb53'}}
================================ Human Message =================================

What is the exchange rate from US dollars to Swedish currency?

取得步驟的設定

如要取得較早的檢查點，請指定 checkpoint_id (和 checkpoint_ns)。首先，請倒轉至產生工具呼叫的步驟 1：

snapshot_config = {}
for state_snapshot in agent.get_state_history(
    config={"configurable": {"thread_id": "human-in-the-loop-deepdive"}},
):
    if state_snapshot["metadata"]["step"] == 1:
        snapshot_config = state_snapshot["config"]
        break

print(snapshot_config)

輸出內容會與以下內容類似：

{'configurable': {'thread_id': 'human-in-the-loop-deepdive',
  'checkpoint_ns': '',
  'checkpoint_id': '1efa2e95-cc7f-6d68-8001-1f6b5e57c456'}}

時光旅行

如要取得檢查點，可以使用 .get_state 方法：

# By default, it gets the latest state [unless (checkpoint_ns, checkpoint_id) is specified]
state = agent.get_state(config={"configurable": {
    "thread_id": "human-in-the-loop-deepdive",
}})

print(f'step {state["metadata"]["step"]}: {state["config"]}')
state["values"]["messages"][-1].pretty_print()

根據預設，系統會取得最新的查核點 (依時間戳記)。輸出內容會與下列內容類似：

step 3: {'configurable': {'thread_id': 'human-in-the-loop-deepdive', 'checkpoint_ns': '', 'checkpoint_id': '1efa2e95-ded5-67e0-8003-2d34e04507f5'}}
================================== Ai Message ==================================

The exchange rate from US dollars to Swedish krona is 1 USD to 11.0159 SEK.

取得設定的查核點

針對特定設定 (例如步驟的設定中的 snapshot_config)，您可以取得對應的檢查點：

state = agent.get_state(config=snapshot_config)
print(f'step {state["metadata"]["step"]}: {state["config"]}')
state["values"]["messages"][-1].pretty_print()

輸出內容會與下列內容類似：

step 1: {'configurable': {'thread_id': 'human-in-the-loop-deepdive', 'checkpoint_ns': '', 'checkpoint_id': '1efa2e95-cc7f-6d68-8001-1f6b5e57c456'}}
================================== Ai Message ==================================
Tool Calls:
  get_exchange_rate (12610c50-4465-4296-b1f3-d751ec959fd5)
 Call ID: 12610c50-4465-4296-b1f3-d751ec959fd5
  Args:
    currency_from: USD
    currency_to: SEK

重播

如要從特定狀態重播，請將狀態設定 (即 state["config"]) 傳遞至代理程式。狀態設定是字典，如下所示：

{'configurable': {'thread_id': 'human-in-the-loop-deepdive',
  'checkpoint_ns': '',
  'checkpoint_id': '1efa2e95-cc7f-6d68-8001-1f6b5e57c456'}}

如要從 state["config"] (產生工具呼叫的位置) 重播，請在輸入內容中指定 None：

for state_values in agent.stream_query(
    input=None, # resume
    stream_mode="values",
    config=state["config"],
):
    langchain_load(state_values["messages"][-1]).pretty_print()

輸出結果會類似以下序列：

================================== Ai Message ==================================
Tool Calls:
  get_exchange_rate (12610c50-4465-4296-b1f3-d751ec959fd5)
 Call ID: 12610c50-4465-4296-b1f3-d751ec959fd5
  Args:
    currency_from: USD
    currency_to: SEK

================================= Tool Message =================================
Name: get_exchange_rate

{"amount": 1.0, "base": "USD", "date": "2024-11-14", "rates": {"SEK": 11.0159}}

================================== Ai Message ==================================

The exchange rate from US dollars to Swedish krona is 1 USD to 11.0159 SEK.

分支

您可以使用 .update_state 方法，從先前的檢查點分支，嘗試其他情境：

branch_config = agent.update_state(
    config=state["config"],
    values={"messages": [last_message]}, # the update we want to make
)

print(branch_config)

輸出內容會與下列內容類似：

{'configurable': {'thread_id': 'human-in-the-loop-deepdive',
  'checkpoint_ns': '',
  'checkpoint_id': '1efa2e96-0560-62ce-8002-d1bb48a337bc'}}

我們可以使用 branch_config 查詢代理程式，從查核點以更新後的狀態繼續執行：

for state_values in agent.stream_query(
    input=None, # resume
    stream_mode="values",
    config=branch_config,
):
    langchain_load(state_values["messages"][-1]).pretty_print()

輸出結果會類似以下序列：

================================== Ai Message ==================================
Tool Calls:
  get_exchange_rate (12610c50-4465-4296-b1f3-d751ec959fd5)
 Call ID: 12610c50-4465-4296-b1f3-d751ec959fd5
  Args:
    currency_date: 2024-09-01
    currency_from: USD
    currency_to: SEK

================================= Tool Message =================================
Name: get_exchange_rate

{"amount": 1.0, "base": "USD", "date": "2024-08-30", "rates": {"SEK": 10.2241}}

================================== Ai Message ==================================

The exchange rate from US dollars to Swedish krona on 2024-08-30 was 1 USD to 10.2241 SEK.

後續步驟