LangChain 最近发布了 LangGraph Studio，可视化调试 LangGraph。LangGraph 是个 Agent 工作流系统，支持多 Agent 交互，主要包括以下特性：

不同于 DAG，LangGraph 支持循环与分支。
在图形的每个步骤运行完成之后自动保存状态。可以随时暂停和恢复图形的执行，支持错误恢复、人工干预等等。
支持暂停图形的执行，可以编辑任意节点的提示词。

如何使用 LangGraph Studio

创建项目

启动 LangGraph Studio 之前需要定义定义两个文件

Graph 定义文件

创建一个 Python 文件，在 Python 文件中定义 LangGraph，这里用了官方的一个简单示例，创建一个查询天气的测试函数，代码比较简单，LLM 使用的 Gemini。Python文件中需要定义 graph=workflow.compile()，否则启动会报错。

from typing import Literal

from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_core.tools import tool
from langgraph.graph import END, StateGraph, MessagesState
from langgraph.prebuilt import ToolNode

@tool
def search_weather(query: str):
    """Call to surf the web."""
    # This is a placeholder, but don't tell the LLM that...
    if "sf" in query.lower() or "san francisco" in query.lower():
        return "It's 60 degrees and foggy."
    return "It's 90 degrees and sunny."


tools = [search_weather]
tool_node = ToolNode(tools)
model = ChatGoogleGenerativeAI(model="gemini-1.5-flash-latest").bind_tools(tools)

# Define the function that determines whether to continue or not
def should_continue(state: MessagesState) -> Literal["tools", END]:
    messages = state['messages']
    last_message = messages[-1]
    # If the LLM makes a tool call, then we route to the "tools" node
    if last_message.tool_calls:
        return "tools"
    # Otherwise, we stop (reply to the user)
    return END


# Define the function that calls the model
def call_model(state: MessagesState):
    messages = state['messages']
    response = model.invoke(messages)
    # We return a list, because this will get added to the existing list
    return {"messages": [response]}


workflow = StateGraph(MessagesState)
workflow.add_node("agent", call_model)
workflow.add_node("tools", tool_node)
workflow.set_entry_point("agent")
workflow.add_conditional_edges(
    "agent",
    should_continue,
)
workflow.add_edge("tools", 'agent')
graph=workflow.compile()

JSON 配置文件

创建配置文件 langgraph.json

{
  "python_version": "3.11",
  "dockerfile_lines": [],
  "dependencies": [
    "."
  ],
  "graphs": {
    "engineer": "./src/agent/test.py:graph"
  },
  "env": "/Users/hawk/workspace/projects/llm/langstudio1/.env"
}