基于langgraph的开发入门（初稿）
前言：由于langgraph是较新的multi-agent框架，资料较少，官方文档又晦涩难懂，且自己只有一点点langchain的经验，所以准备精读langgraph的框架，特此记录，以供查阅
Chapter1：初识langgraph
作用： 1.一个能够实现多个action的库，用循环的方式能够协调多个langchain。能够循环调用大模型的能力，而不是一个DAG框架（类似于metagpt那种），这能够帮助大模型知道下一步做什么。
安装
pip install langgraph
启动举例
1.安装几个库
pip install -U langchain langchain_openai tavily-python
2.设置api的key
export OPENAI_API_KEY=sk-…export TAVILY_API_KEY=tvly-…
openai_key是openai的chatgpt api调用时使用的key
tavily_key是一个类似搜索引擎的api，能够通过发送请求，得到对应的一些信息，并且对LLM agent的优化效果较好
可以设置langsmith来查看记录agent运行情况
3.设置工具
工具列表类似langchain，只需要把工具放到列表里
from langchain_community.tools.tavily_search import TavilySearchResults
tools = [TavilySearchResults(max_results=1)]
利用ToolExecutor对工具进行封装
from langgraph.prebuilt import ToolExecutor
tool_executor = ToolExecutor(tools)
4.加载模型
模型要求：1.能够有多轮对话能力 2.支持OpenAI格式的输入
以chatgpt为例
from langchain_openai import ChatOpenAI
# We will set streaming=True so that we can stream tokens
# See the streaming section for more information on this.
model = ChatOpenAI(temperature=0, streaming=True)
对于各个模型的function calling功能，一般需求特定的格式，所以把我们的工具和模型进行绑定
from langchain.tools.render import format_tool_to_openai_function
functions = [format_tool_to_openai_function(t) for t in tools]
model = model.bind_functions(functions)
5.状态图（用于查看模型状态）
状态图通过一个列表进行记录，并将子节点的状态进行返回
from typing import TypedDict, Annotated, Sequence
import operator
from langchain_core.messages import BaseMessage
class AgentState(TypedDict):
messages: Annotated[Sequence[BaseMessage], operator.add]
6.定义节点
每个节点有这不同的功能和作用，langgraph就是靠着一个个节点进行的
类似langchain，有两个主要的节点，一个是决定使用什么工具，另一个是用来调用工具
其中包含条件节点。在agent决定采取action时，条件节点才会被使用，否则将结束。
from langgraph.prebuilt import ToolInvocation
import json
from langchain_core.messages import FunctionMessage
# Define the function that determines whether to continue or not
def should_continue(state):
messages = state['messages']
#获取状态信息的最后一个
last_message = messages[-1]
# If there is no function call, then we finish
if "function_call" not in last_message.additional_kwargs:
return "end"
# Otherwise if there is, we continue
else:
return "continue"
# Define the function that calls the model
def call_model(state):
messages = state['messages']
response = model.invoke(messages)
# We return a list, because this will get added to the existing list
return {"messages": [response]}
# Define the function to execute tools
def call_tool(state):
messages = state['messages']
# Based on the continue condition
# we know the last message involves a function call
last_message = messages[-1]
# We construct an ToolInvocation from the function_call
action = ToolInvocation(
tool=last_message.additional_kwargs["function_call"]["name"],
tool_input=json.loads(last_message.additional_kwargs["function_call"]["arguments"]),
)
# We call the tool_executor and get back a response
response = tool_executor.invoke(action)
# We use the response to create a FunctionMessage
function_message = FunctionMessage(content=str(response), name=action.tool)
# We return a list, because this will get added to the existing list
return {"messages": [function_message]}
7.graph创建
定义好节点和状态之后，就可以开始创建graph了
from langgraph.graph import StateGraph, END
# Define a new graph
workflow = StateGraph(AgentState)
# Define the two nodes we will cycle between
workflow.add_node("agent", call_model)
workflow.add_node("action", call_tool)
# Set the entrypoint as `agent`
# This means that this node is the first one called
workflow.set_entry_point("agent")
# We now add a conditional edge
workflow.add_conditional_edges(
# First, we define the start node. We use `agent`.
# This means these are the edges taken after the `agent` node is called.
"agent",
# Next, we pass in the function that will determine which node is called next.
should_continue,
# Finally we pass in a mapping.
# The keys are strings, and the values are other nodes.
# END is a special node marking that the graph should finish.
# What will happen is we will call `should_continue`, and then the output of that
# will be matched against the keys in this mapping.
# Based on which one it matches, that node will then be called.
{
# If `tools`, then we call the tool node.
"continue": "action",
# Otherwise we finish.
"end": END
}
)
# We now add a normal edge from `tools` to `agent`.
# This means that after `tools` is called, `agent` node is called next.
workflow.add_edge('action', 'agent')
# Finally, we compile it!
# This compiles it into a LangChain Runnable,
# meaning you can use it as you would any other runnable
app = workflow.compile()
代码解释：
-
集成agentstate创建StateGraph
-
加入agent节点 和模型进行交互信息
-
加入action节点，进行action执行
-
设置整体流程被启用的第一个节点为agent节点作为入口
-
然后就开始按图写流程
-
加入边，对agent输出进行判断，如果是continue则action，end则结束
-
action之后，把结果返回agent
-
开始运行
8.可以使用啦
from langchain_core.messages import HumanMessage
inputs = {"messages": [HumanMessage(content="what is the weather in sf")]}
app.invoke(inputs)
流式输出（streaming）
下面有几种方式
节点输出
inputs = {"messages": [HumanMessage(content="what is the weather in sf")]}
for output in app.stream(inputs):
# stream() yields dictionaries with output keyed by node name
for key, value in output.items():
print(f"Output from node '{key}':")
print("---")
print(value)
print("\n---\n")
代码解释：对于outputs每次生成的k，v进行print（yield机制）
流式输出LLM的token
inputs = {"messages": [HumanMessage(content="what is the weather in sf")]}
async for output in app.astream_log(inputs, include_types=["llm"]):
# astream_log() yields the requested logs (here LLMs) in JSONPatch format
for op in output.ops:
if op["path"] == "/streamed_output/-":
# this is the output from .stream()
...
elif op["path"].startswith("/logs/") and op["path"].endswith(
"/streamed_output/-"
):
# because we chose to only include LLMs, these are LLM tokens
print(op["value"])
代码解释：
选择大模型的输出日志，每次都返回最新的生成token。并且不断返回
使用场景
需要循环调用的时候，而如果只是链式的，langchain语言就可以做到
使用案例
- ChatAgentExecutor
Getting Started Notebook: Walks through creating this type of executor from scratch
High Level Entrypoint: Walks through how to use the high level entrypoint for the chat agent executor.
Human-in-the-loop: How to add a human-in-the-loop component
Force calling a tool first: How to always call a specific tool first
Respond in a specific format: How to force the agent to respond in a specific format
Dynamically returning tool output directly: How to dynamically let the agent choose whether to return the result of a tool directly to the user
Managing agent steps: How to more explicitly manage intermediate steps that an agent takes
-
AgentExecutor
- Getting Started Notebook: Walks through creating this type of executor from scratch
- High Level Entrypoint: Walks through how to use the high level entrypoint for the chat agent executor.
- Human-in-the-loop: How to add a human-in-the-loop component
- Force calling a tool first: How to always call a specific tool first
- Managing agent steps: How to more explicitly manage intermediate steps that an agent takes
-
Multi-agentMulti-agent collaboration: how to create two agents that work together to accomplish a taskMulti-agent with supervisor: how to orchestrate individual agents by using an LLM as a “supervisor” to distribute workHierarchical agent teams: how to orchestrate “teams” of agents as nested graphs that can collaborate to solve a problem
-
Chatbot Evaluation via Simulation
Chat bot evaluation as multi-agent simulation: How to simulate a dialogue between a “virtual user” and your chat bot
- Async
running LangGraph in async workflows, you may want to create the nodes to be async by default. In order for a walkthrough on how to do that, see this documentation
-
Streaming TokensSometimes language models take a while to respond and you may want to stream tokens to end users. For a guide on how to do this, see this documentation
-
PersistenceLangGraph comes with built-in persistence, allowing you to save the state of the graph at point and resume from there. In order for a walkthrough on how to do that, see this documentation
一些类的使用
StateGraph
graph
EndPrebuilt Examples