从用户需求生成提示¶
在这个示例中，我们将创建一个聊天机器人，帮助用户生成提示。 它将首先从用户那里收集需求，然后生成提示（并根据用户输入进行优化）。 这些步骤被分为两个独立的状态，而大语言模型（LLM）将决定何时在这些状态之间进行转换。
该系统的图形表示如下所示。
环境配置¶
首先，让我们安装所需的软件包并设置我们的OpenAI API密钥（我们将使用的大型语言模型）
import getpass
import os
def _set_env(var: str):
if not os.environ.get(var):
os.environ[var] = getpass.getpass(f"{var}: ")
_set_env("OPENAI_API_KEY")
使用LangSmith进行LangGraph开发
注册LangSmith，可以快速发现并解决项目中的问题，提高LangGraph项目的性能。LangSmith允许您使用跟踪数据来调试、测试和监控使用LangGraph构建的LLM应用程序——更多关于如何开始的信息，请参阅这里。
收集信息¶
首先，我们定义图中负责收集用户需求的部分。这将是一个带有特定系统消息的LLM调用。它将能够访问一个工具，在准备生成提示时可以调用该工具。
使用Pydantic与LangChain
本笔记本使用Pydantic v2 BaseModel，需要langchain-core >= 0.3。使用langchain-core < 0.3会导致错误，因为混合使用了Pydantic v1和v2的BaseModels。
from typing import List
from langchain_core.messages import SystemMessage
from langchain_openai import ChatOpenAI
from pydantic import BaseModel
API Reference: SystemMessage | ChatOpenAI
template = """Your job is to get information from a user about what type of prompt template they want to create.
You should get the following information from them:
- What the objective of the prompt is
- What variables will be passed into the prompt template
- Any constraints for what the output should NOT do
- Any requirements that the output MUST adhere to
If you are not able to discern this info, ask them to clarify! Do not attempt to wildly guess.
After you are able to discern all the information, call the relevant tool."""
def get_messages_info(messages):
return [SystemMessage(content=template)] + messages
class PromptInstructions(BaseModel):
"""Instructions on how to prompt the LLM."""
objective: str
variables: List[str]
constraints: List[str]
requirements: List[str]
llm = ChatOpenAI(temperature=0)
llm_with_tool = llm.bind_tools([PromptInstructions])
def info_chain(state):
messages = get_messages_info(state["messages"])
response = llm_with_tool.invoke(messages)
return {"messages": [response]}
生成提示¶
我们现在设置将生成提示的状态。 这将需要一个单独的系统消息，以及一个用于过滤掉工具调用之前的全部消息的函数（因为在那之前，前一个状态决定是时候生成提示了。
from langchain_core.messages import AIMessage, HumanMessage, ToolMessage
# New system prompt
prompt_system = """Based on the following requirements, write a good prompt template:
{reqs}"""
# Function to get the messages for the prompt
# Will only get messages AFTER the tool call
def get_prompt_messages(messages: list):
tool_call = None
other_msgs = []
for m in messages:
if isinstance(m, AIMessage) and m.tool_calls:
tool_call = m.tool_calls[0]["args"]
elif isinstance(m, ToolMessage):
continue
elif tool_call is not None:
other_msgs.append(m)
return [SystemMessage(content=prompt_system.format(reqs=tool_call))] + other_msgs
def prompt_gen_chain(state):
messages = get_prompt_messages(state["messages"])
response = llm.invoke(messages)
return {"messages": [response]}
API Reference: AIMessage | HumanMessage | ToolMessage
定义状态逻辑¶
这是聊天机器人处于何种状态的逻辑。
如果最后一条消息是工具调用，则我们处于“提示创建者” (prompt) 应该响应的状态。
否则，如果最后一条消息不是 HumanMessage，则我们知道人类应在下一条消息中响应，因此我们处于 END 状态。
如果最后一条消息是 HumanMessage，则如果之前有过工具调用，我们处于 prompt 状态。
否则，我们处于“信息收集” (info) 状态。
from typing import Literal
from langgraph.graph import END
def get_state(state):
messages = state["messages"]
if isinstance(messages[-1], AIMessage) and messages[-1].tool_calls:
return "add_tool_message"
elif not isinstance(messages[-1], HumanMessage):
return END
return "info"
API Reference: END
创建图形¶
我们现在可以创建图形了。 我们将使用SqliteSaver来持久化对话历史记录。
from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import StateGraph, START
from langgraph.graph.message import add_messages
from typing import Annotated
from typing_extensions import TypedDict
class State(TypedDict):
messages: Annotated[list, add_messages]
memory = MemorySaver()
workflow = StateGraph(State)
workflow.add_node("info", info_chain)
workflow.add_node("prompt", prompt_gen_chain)
@workflow.add_node
def add_tool_message(state: State):
return {
"messages": [
ToolMessage(
content="Prompt generated!",
tool_call_id=state["messages"][-1].tool_calls[0]["id"],
)
]
}
workflow.add_conditional_edges("info", get_state, ["add_tool_message", "info", END])
workflow.add_edge("add_tool_message", "prompt")
workflow.add_edge("prompt", END)
workflow.add_edge(START, "info")
graph = workflow.compile(checkpointer=memory)
API Reference: MemorySaver | StateGraph | START | add_messages
使用聊天机器人¶
我们现在可以使用创建的聊天机器人了。
import uuid
cached_human_responses = ["hi!", "rag prompt", "1 rag, 2 none, 3 no, 4 no", "red", "q"]
cached_response_index = 0
config = {"configurable": {"thread_id": str(uuid.uuid4())}}
while True:
try:
user = input("User (q/Q to quit): ")
except:
user = cached_human_responses[cached_response_index]
cached_response_index += 1
print(f"User (q/Q to quit): {user}")
if user in {"q", "Q"}:
print("AI: Byebye")
break
output = None
for output in graph.stream(
{"messages": [HumanMessage(content=user)]}, config=config, stream_mode="updates"
):
last_message = next(iter(output.values()))["messages"][-1]
last_message.pretty_print()
if output and "prompt" in output:
print("Done!")
User (q/Q to quit): hi!
==================================[1m Ai Message [0m==================================
Hello! How can I assist you today?
User (q/Q to quit): rag prompt
==================================[1m Ai Message [0m==================================
Sure! I can help you create a prompt template. To get started, could you please provide me with the following information:
1. What is the objective of the prompt?
2. What variables will be passed into the prompt template?
3. Any constraints for what the output should NOT do?
4. Any requirements that the output MUST adhere to?
Once I have this information, I can assist you in creating the prompt template.
User (q/Q to quit): 1 rag, 2 none, 3 no, 4 no
==================================[1m Ai Message [0m==================================
Tool Calls:
PromptInstructions (call_tcz0foifsaGKPdZmsZxNnepl)
Call ID: call_tcz0foifsaGKPdZmsZxNnepl
Args:
objective: rag
variables: ['none']
constraints: ['no']
requirements: ['no']
=================================[1m Tool Message [0m=================================
Prompt generated!
==================================[1m Ai Message [0m==================================
Please write a response using the RAG (Red, Amber, Green) rating system.
Done!
User (q/Q to quit): red
==================================[1m Ai Message [0m==================================
Response: The status is RED.
User (q/Q to quit): q
AI: Byebye