from langchain_openai.chat_models import ChatOpenAI
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain.tools.render import format_tool_to_openai_function
from langgraph.prebuilt import ToolExecutor,ToolInvocation
from typing import TypedDict, Annotated, Sequence
import operator
from langchain_core.messages import BaseMessage,FunctionMessage,HumanMessage
from langchain.tools import ShellTool
import json
import os
import gradio as gr
os.environ["LANGCHAIN_TRACING_V2"] ="True"
os.environ["LANGCHAIN_API_KEY"]="ls__54e16f70b2b0455aad0f2cbf47777d30"
os.environ["OPENAI_API_KEY"]="20a79668d6113e99b35fcd541c65bfeaec497b8262c111bd328ef5f1ad8c6335"
# os.environ["OPENAI_API_KEY"]="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"
os.environ["LANGCHAIN_ENDPOINT"]="https://api.smith.langchain.com"
os.environ["LANGCHAIN_PROJECT"]="default"
os.environ['TAVILY_API_KEY'] = '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'

class AgentState(TypedDict):
    messages: Annotated[Sequence[BaseMessage], operator.add]

model = ChatOpenAI(model="gpt-3.5-turbo-1106",api_key="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")
shell_tool = ShellTool()
tools = [TavilySearchResults(max_results=1),shell_tool]


functions = [format_tool_to_openai_function(t) for t in tools]
model = model.bind_functions(functions)

tool_executor = ToolExecutor(tools)
# Define the function that determines whether to continue or not
def should_continue(state):
    messages = state['messages']
    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]}

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()

# inputs = {"messages": [HumanMessage(content="查询你的cast命令版本")]}
# app.invoke(inputs)

async def predict(question):
    que={"messages": [HumanMessage(content=question)]}
    res=app.invoke(que)
    if res:
        return(res["output"])
    else:print("不好意思，出了一个小问题，请联系我的微信：13603634456")
    
	
gr.Interface(
    predict,inputs="textbox",
    outputs="textbox",
    title="定制版AI专家BOT-0.1版",
    description="这是一个定制版的AI专家BOT，你可以通过输入问题，让AI为你回答。\n目前提供三个示例工具：\n1.bash命令行执行工具，可以将人类语言转化为bash命令，然后执行。\n2.搜索引擎").launch()