import gradio as gr
import os
import matplotlib.pyplot as plt
import pandas as pd
from langgraph.graph import StateGraph
from langgraph.prebuilt import create_react_agent
from langgraph.types import Command
from langchain_core.messages import HumanMessage
from langchain_anthropic import ChatAnthropic

# Set the API key from Hugging Face secrets
os.environ["ANTHROPIC_API_KEY"] = os.getenv("ANTHROPIC_API_KEY")

# Claude 3.5 Sonnet
llm = ChatAnthropic(model="claude-3-5-sonnet-latest")

# Create the system prompt
def make_system_prompt(suffix: str) -> str:
    return (
        "You are a helpful AI assistant, collaborating with other assistants."
        " Use the provided tools to progress towards answering the question."
        " If you are unable to fully answer, that's OK—another assistant with different tools"
        " will help where you left off. Execute what you can to make progress."
        " If you or any of the other assistants have the final answer or deliverable,"
        " prefix your response with FINAL ANSWER so the team knows to stop."
        f"\n{suffix}"
    )

# Workflow node: research
def research_node(state):
    agent = create_react_agent(
        llm,
        tools=[],
        state_modifier=make_system_prompt("You can only do research.")
    )
    result = agent.invoke(state)
    goto = "chart_generator" if "FINAL ANSWER" not in result["messages"][-1].content else "__end__"
    result["messages"][-1] = HumanMessage(
        content=result["messages"][-1].content,
        name="researcher"
    )
    return Command(update={"messages": result["messages"]}, goto=goto)

# Workflow node: chart generation
def chart_node(state):
    agent = create_react_agent(
        llm,
        tools=[],
        state_modifier=make_system_prompt("You can only generate charts.")
    )
    result = agent.invoke(state)
    result["messages"][-1] = HumanMessage(
        content=result["messages"][-1].content,
        name="chart_generator"
    )
    return Command(update={"messages": result["messages"]}, goto="__end__")

# LangGraph setup
workflow = StateGraph(dict)
workflow.add_node("researcher", research_node)
workflow.add_node("chart_generator", chart_node)
workflow.set_entry_point("researcher")
workflow.set_finish_point("__end__")
workflow.add_edge("researcher", "chart_generator")
graph = workflow.compile()

# LangGraph runner
def run_langgraph(input_text):
    try:
        events = graph.stream({"messages": [("user", input_text)]})
        output = []
        for event in events:
            output.append(event)

        final_response = output[-1]["messages"][-1].content

        if "FINAL ANSWER" in final_response:
            # Simulated chart creation from dummy data
            years = [2020, 2021, 2022, 2023, 2024]
            gdp = [21.4, 22.0, 23.1, 24.8, 26.2]

            plt.figure()
            plt.plot(years, gdp, marker="o")
            plt.title("USA GDP Over Last 5 Years")
            plt.xlabel("Year")
            plt.ylabel("GDP in Trillions USD")
            plt.grid(True)
            plt.tight_layout()
            plt.savefig("gdp_chart.png")

            return "Chart generated based on FINAL ANSWER.", "gdp_chart.png"
        else:
            return final_response, None
    except Exception as e:
        return f"Error: {str(e)}", None

# Gradio interface
def process_input(user_input):
    return run_langgraph(user_input)

interface = gr.Interface(
    fn=process_input,
    inputs=gr.Textbox(label="Enter your research task"),
    outputs=[gr.Textbox(label="Output"), gr.Image(type="filepath", label="Chart")],
    title="LangGraph Research Automation",
    description="Enter a research prompt and view chart output when applicable."
)

if __name__ == "__main__":
    interface.launch()