# Read the data
import pandas as pd
df = pd.read_csv('./Automobile_data.csv')
#df = df.drop(columns = ['normalized-losses','symboling'], axis = 1)

context_data = []
for i in range(len(df)):  # Loop over rows
    context = ""
    for j in range(26):  # Loop over the first 8 columns
        context += df.columns[j]  # Add column name
        context += ": "
        context += str(df.iloc[i][j])  # Convert value to string
        context += " "
    context_data.append(context)


import os

# Get the secret key from the environment
groq_key = os.environ.get('groq_API_Keys')

## LLM used for RAG
from langchain_groq import ChatGroq

llm = ChatGroq(model="llama-3.1-70b-versatile",api_key=groq_key)

## Embedding model!
from langchain_huggingface import HuggingFaceEmbeddings
embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")

# create vector store!
from langchain_chroma import Chroma

vectorstore = Chroma(
    collection_name="car_dataset_store",
    embedding_function=embed_model,
    persist_directory="./",
)

# add data to vector nstore
vectorstore.add_texts(context_data)

retriever = vectorstore.as_retriever()

from langchain_core.prompts import PromptTemplate

template = ("""You are a car expert.
    Use the provided context to answer the question.
    If you don't know the answer, say so. Explain your answer in detail.
    Do not discuss the context in your response; just provide the answer directly.

    Context: {context}

    Question: {question}

    Answer:""")

rag_prompt = PromptTemplate.from_template(template)

from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough

rag_chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | rag_prompt
    | llm
    | StrOutputParser()
)


import gradio as gr

# Function for the chatbot response stream with error handling
def rag_memory_stream(message, history):
    partial_text = ""
    try:
        for new_text in rag_chain.stream(message):
            print(f"Processing: {new_text}")  # Debugging output
            partial_text += new_text
            yield partial_text
    except Exception as e:
        yield f"An error occurred: {str(e)}"

# Function to process car preferences
def process_preferences(make, budget, fuel_type):
    return (
        f"You've selected:\n"
        f"- **Preferred Make**: {make}\n"
        f"- **Budget**: ${budget}\n"
        f"- **Fuel Type**: {fuel_type}\n\n"
        f"Based on your preferences, I recommend exploring the latest models of {make} "
        f"that fit your budget and offer {fuel_type.lower()} options!"
    )

# Examples and app information
examples = ['I need a car', 'What is the make and fuel type of a car?']
description = "An advanced chatbot that helps you choose the right car based on your preferences and budget."
title = "Car Expert :) Let Me Help You Find the Perfect Ride!"

# Custom theme with sky-blue background and black text
custom_theme = gr.themes.Base(primary_hue="blue", secondary_hue="green").set(
    body_background_fill="#87CEEB",  # Sky blue background
    body_text_color="#000000",      # Black text
)

# Advanced Interface with Car Preferences
with gr.Blocks(theme=custom_theme) as demo:
    gr.Markdown(f"# {title}")
    gr.Markdown(description)

    with gr.Tabs():
        # Chat Tab
        with gr.Tab("Chat"):
            chat_interface = gr.ChatInterface(
                fn=rag_memory_stream,
                type="messages",
                examples=examples,
                fill_height=True,
            )

        # Car Preferences Tab
        with gr.Tab("Car Preferences"):
            gr.Markdown("### Provide your preferences to get tailored advice:")
            
            make = gr.Dropdown(
                choices=["Toyota", "Honda", "BMW", "Tesla", "Ford"],
                label="Preferred Make",
                info="Choose the car manufacturer you prefer.",
            )
            budget = gr.Slider(
                minimum=5000, maximum=100000, step=500,
                label="Budget (in USD)",
                info="Select your budget range.",
            )
            fuel_type = gr.Radio(
                choices=["Gasoline", "Diesel", "Electric", "Hybrid"],
                label="Fuel Type",
                info="Choose the type of fuel you prefer.",
            )
            submit_button = gr.Button("Submit Preferences")
            output = gr.Textbox(
                label="Recommendation",
                placeholder="Your recommendations will appear here...",
            )
            
            # Link the submit button to the processing function
            submit_button.click(
                process_preferences,  # Function to call
                inputs=[make, budget, fuel_type],  # Inputs from UI
                outputs=output,  # Where to display the result
            )

        # Upload Documents Tab
        with gr.Tab("Upload Documents"):
            gr.Markdown("### Upload any related documents for personalized suggestions:")
            file_upload = gr.File(label="Upload Car Listings or Preferences")

        # Help Tab
        with gr.Tab("Help"):
            gr.Markdown("### Need Assistance?")
            gr.Markdown(
                """
                - Use the **Chat** tab to ask questions about cars.
                - Fill in your **Car Preferences** for tailored recommendations.
                - Upload files in the **Upload Documents** tab.
                - Contact support at: support@carexpert.com
                """
            )

    gr.Markdown("### About")
    gr.Markdown(
        """
        This chatbot is powered by LangChain and Groq API for real-time AI interactions. 
        Designed to provide personalized car-buying assistance!
        """
    )

# Launch the app
if __name__ == "__main__":
    demo.launch()