import streamlit as st
import pandas as pd
from fuzzywuzzy import process


def load_data():
    return pd.read_csv("benchmark_data.csv")


def fuzzy_search(data, query, column):
    if query:  
        choices = data[column].unique() 
        results = process.extract(query, choices, limit=10)  
        selected = [res[0] for res in results]
        return data[data[column].isin(selected)]  
    return data


def main():
    st.title("Multihop-RAG Benchmark Space")

    data = load_data()

    st.sidebar.header("Search Options")
    framework_query = st.sidebar.text_input("Search by Framework")
    model_query = st.sidebar.text_input("Search by Model")

    if framework_query:
        data = fuzzy_search(data, framework_query, 'framework')
    if model_query:
        data = fuzzy_search(data, model_query, 'model')

    st.header("Benchmark Results")
    st.write("Displaying results for MRR@10 and Hit@10 across different frameworks, models, and chunk sizes.")
    st.dataframe(data)

    if st.sidebar.checkbox("Show Metrics Distribution"):
        st.subheader("Metrics Distribution")
        st.bar_chart(data[['MRR@10', 'Hit@10']])

if __name__ == "__main__":
    main()