"""
# My first app
Here's our first attempt at using data to create a table:
"""
import streamlit as st
from retriever import do_search

def local_css(file_name):
    with open(file_name) as f:
        st.markdown(f'<style>{f.read()}</style>', unsafe_allow_html=True)


def render_retrieved_content(content, score):
    print_score = ''
    if score is not None:
        score = round(score, 3)
        print_score = f'<b> Similarity Score: {score}</b>'
    return f'<blockquote>{content} </blockquote> {print_score}'

local_css('style.css')
st.header('🧐  Where my docs at?')
st.markdown('✨ Imagine you have a bunch of text documents and looking for one specific passage, '
         'but you can not remember on the exact words. Just about rough content. <br><br>'
         '💡 This demo compares different search approaches that can help you to find the right '
         'information.', unsafe_allow_html=True)

option = st.selectbox(
     'Choose a dataset',
     ('CDU election program 2021', 'Partisan news 2019 (dutch)'))



search = st.text_input('Enter your search query')
if search:
    result = do_search(search)

    st.markdown('### 🔎  Term Frequency–Inverse Document Frequency (TF-IDF)')
    st.markdown('Is a statistical approach that calculates how relevant a word is to a document '
                'in your collection. Only documents will be found that contain one of the words of '
                'the given search query. You still have to remember on exact terms that are in the'
                'searched phrase.')
    st.markdown(render_retrieved_content(result[0][0].content, None),
                unsafe_allow_html=True)

    st.markdown('### 🧠  Semantic search')
    st.markdown('An alternative approach is semantic search. Instead of using words of the '
                'documents to calculate the score, we use a neural network that calculate the '
                'similarity between the query and the documents of the collection. In other words, '
                'the chance is high to find topic related documents without knowing the exact '
                'terms.')
    st.markdown(render_retrieved_content(result[1][0].content, result[1][0].score),
                unsafe_allow_html=True)

    st.markdown('### 🚀  Domain adapted semantic search')
    st.markdown('If our document collection contains a lot of domain specific documents, '
                'we can not use standard models. These models were trained on a large amount of '
                'public available data, that covers probably not your domain specific words. To '
                'improve the search results, we could fine-tune the network to calculate more '
                'accurate similarities between queries and document regarding to your domain.')
    st.markdown(render_retrieved_content(result[2][0].content, result[2][0].score),
                unsafe_allow_html=True)