pages/3_Earnings_Semantic_Search_🔎_.py

import streamlit as st
from functions import *

st.set_page_config(page_title="Earnings Semantic Search", page_icon="🔎")
st.sidebar.header("Semantic Search")
st.markdown("## Earnings Semantic Search with SBert")

search_input = st.text_input(
        label='Enter Your Search Query, e.g "What challenges did the business face?"', key='search')
        
top_k = st.sidebar.slider("Number of Top Hits Generated",min_value=1,max_value=5,value=2)

window_size = st.sidebar.slider("Number of Sentences Generated in Search Response",min_value=1,max_value=5,value=3)

    earnings_sentiment, earnings_sentences = sentiment_pipe(earnings_passages)
    
    with st.expander("See Transcribed Earnings Text"):
        st.write(f"Number of Sentences: {len(earnings_sentences)}")
        
        st.write(earnings_passages)
    
    
    ## Save to a dataframe for ease of visualization
    sen_df = pd.DataFrame(earnings_sentiment)
    sen_df['text'] = earnings_sentences
    grouped = pd.DataFrame(sen_df['label'].value_counts()).reset_index()
    grouped.columns = ['sentiment','count']
    

passages = preprocess_plain_text(st.session_state['earnings_passages'],window_size=window_size)

##### Sematic Search #####
# Encode the query using the bi-encoder and find potentially relevant passages
corpus_embeddings = sbert.encode(passages, convert_to_tensor=True, show_progress_bar=True)
question_embedding = sbert.encode(search_input, convert_to_tensor=True)
question_embedding = question_embedding.cpu()
hits = util.semantic_search(question_embedding, corpus_embeddings, top_k=top_k,score_function=util.dot_score)
hits = hits[0]  # Get the hits for the first query

##### Re-Ranking #####
# Now, score all retrieved passages with the cross_encoder
cross_inp = [[query, passages[hit['corpus_id']]] for hit in hits]
cross_scores = cross_encoder.predict(cross_inp)

# Sort results by the cross-encoder scores
for idx in range(len(cross_scores)):
    hits[idx]['cross-score'] = cross_scores[idx]

# Output of top-3 hits from bi-encoder
st.markdown("\n-------------------------\n")
st.subheader(f"Top-{top_k} Bi-Encoder Retrieval hits")
hits = sorted(hits, key=lambda x: x['score'], reverse=True)

cross_df = display_df_as_table(hits,top_k)
st.write(cross_df.to_html(index=False), unsafe_allow_html=True)

# Output of top-3 hits from re-ranker
st.markdown("\n-------------------------\n")
st.subheader(f"Top-{top_k} Cross-Encoder Re-ranker hits")
hits = sorted(hits, key=lambda x: x['cross-score'], reverse=True)

rerank_df = display_df_as_table(hits,top_k,'cross-score')
st.write(rerank_df.to_html(index=False), unsafe_allow_html=True