app.py

import streamlit as st
import time
import pandas as pd
import numpy as np


#pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer, util


# Load document embeddings
doc_emb = np.loadtxt("abstract-embed.txt", dtype=float)
doc_emb

# Load data
df = pd.read_csv("sessions.csv", usecols=['Unique ID', 'Name', 'Description', 'Activity Code', 'Start Time', 'End Time', 'Location Name'])
df.head()

# Get attributes from dataframe
docs = list(df["Description"])
titles = list(df["Name"])
start_times = list(df["Start Time"])
end_times = list(df["End Time"])
locations = list(df["Location Name"])


# Query
query = input("Enter your query: ")

#Encode query and documents
query_emb = model.encode(query).astype(float)

#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb.astype(float))[0].cpu().tolist()

#Combine docs & scores with other attributes
doc_score_pairs = list(zip(docs, scores, titles, start_times, end_times, locations))

# top_k results to return
top_k=3
print(" Your top", top_k, "most similar sessions in the Summit:")

#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)


#Output presentation recommendations
for doc, score, title, start_time, end_time, location in doc_score_pairs[:top_k]:
   
    print("Score: %f" %score)
    print("Title: %s" %title)
    print("Abstract: %s" %doc)
    print("Location: %s" %location)
    f"From {start_time} to {end_time}"
    print('\n')