Update app.py

app.py

@@ -1,32 +1,75 @@
+
 import streamlit as st
-import plotly.graph_objects as go
-from transformers import pipeline
-import re
-import time
-import requests
 from PIL import Image
-import itertools
-import numpy as np
-import matplotlib.pyplot as plt
-from matplotlib.colors import rgb2hex
-import matplotlib
-from matplotlib.colors import ListedColormap, rgb2hex
-import ipywidgets as widgets
-from IPython.display import display, HTML
-import re
-import pandas as pd
-from pprint import pprint
-from tenacity import retry
-from tqdm import tqdm
-import tiktoken
-import scipy.stats
+import spacy
+import streamlit as st
+from streamlit_pdf_viewer import pdf_viewer
+
+
+
+st.set_page_config(page_title="FACTOID: FACtual enTailment fOr hallucInation Detection", layout="wide")
+st.title('Welcome to :blue[FACTOID] ') 
+
+st.header('FACTOID: FACtual enTailment fOr hallucInation Detection :blue[Web Demo]')
+#image = Image.open('image.png')
+#st.image(image, caption='Traditional Entailment vs Factual Entailment')
+pdf_viewer(input="fac.pdf", width=700)
+
+# List of sentences
+sentence1 = [f"U.S. President Barack Obama declared that the U.S. will refrain from deploying troops in Ukraine."]
+sentence2 = [f"Joe Biden said we’d not send U.S. troops to fight Russian troops in Ukraine, but we would provide robust military assistance and try to unify the Western world against Russia’s aggression."]
+# Create a dropdown menu
+selected_sentence1 = st.selectbox("Select first sentence:", sentence1)
+selected_sentence2 = st.selectbox("Select first sentence:", sentence2)
+
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
-from transformers import GPT2LMHeadModel
-import tiktoken
-import seaborn as sns
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
-# from colorama import Fore, Style
-import openai  # for OpenAI API calls
+device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
 
-import streamlit as st
-st.image('image.png', caption='Traditional Taxtual Entailment vs Factual Entailment')
+model_name = "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7"
+tokenizer = AutoTokenizer.from_pretrained(model_name,use_fast=False)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+
+premise = selected_sentence1
+hypothesis = selected_sentence2
+input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
+output = model(input["input_ids"].to(device))  # device = "cuda:0" or "cpu"
+prediction = torch.softmax(output["logits"][0], -1).tolist()
+label_names = ["support", "neutral", "refute"]
+prediction = {name: float(pred) for pred, name in zip(prediction, label_names)}
+highest_label = max(prediction, key=prediction.get)
+
+
+from transformers import pipeline
+pipe = pipeline("text-classification",model="sileod/deberta-v3-base-tasksource-nli")
+labels=pipe([dict(text=selected_sentence1,
+  text_pair=selected_sentence2)])
+
+
+import en_core_web_sm
+
+
+def extract_person_names(sentence):
+    nlp = spacy.load("en_core_web_sm")
+    doc = nlp(sentence)
+    person_names = [entity.text for entity in doc.ents if entity.label_ == 'PERSON']
+    
+    return person_names[0]
+
+person_name1 = extract_person_names(selected_sentence1)
+person_name2 = extract_person_names(selected_sentence2)
+
+
+col1, col2 = st.columns(2)
+
+with col1:
+    st.write("Without Factual Entailment.")
+    st.write("Textual Entailment Model:\n",highest_label)
+
+with col2:
+    st.write("With Factual Entailment:")
+    st.write("Textual Entailment Model:\n",labels[0]['label'])
+    st.write("Span Detection Model:\n")
+    st.write(f"{person_name1}::{person_name2}")
+