add the app file and log_in option

app.py

@@ -0,0 +1,92 @@
+import gradio as gr
+import pandas as pd
+import nltk
+import random
+from bs4 import BeautifulSoup
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+import spacy
+from numpy.linalg import norm
+from sentence_transformers import SentenceTransformer, util
+
+# nltk.download('punkt')
+# nltk.download('wordnet')
+# nltk.download('omw-1.4')
+
+threshold = 0.65
+sentence_length = 6
+questions = [
+    "Is it  new or used", "Are there any wear & tear", "Does it come with dust bag, receipt & original box",
+    "Are there any scratches, marks", "Are there any fading, stains, discolorization",
+    "Is this item customized, repainted or has hardware been replaced", "Is it special edition", "Is there any odour",
+    "Are there multiple items or extra add-ons in this listing?",
+    "Is there a date code or serial number present on the item?"
+]
+
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+
+def generate_phrases(desc: str, length: int):
+    desc_list = desc.split()
+    phrase_list = []
+    if len(desc_list) >= length:
+        for i in range(len(desc_list) - (length - 1)):
+            sub_list = []
+            for j in range(i, i + length):
+                sub_list.append(desc_list[j])
+            phrase_list.append(' '.join(sub_list))
+    else:
+        phrase_list.append(' '.join(desc_list))
+
+    return phrase_list
+
+
+def find_answers_new(description: str):
+    sentences = generate_phrases(description, sentence_length)
+    sentences_embedding = model.encode(sentences)
+
+    answers = []
+
+    for question in questions:
+        query_embedding = model.encode(question)
+        similarities = util.cos_sim(query_embedding, sentences_embedding)
+
+        similarity_i = 0
+
+        new_row = None
+
+        for similarity in similarities[0]:
+            model_answer = sentences[similarity_i]
+
+            similarity_i += 1
+
+            if round(similarity.item(), 2) > threshold:
+                if new_row is not None and similarity.item() < new_row['Similarity']:
+                    continue
+
+                new_row = {'ModelAnswer': model_answer, 'Similarity': similarity.item()}
+
+        if new_row is not None:
+            answers.append(new_row['ModelAnswer'])
+        else:
+            answers.append('No answer')
+    return answers
+
+
+authorized_users = [("test_user_account", "test_user_pwd"), ]
+
+demo = gr.Interface(fn=find_answers_new,
+                    inputs=[gr.Textbox(lines=20, label="Item Description", placeholder="Desc Here...")],
+                    outputs=[gr.Textbox(lines=1, label="Is it  new or used"),
+                             gr.Textbox(lines=1, label="Are there any wear & tear"),
+                             gr.Textbox(lines=1, label="Does it come with dust bag, receipt & original box"),
+                             gr.Textbox(lines=1, label="Are there any scratches, marks"),
+                             gr.Textbox(lines=1, label="Are there any fading, stains, discolorization"),
+                             gr.Textbox(lines=1,
+                                        label="Is this item customized, repainted or has hardware been replaced"),
+                             gr.Textbox(lines=1, label="Is it special edition"),
+                             gr.Textbox(lines=1, label="Is there any odour"),
+                             gr.Textbox(lines=1, label="Are there multiple items or extra add-ons in this listing?"),
+                             gr.Textbox(lines=1, label="Is there a date code or serial number present on the item?")
+                             ])
+demo.launch(debug=False, share=True, auth=authorized_users)

requirements.txt

@@ -0,0 +1,8 @@
+gradio~=4.36.1
+pandas~=2.2.2
+nltk~=3.8.1
+numpy~=1.26.4
+spacy~=3.7.5
+beautifulsoup4~=4.12.3
+scikit-learn~=1.5.0
+sentence-transformers~=2.2.2