Update app.py

app.py

@@ -10,12 +10,14 @@ from nltk.corpus import stopwords
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 import unicodedata
+import json
 
 nltk.download('punkt')
 nltk.download('averaged_perceptron_tagger')
 nltk.download('stopwords')
 
 
+
 def get_paragraph(row, index):
     ans = ''
     for x in row[index]:
@@ -237,33 +239,52 @@ def get_article_recommendations(user_input):
     return recommendations
 
 
-def get_links(user_input):
-    recommendations = get_article_recommendations(user_input)
-    links = []
-    for article in recommendations:
-        cosine_similarity, article_id, journal_id = article
-        link = {
-            "title": journal_main['article_df'][journal_id].iloc[article_id, 0],
-            "url": journal_main['article_df'][journal_id].iloc[article_id, 1],
-            "article_id": int(article_id),
-            "journal_id": int(journal_id)
-        }
-        links.append(link)
-    return links
-
-
-def validation(user_input):
-    user_words = set(user_input.lower().split())
-    if any(word not in stop_words for word in user_words):
-        return "valid"
+def validation(text):
+    words = word_tokenize(text)
+    # Perform part-of-speech tagging
+    tagged_words = pos_tag(words)
+    # Check if any adjective or noun is present
+    adjectives = [word for word, pos in tagged_words if pos.startswith('JJ')]
+    nouns = [word for word, pos in tagged_words if pos.startswith('NN')]
+
+    result = {}
+
+    if not adjectives and not nouns:
+        result['validation'] = 'invalid'
     else:
-        return "invalid"
-    
+        adjective_str = ' '.join(adjectives)
+        noun_str = ' '.join(nouns)
+        combined_sentence = f"{adjective_str} {noun_str}"
+        result['validation'] = 'valid'
+        result['sentence'] = combined_sentence
+
+    return json.dumps(result, indent=4)
+
+
+def get_links(user_input):
+    check=validation(user_input)
+    if check['validation'] == 'valid':
+        recommendations = get_article_recommendations(check['sentence'])
+        links = []
+        for article in recommendations:
+            cosine_similarity, article_id, journal_id = article
+            link = {
+                "title": journal_main['article_df'][journal_id].iloc[article_id, 0],
+                "url": journal_main['article_df'][journal_id].iloc[article_id, 1],
+                "article_id": int(article_id),
+                "journal_id": int(journal_id)
+            }
+            links.append(link)
+        return links
+    else: 
+        return []
+
+
 
 validation_interface = gradio.Interface(
     fn=validation,
     inputs="text",
-    outputs=gradio.outputs.Textbox(label="Validation Result"),
+    outputs=gradio.outputs.JSON(),
     title="Validation API - Testing API of ScholarSync",
     description="API to validate user input"
 )