Update app.py

app.py

@@ -23,7 +23,7 @@ import json
 import os
 from sentence_transformers import SentenceTransformer, util
 import textstat
-import language_tool_python
+from spellchecker import SpellChecker
 from transformers import pipeline
 
 print("***************************************************************")
@@ -40,7 +40,7 @@ wiki_wiki = wikipediaapi.Wikipedia(user_agent= user_agent,language='en')
 
 @st.cache_resource
 def load_model():
-    model_name = "DevBM/t5-large-squad"
+    model_name = "DevBM/t5-small-squad"
     model = T5ForConditionalGeneration.from_pretrained(model_name)
     tokenizer = T5Tokenizer.from_pretrained(model_name)
     return model, tokenizer
@@ -58,14 +58,12 @@ def load_qa_models():
     # Initialize BERT model for sentence similarity
     similarity_model = SentenceTransformer('all-MiniLM-L6-v2')
 
-    # Initialize language tool for grammar checking
-    language_tool = language_tool_python.LanguageTool('en-US')
-
-    return similarity_model, language_tool
+    spell = SpellChecker()
+    return similarity_model, spell
 
 nlp, s2v = load_nlp_models()
 model, tokenizer = load_model()
-similarity_model, language_tool = load_qa_models()
+similarity_model, spell = load_qa_models()
 
 def save_feedback(question, answer,rating):
     feedback_file = 'question_feedback.json'
@@ -251,18 +249,18 @@ def assess_question_quality(context, question, answer):
     # Assess complexity using token length (as a simple metric)
     complexity_score = min(len(question_doc) / 20, 1)  # Normalize to 0-1
 
-    # Assess grammatical correctness
-    errors = language_tool.check(question)
-    grammatical_correctness = 1 - (len(errors) / len(question_doc))  # Normalize to 0-1
+    # Assess Spelling correctness
+    misspelled = spell.unknown(question.split())
+    spelling_correctness = 1 - (len(misspelled) / len(question.split()))  # Normalize to 0-1
 
     # Calculate overall score (you can adjust weights as needed)
     overall_score = (
         0.4 * relevance_score +
-        0.3 * complexity_score +
-        0.3 * grammatical_correctness
+        0.4 * complexity_score +
+        0.2 * spelling_correctness
     )
 
-    return overall_score, relevance_score, complexity_score, grammatical_correctness
+    return overall_score, relevance_score, complexity_score, spelling_correctness
 
 def main():
     # Streamlit interface
@@ -303,7 +301,7 @@ def main():
                 break
             question = generate_question(context, keyword, num_beams=num_beams)
             options = generate_options(keyword,context)
-            overall_score, relevance_score, complexity_score, grammatical_correctness = assess_question_quality(context,question,keyword)
+            overall_score, relevance_score, complexity_score, spelling_correctness = assess_question_quality(context,question,keyword)
             tpl = {
                 "question" : question,
                 "context" : context,
@@ -312,7 +310,7 @@ def main():
                 "overall_score" : overall_score,
                 "relevance_score" : relevance_score,
                 "complexity_score" : complexity_score,
-                "grammatical_correctness" : grammatical_correctness,
+                "spelling_correctness" : spelling_correctness,
             }
             st.session_state.generated_questions.append(tpl)
 
@@ -339,7 +337,7 @@ def main():
                 st.write(f"**Overall Quality Score:** {q['overall_score']:.2f}")
                 st.write(f"**Relevance Score:** {q['relevance_score']:.2f}")
                 st.write(f"**Complexity Score:** {q['complexity_score']:.2f}")
-                st.write(f"**Grammatical Correctness:** {q['grammatical_correctness']:.2f}")
+                st.write(f"**Spelling Correctness:** {q['spelling_correctness']:.2f}")
 
             # q['context'] = st.text_area(f"Edit Context {i+1}:", value=q['context'], key=f"context_{i}")
             if enable_feedback_mode:
@@ -389,7 +387,6 @@ def main():
                 st.write("No feedback data available yet.")
 
         print("********************************************************************************")
-        
 
 if __name__ == '__main__':
     main()