Update app.py

app.py

@@ -7,38 +7,58 @@ from docx import Document
 # Load the tokenizer and model for sentence embeddings
 @st.cache_resource
 def load_model():
-    tokenizer = AutoTokenizer.from_pretrained("rakeshkiriyath/gpt2Medium_text_to_sql")
-    model = AutoModelForCausalLM.from_pretrained("rakeshkiriyath/gpt2Medium_text_to_sql")
-    sentence_model = SentenceTransformer('all-MiniLM-L6-v2')  # Smaller, faster sentence embeddings model
-    return tokenizer, model, sentence_model
+    try:
+        tokenizer = AutoTokenizer.from_pretrained("rakeshkiriyath/gpt2Medium_text_to_sql")
+        model = AutoModelForCausalLM.from_pretrained("rakeshkiriyath/gpt2Medium_text_to_sql")
+        sentence_model = SentenceTransformer('all-MiniLM-L6-v2')  # Smaller, faster sentence embeddings model
+        st.success("Model loaded successfully!")
+        return tokenizer, model, sentence_model
+    except Exception as e:
+        st.error(f"Error loading models: {e}")
+        return None, None, None
 
 # Extract text from a PDF file
 def extract_text_from_pdf(pdf_file):
-    pdf_reader = PyPDF2.PdfReader(pdf_file)
-    text = ""
-    for page in pdf_reader.pages:
-        text += page.extract_text()
-    return text
+    try:
+        pdf_reader = PyPDF2.PdfReader(pdf_file)
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+        return text
+    except Exception as e:
+        st.error(f"Error reading PDF: {e}")
+        return ""
 
 # Extract text from a Word document
 def extract_text_from_word(docx_file):
-    doc = Document(docx_file)
-    text = ""
-    for paragraph in doc.paragraphs:
-        text += paragraph.text + "\n"
-    return text
+    try:
+        doc = Document(docx_file)
+        text = ""
+        for paragraph in doc.paragraphs:
+            text += paragraph.text + "\n"
+        return text
+    except Exception as e:
+        st.error(f"Error reading Word document: {e}")
+        return ""
 
 # Compare sentences for similarity
 def compare_sentences(doc1_sentences, doc2_sentences, sentence_model):
     similar_sentences = []
     for i, sent1 in enumerate(doc1_sentences):
+        if not sent1.strip():
+            continue  # Skip empty sentences
         best_match = None
         best_score = 0
         for j, sent2 in enumerate(doc2_sentences):
-            score = util.pytorch_cos_sim(sentence_model.encode(sent1), sentence_model.encode(sent2)).item()
-            if score > best_score:  # Higher similarity score
-                best_score = score
-                best_match = (i, j, score, sent1, sent2)
+            if not sent2.strip():
+                continue
+            try:
+                score = util.pytorch_cos_sim(sentence_model.encode(sent1), sentence_model.encode(sent2)).item()
+                if score > best_score:  # Higher similarity score
+                    best_score = score
+                    best_match = (i, j, score, sent1, sent2)
+            except Exception as e:
+                st.error(f"Error comparing sentences: {e}")
         if best_match and best_score > 0.6:  # Threshold for similarity
             similar_sentences.append(best_match)
     return similar_sentences
@@ -54,22 +74,53 @@ def main():
 
     if uploaded_file1 and uploaded_file2:
         # Extract text from the uploaded documents
-        text1 = extract_text_from_pdf(uploaded_file1) if uploaded_file1.name.endswith(".pdf") else extract_text_from_word(uploaded_file1)
-        text2 = extract_text_from_pdf(uploaded_file2) if uploaded_file2.name.endswith(".pdf") else extract_text_from_word(uploaded_file2)
+        if uploaded_file1.name.endswith(".pdf"):
+            text1 = extract_text_from_pdf(uploaded_file1)
+        else:
+            text1 = extract_text_from_word(uploaded_file1)
+
+        if uploaded_file2.name.endswith(".pdf"):
+            text2 = extract_text_from_pdf(uploaded_file2)
+        else:
+            text2 = extract_text_from_word(uploaded_file2)
+
+        if not text1.strip():
+            st.error("The first document is empty or could not be read.")
+            return
+        if not text2.strip():
+            st.error("The second document is empty or could not be read.")
+            return
+
+        st.write("### Preview of Document 1:")
+        st.text(text1[:500])  # Display a preview of Document 1
+        st.write("### Preview of Document 2:")
+        st.text(text2[:500])  # Display a preview of Document 2
 
         # Split text into sentences
         doc1_sentences = text1.split('. ')
         doc2_sentences = text2.split('. ')
 
-        # Load model
+        # Limit sentences for testing purposes (optional)
+        doc1_sentences = doc1_sentences[:50]  # Remove this line for full processing
+        doc2_sentences = doc2_sentences[:50]  # Remove this line for full processing
+
+        # Load models
         tokenizer, model, sentence_model = load_model()
+        if not sentence_model:
+            st.error("Failed to load the sentence embedding model.")
+            return
 
         # Perform sentence comparison
+        st.info("Comparing sentences, this may take a moment...")
         similar_sentences = compare_sentences(doc1_sentences, doc2_sentences, sentence_model)
 
         # Display results
         st.header("Comparative Analysis Results")
+        st.write(f"Number of sentences in Document 1: {len(doc1_sentences)}")
+        st.write(f"Number of sentences in Document 2: {len(doc2_sentences)}")
+
         if similar_sentences:
+            st.success(f"Found {len(similar_sentences)} similar sentences!")
             for match in similar_sentences:
                 doc1_index, doc2_index, score, sent1, sent2 = match
                 st.markdown(f"**Document 1 Sentence {doc1_index + 1}:** {sent1}")
@@ -78,7 +129,6 @@ def main():
                 st.markdown("---")
         else:
             st.info("No significantly similar sentences found.")
-
     else:
         st.warning("Please upload two documents to compare.")