Update app.py

app.py

@@ -60,10 +60,33 @@ def fetch_full_article(url):
 # Initialize the summarization pipeline with BART
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 
+def split_text_into_chunks(text, chunk_size, overlap_size):
+    chunks = []
+    index = 0
+    while index < len(text):
+        # End index for the current chunk
+        end_index = index + chunk_size
+        # Extend the end index to include the overlap, if possible
+        end_index_with_overlap = min(end_index + overlap_size, len(text))
+        # Extract the chunk with the overlap
+        chunk = text[index:end_index_with_overlap]
+        chunks.append(chunk)
+        # Move the index to the start of the next chunk, which is end_index
+        index = end_index
+    return chunks
+    
+
 def generate_social_media_post(article_text):
-    # Summarize the article text
-    summary = summarizer(article_text, max_length=1000, min_length=200, do_sample=False)[0]['summary_text']
-    return summary
+    chunk_size = 900  # This is close to the model's maximum length for BART
+    overlap_size = 50  # Overlap size to ensure continuity in the text
+    chunks = split_text_into_chunks(article_text, chunk_size, overlap_size)
+    
+    summarized_text = ''
+    for chunk in chunks:
+        # Call the summarizer for each chunk
+        summary = summarizer(chunk, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
+        summarized_text += summary + ' '
+    return summarized_text.strip()
 
 
 
@@ -103,7 +126,7 @@ def page_article_to_social_post():
                 
                 # Store the full article text in session state for later use
                 st.session_state.full_article_text = article_text
-                
+
             if st.button('Generate Social Media Post') and 'full_article_text' in st.session_state:
                 with st.spinner('Generating...'):
                     # Generate a summary based on the full article text
@@ -111,7 +134,6 @@ def page_article_to_social_post():
                     st.success('Generated Content:')
                     st.write(post_content)
 
-
 def page_test():
     st.title('Test Page')
     st.write('This is a test page with a test name.')