Update app.py

app.py

@@ -37,16 +37,38 @@ def extract_text(file_bytes):
     except Exception as e:
         return f"❌ Error reading file: {str(e)}"
 
+# Function to chunk text into smaller pieces
+def chunk_text(text, chunk_size=4000):
+    return [text[i:i + chunk_size] for i in range(0, len(text), chunk_size)]
+
 # Summarize the extracted text
 def summarize_file(file_bytes):
     text = extract_text(file_bytes)
     if not text or len(text.strip()) == 0:
         return "❌ No text found in the uploaded file."
 
-    # Truncate to fit model token limit
-    text = text[:3000]
-    summary = summarizer(text, max_length=150, min_length=40, do_sample=False)
-    return summary[0]["summary_text"]
+    # Ensure at least 300,000 characters can be processed (no truncation)
+    if len(text) > 300000:
+        text = text[:300000]  # Optional: cap at 300,000 if desired, but can be removed for larger inputs
+
+    # Chunk the text into 4,000-character segments
+    chunks = chunk_text(text, chunk_size=4000)
+    if not chunks:
+        return "❌ No valid chunks to summarize."
+
+    # Summarize each chunk
+    summaries = []
+    for i, chunk in enumerate(chunks):
+        try:
+            summary = summarizer(chunk, max_length=150, min_length=40, do_sample=False)
+            summaries.append(f"**Chunk {i+1} Summary**:\n{summary[0]['summary_text']}")
+        except Exception as e:
+            summaries.append(f"**Chunk {i+1} Summary**: ❌ Error summarizing chunk: {str(e)}")
+
+    # Combine summaries
+    combined_summary = "\n\n".join(summaries)
+    total_chars = len(text)
+    return f"**Total Characters Processed**: {total_chars}\n\n**Summaries**:\n{combined_summary}"
 
 # Gradio UI
 demo = gr.Interface(
@@ -54,11 +76,12 @@ demo = gr.Interface(
     inputs=gr.File(label="📄 Upload Notes (PDF, TXT, or Handwritten Image)", type="binary"),
     outputs=gr.Textbox(label="📝 Summarized Notes"),
     title="📚 Note Summarizer",
-    description="Upload academic notes in PDF, TXT, or image format. This app extracts and summarizes the content using a Hugging Face transformer model."
+    description="Upload academic notes in PDF, TXT, or image format (supports at least 300,000 characters). This app extracts and summarizes the content using a Hugging Face transformer model."
 )
 
-demo.launch()
-
+# Launch the interface
+if __name__ == "__main__":
+    demo.launch()