Update app.py

app.py

@@ -1,23 +1,153 @@
-```python
 import gradio as gr
-import logging
+import fitz  # PyMuPDF
+import torch
+from transformers import pipeline
+import time, logging, re
+import matplotlib
+matplotlib.use('Agg')
+import matplotlib.pyplot as plt
+import io
+from PIL import Image
+from concurrent.futures import ThreadPoolExecutor
 
-# Existing imports and code (omitted for brevity) remain unchanged until the launch section
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Set device (CPU or GPU)
+device = 0 if torch.cuda.is_available() else -1
+logger.info(f"🔧 Using {'GPU' if device == 0 else 'CPU'}")
+
+# Load model
+try:
+    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", device=device)
+except Exception as e:
+    logger.error(f"❌ Model loading failed: {str(e)}")
+    exit(1)
+
+def visualize_chunk_status(chunk_data):
+    status_colors = {'summarized': 'green', 'skipped': 'orange', 'error': 'red'}
+    labels = [f"C{i['chunk']}" for i in chunk_data]
+    colors = [status_colors.get(i['status'], 'gray') for i in chunk_data]
+    times = [i.get('time', 0.1) for i in chunk_data]
+
+    fig, ax = plt.subplots(figsize=(10, 2.5))
+    ax.barh(labels, times, color=colors)
+    ax.set_xlabel("Time (s)")
+    ax.set_title("📊 Chunk Processing Status")
+    plt.tight_layout()
+    buf = io.BytesIO()
+    plt.savefig(buf, format='png')
+    plt.close(fig)
+    buf.seek(0)
+    return Image.open(buf)
+
+def create_summary_flowchart(summaries):
+    filtered = [
+        s for s in summaries 
+        if s.startswith("**Chunk") and "Skipped" not in s and "Error" not in s
+    ]
+    if not filtered:
+        return None
+
+    fig_height = max(2, len(filtered) * 0.8 + 1)
+    fig, ax = plt.subplots(figsize=(6, fig_height))
+    ax.axis('off')
+
+    ypos = list(range(len(filtered) * 2, 0, -2))
+    boxprops = dict(boxstyle="round,pad=0.5", facecolor="lightblue", edgecolor="black")
+
+    for i, (y, summary) in enumerate(zip(ypos, filtered)):
+        summary_text = summary.split("**Chunk")[1]
+        summary_text = summary_text.replace("**:", ":").split("\n", 1)[-1].strip()
+        if len(summary_text) > 120:
+            summary_text = summary_text[:120] + "..."
+        ax.text(0.5, y, summary_text, ha='center', va='center', bbox=boxprops, fontsize=9)
+
+        if i < len(filtered) - 1:
+            ax.annotate('', xy=(0.5, y - 1.2), xytext=(0.5, y - 0.3),
+                        arrowprops=dict(arrowstyle="->", lw=1.5))
+
+    plt.tight_layout()
+    buf = io.BytesIO()
+    fig.savefig(buf, format='png', bbox_inches='tight')
+    plt.close(fig)
+    buf.seek(0)
+    return Image.open(buf)
+
+def process_chunk(i, chunk):
+    chunk_result = {'chunk': i + 1, 'status': '', 'time': 0}
+    start_time = time.time()
+
+    if sum(1 for c in chunk if not c.isalnum()) / len(chunk) > 0.5:
+        result = f"**Chunk {i+1}**: Skipped (equation-heavy)"
+        chunk_result['status'] = 'skipped'
+    else:
+        try:
+            summary = summarizer(chunk, max_length=80, min_length=15, do_sample=False)[0]['summary_text']
+            result = f"**Chunk {i+1}**:\n{summary}"
+            chunk_result['status'] = 'summarized'
+        except Exception as e:
+            result = f"**Chunk {i+1}**: ❌ Error: {str(e)}"
+            chunk_result['status'] = 'error'
+
+    chunk_result['time'] = time.time() - start_time
+    return result, chunk_result
+
+def summarize_file(file_bytes):
+    start = time.time()
+    summaries = []
+    chunk_info = []
+
+    try:
+        doc = fitz.open(stream=file_bytes, filetype="pdf")
+        text = "".join(page.get_text("text") for page in doc)
+        text = re.sub(r"\$\s*([^$]+)\s*\$", r"\1", text)
+        text = re.sub(r"\\cap", "intersection", text)
+        text = re.sub(r"\s+", " ", text).strip()
+        text = "".join(c for c in text if ord(c) < 128)
+    except Exception as e:
+        return f"❌ Text extraction failed: {str(e)}", None, None
+
+    if not text.strip():
+        return "❌ No text found", None, None
+
+    chunks = [text[i:i+1500] for i in range(0, min(len(text), 30000), 1500)]
+
+    with ThreadPoolExecutor(max_workers=4) as executor:
+        results = list(executor.map(lambda ic: process_chunk(*ic), enumerate(chunks)))
+
+    for summary, info in results:
+        summaries.append(summary)
+        chunk_info.append(info)
+
+    final_summary = f"**Processed chunks**: {len(chunks)}\n**Time**: {time.time() - start:.2f}s\n\n" + "\n\n".join(summaries)
+    process_img = visualize_chunk_status(chunk_info)
+    flow_img = create_summary_flowchart(summaries)
+    return final_summary, process_img, flow_img
+
+demo = gr.Interface(
+    fn=summarize_file,
+    inputs=gr.File(label="📄 Upload PDF", type="binary"),
+    outputs=[
+        gr.Textbox(label="📝 Summary", lines=20),
+        gr.Image(label="📊 Chunk Status", type="pil"),
+        gr.Image(label="🔁 Flow Summary", type="pil")
+    ],
+    title="📘 PDF Summarizer with Visual Flow",
+    description="Summarizes up to 30,000 characters from a PDF. Includes chunk status and flowchart visualizations."
+)
 
 if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
-    logger = logging.getLogger(__name__)
-    
     try:
         logger.info("Starting Gradio application on http://127.0.0.1:7860")
         demo.launch(
             share=False,
             server_name="127.0.0.1",
             server_port=7860,
-            debug=True  # Enable debug mode for detailed error output
+            debug=True
         )
     except Exception as e:
-        logger.error(f"Gradio launch failed: {str(e)}")
+        logger.error(f"Gradio launch failed on port 7860: {str(e)}")
         logger.info("Trying alternative port 7861...")
         try:
             demo.launch(
@@ -29,13 +159,6 @@ if __name__ == "__main__":
         except Exception as e2:
             logger.error(f"Gradio launch failed on port 7861: {str(e2)}")
             raise
-```
-
-**Changes**:
-- Added explicit `server_name="127.0.0.1"` for local binding.
-- Enabled `debug=True` for detailed Gradio logs.
-- Added a fallback to try port 7861 if 7860 fails.
-- Enhanced logging with `logging` module to capture initialization errors.