Upload 3 files

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+from transformers import pipeline
+from helper import extract_text_from_pdf, extract_text_from_image, generate_todo
+
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+def process_input(file):
+    file_type = file.name.split('.')[-1]
+
+    if file_type.lower() == "pdf":
+        text = extract_text_from_pdf(file.name)
+    elif file_type.lower() in ["png", "jpg", "jpeg"]:
+        text = extract_text_from_image(file.name)
+    else:
+        text = file.read().decode("utf-8")
+    
+    if not text.strip():
+        return "No content found", ""
+    
+    summary = summarizer(text, max_length=120, min_length=30, do_sample=False)[0]['summary_text']
+    todos = generate_todo(summary)
+    
+    return summary, todos
+
+iface = gr.Interface(
+    fn=process_input,
+    inputs=gr.File(type="file", label="Upload text/pdf/image"),
+    outputs=[
+        gr.Textbox(label="Summary", lines=5),
+        gr.Textbox(label="To-Do List", lines=5)
+    ],
+    title="🧠 Multimodal Productivity Agent",
+    description="Upload text, PDFs, or images to generate a summary and actionable to-do list."
+)
+
+iface.launch()

helper.py

@@ -0,0 +1,22 @@
+import pdfplumber
+import pytesseract
+from PIL import Image
+
+# Extract text from PDF
+def extract_text_from_pdf(pdf_file):
+    all_text = ""
+    with pdfplumber.open(pdf_file) as pdf:
+        for page in pdf.pages:
+            all_text += page.extract_text() + "\n"
+    return all_text.strip()
+
+# Extract text from image
+def extract_text_from_image(image_file):
+    image = Image.open(image_file)
+    return pytesseract.image_to_string(image)
+
+# Basic to-do list generator
+def generate_todo(summary):
+    lines = summary.strip().split('.')
+    todos = [f"🔹 {line.strip()}" for line in lines if line.strip()]
+    return '\n'.join(todos)

requirements.txt.txt

@@ -0,0 +1,6 @@
+gradio
+transformers
+pdfplumber
+pytesseract
+Pillow
+torch