Spaces:
Running
Running
| import gradio as gr | |
| from transformers import pipeline | |
| from PIL import Image | |
| # Load summarization and image captioning models | |
| summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6") | |
| image_captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning") | |
| def analyze_input(file, question=None): | |
| if file is None: | |
| return "Please upload a document or image." | |
| filename = file.name.lower() | |
| if filename.endswith((".png", ".jpg", ".jpeg")): | |
| image = Image.open(file) | |
| caption = image_captioner(image)[0]['generated_text'] | |
| return f"📷 Image Interpretation:\n{caption}" | |
| elif filename.endswith((".pdf", ".docx", ".pptx", ".xlsx")): | |
| from PyPDF2 import PdfReader | |
| import docx | |
| import pptx | |
| import pandas as pd | |
| try: | |
| text = "" | |
| if filename.endswith(".pdf"): | |
| reader = PdfReader(file) | |
| text = "\n".join([page.extract_text() for page in reader.pages if page.extract_text()]) | |
| elif filename.endswith(".docx"): | |
| doc = docx.Document(file) | |
| text = "\n".join([p.text for p in doc.paragraphs if p.text.strip()]) | |
| elif filename.endswith(".pptx"): | |
| prs = pptx.Presentation(file) | |
| for slide in prs.slides: | |
| for shape in slide.shapes: | |
| if hasattr(shape, "text"): | |
| text += shape.text + "\n" | |
| elif filename.endswith(".xlsx"): | |
| df = pd.read_excel(file, sheet_name=None) | |
| text = "\n".join([df[sheet].to_string() for sheet in df]) | |
| if not text.strip(): | |
| return "Could not extract meaningful text from the document." | |
| summary = summarizer(text[:3000], max_length=200, min_length=30, do_sample=False) | |
| return f"📄 Document Summary:\n{summary[0]['summary_text']}" | |
| except Exception as e: | |
| return f"❌ Error processing document: {str(e)}" | |
| else: | |
| return "Unsupported file type. Please upload a valid image or document." | |
| iface = gr.Interface( | |
| fn=analyze_input, | |
| inputs=gr.File(label="Upload Document or Image"), | |
| outputs=gr.Textbox(label="Result", lines=10), | |
| title="Document & Image Analysis Web Service", | |
| description="Upload a document (PDF, DOCX, PPTX, XLSX) to get a summary or an image to get a caption. Runs fully on CPU." | |
| ) | |
| demo = gr.TabbedInterface(iface,"Docs and Images") | |
| app = gr.mount_gradio_app(app, demo, path="/") | |
| def home(): | |
| return RedirectResponse(url="/") | |