Spaces:
Running
Running
| import gradio as gr | |
| from transformers import pipeline | |
| from PIL import Image | |
| from fastapi import FastAPI | |
| from starlette.responses import RedirectResponse | |
| # 🔥 Fix for Pydantic v2 compatibility with Gradio | |
| import gradio.context | |
| from pydantic import BaseModel | |
| if not hasattr(BaseModel, "model_fields"): # model_fields was renamed from __fields__ in Pydantic v1 → v2 | |
| BaseModel.model_fields = BaseModel.__fields__ | |
| # 🔁 Load Hugging Face Pipelines | |
| summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6") | |
| image_captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning") | |
| # 🚀 Create FastAPI App | |
| app = FastAPI() | |
| def analyze_input(file, question=None): | |
| if file is None: | |
| return "Please upload a document or image." | |
| filename = file.name.lower() | |
| # 🖼️ Image | |
| if filename.endswith((".png", ".jpg", ".jpeg")): | |
| image = Image.open(file) | |
| caption = image_captioner(image)[0]['generated_text'] | |
| return f"📷 Image Interpretation:\n{caption}" | |
| # 📄 Document | |
| elif filename.endswith((".pdf", ".docx", ".pptx", ".xlsx")): | |
| import pdfplumber | |
| import docx | |
| import pptx | |
| import pandas as pd | |
| try: | |
| text = "" | |
| if filename.endswith(".pdf"): | |
| with pdfplumber.open(file) as pdf: | |
| text = "\n".join([page.extract_text() for page in pdf.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." | |
| # 🎛️ Gradio UI | |
| 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) or image to get a summary or caption. CPU-friendly." | |
| ) | |
| # ⌨️ Wrap in Tabbed UI | |
| demo = gr.TabbedInterface([iface], ["Docs and Images"]) | |
| # 🔗 Mount Gradio to FastAPI | |
| app = gr.mount_gradio_app(app, demo, path="/") | |
| # 🏠 Base redirect | |
| def home(): | |
| return RedirectResponse(url="/") | |