Spaces:
Running
Running
| from fastapi import FastAPI, UploadFile | |
| from fastapi.responses import RedirectResponse | |
| import fitz # PyMuPDF | |
| import docx | |
| import openpyxl | |
| import pptx | |
| from PIL import Image | |
| import io | |
| import gradio as gr | |
| from transformers import pipeline | |
| # Models | |
| summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6") | |
| image_captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning") | |
| app = FastAPI() | |
| # ------------------------- | |
| # Document Extraction Utils | |
| # ------------------------- | |
| def extract_text_from_pdf(file): | |
| text = "" | |
| with fitz.open(stream=file.read(), filetype="pdf") as doc: | |
| for page in doc: | |
| text += page.get_text() | |
| return text | |
| def extract_text_from_docx(file): | |
| doc = docx.Document(io.BytesIO(file.read())) | |
| return "\n".join([para.text for para in doc.paragraphs if para.text.strip()]) | |
| def extract_text_from_pptx(file): | |
| text = [] | |
| prs = pptx.Presentation(io.BytesIO(file.read())) | |
| for slide in prs.slides: | |
| for shape in slide.shapes: | |
| if hasattr(shape, "text"): | |
| text.append(shape.text) | |
| return "\n".join(text) | |
| def extract_text_from_xlsx(file): | |
| wb = openpyxl.load_workbook(io.BytesIO(file.read())) | |
| text = [] | |
| for sheet in wb.sheetnames: | |
| ws = wb[sheet] | |
| for row in ws.iter_rows(values_only=True): | |
| line = " ".join(str(cell) for cell in row if cell) | |
| text.append(line) | |
| return "\n".join(text) | |
| def summarize_document(file): | |
| import os | |
| name = getattr(file, "name", "") | |
| ext = os.path.splitext(name)[1].lower() | |
| if ext == ".pdf": | |
| text = extract_text_from_pdf(file) | |
| elif ext == ".docx": | |
| text = extract_text_from_docx(file) | |
| elif ext == ".pptx": | |
| text = extract_text_from_pptx(file) | |
| elif ext == ".xlsx": | |
| text = extract_text_from_xlsx(file) | |
| else: | |
| return "Unsupported file format." | |
| if not text.strip(): | |
| return "No extractable text found." | |
| text = text[:3000] | |
| try: | |
| summary = summarizer(text, max_length=150, min_length=30, do_sample=False) | |
| return summary[0]["summary_text"] | |
| except Exception as e: | |
| return f"Summarization error: {e}" | |
| def interpret_image(image): | |
| if image is None: | |
| return "No image uploaded." | |
| try: | |
| return image_captioner(image)[0]["generated_text"] | |
| except Exception as e: | |
| return f"Image captioning error: {e}" | |
| # ------------------------- | |
| # Gradio Interfaces | |
| # ------------------------- | |
| doc_summary = gr.Interface( | |
| fn=summarize_document, | |
| inputs=gr.File(label="Upload a Document"), | |
| outputs="text", | |
| title="📄 Document Summarizer" | |
| ) | |
| img_caption = gr.Interface( | |
| fn=interpret_image, | |
| inputs=gr.Image(type="pil", label="Upload an Image"), | |
| outputs="text", | |
| title="🖼️ Image Interpreter" | |
| ) | |
| # ------------------------- | |
| # Combine into Gradio + FastAPI | |
| # ------------------------- | |
| demo = gr.TabbedInterface([doc_summary, img_caption], ["Document QA", "Image QA"]) | |
| app = gr.mount_gradio_app(app, demo, path="/") | |
| def home(): | |
| return RedirectResponse(url="/") | |