Spaces:
Running
Running
File size: 3,096 Bytes
5b4fc38 3e87c53 cf9a79a 3e87c53 e5b6ad2 3e87c53 e5b6ad2 1e83db4 a74f8b0 3e87c53 cf9a79a 3e87c53 cf9a79a 3e87c53 cf9a79a 3e87c53 cf9a79a 3e87c53 e5b6ad2 cf9a79a 3e87c53 e5b6ad2 3e87c53 e5b6ad2 3e87c53 5b4fc38 3e87c53 5b4fc38 3e87c53 5b4fc38 3e87c53 5b4fc38 3e87c53 5b4fc38 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
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: UploadFile):
ext = file.filename.split(".")[-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."
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="/")
@app.get("/")
def home():
return RedirectResponse(url="/")
|