app.py

from fastapi import FastAPI, UploadFile, File
from PIL import Image
import pytesseract
import fitz  # PyMuPDF
import io
import uuid

app = FastAPI()

@app.get("/")
def home():
    return {
        "status": "running",
        "usage": "POST /extract (image or pdf file)"
    }

# -------------------------
# MAIN DOCUMENT PROCESSOR
# -------------------------
@app.post("/extract")
async def extract(file: UploadFile = File(...)):

    content = await file.read()
    filename = file.filename.lower()

    text = ""

    # -------------------------
    # PDF HANDLING
    # -------------------------
    if filename.endswith(".pdf"):
        doc = fitz.open(stream=content, filetype="pdf")

        for page in doc:
            text += page.get_text()

    # -------------------------
    # IMAGE OCR HANDLING
    # -------------------------
    else:
        image = Image.open(io.BytesIO(content))
        text = pytesseract.image_to_string(image)

    return {
        "filename": file.filename,
        "text": text.strip()
    }