from base64 import b64decode, b64encode from io import BytesIO from fastapi import FastAPI, File, Form from PIL import Image from transformers import pipeline description = """ ## DocQA with 🤗 transformers, FastAPI, and Docker This app shows how to do Document Question Answering using FastAPI in a Docker Space 🚀 Check out the docs for the `/predict` endpoint below to try it out! """ # NOTE - we configure docs_url to serve the interactive Docs at the root path # of the app. This way, we can use the docs as a landing page for the app on Spaces. app = FastAPI(docs_url="/", description=description) pipe = pipeline("document-question-answering", model="impira/layoutlm-document-qa") @app.post("/predict") def predict(image_file: bytes = File(...), question: str = Form(...)): """ Using the document-question-answering pipeline from `transformers`, take a given input document (image) and a question about it, and return the predicted answer. The model used is available on the hub at: [`impira/layoutlm-document-qa`](https://huggingface.co./impira/layoutlm-document-qa). """ image = Image.open(BytesIO(image_file)) output = pipe(image, question) return output