initial commit

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,58 @@
+import os
+
+# os.system('chmod 777 /tmp')
+# os.system('apt-get update -y')
+# os.system('apt-get install tesseract-ocr -y')
+# os.system('pip install -q pytesseract')
+
+from base64 import b64decode, b64encode
+from io import BytesIO
+
+
+import tesserocr
+from fastapi import FastAPI, File, Form
+from PIL import Image
+from transformers import pipeline
+#import streamlit as st
+
+# pytesseract.pytesseract.tesseract_cmd = r’./Tesseract-OCR/tesseract.exe’
+choices = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
+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()
+
+pipe = pipeline("document-question-answering", model="impira/layoutlm-document-qa")
+
+
+#st.write(output)
+
+# @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
+
+@app.get("/")
+def root():
+    return {"Hello":"world"}
+
+@app.get("/hello")
+def read_root():
+    image = 'https://templates.invoicehome.com/invoice-template-us-neat-750px.png'
+
+    question = "What is the invoice number?"
+    output = pipe(image, question)
+    return output

packages.txt

@@ -0,0 +1 @@
+tesseract-ocr-all

requirements.txt

@@ -0,0 +1,9 @@
+fastapi==0.74.*
+requests==2.27.*
+uvicorn[standard]==0.17.*
+sentencepiece==0.1.*
+torch==1.11.*
+transformers[vision]==4.*
+pytesseract==0.3.10
+tesserocr
+python-multipart==0.0.6