Merge pull request #1 from amazingvince/main

adding support for 3.7 and colab

DocQA_example.ipynb

@@ -0,0 +1,57 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "DocQA_example.ipynb",
+      "provenance": [],
+      "collapsed_sections": [],
+      "authorship_tag": "ABX9TyPo0xYtL+cYJfNl6lhkeDjX",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/amazingvince/docqa/blob/main/DocQA_example.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "yS9UNjHnAAS9"
+      },
+      "outputs": [],
+      "source": [
+        "!git clone https://github.com/impira/docqa.git\n",
+        "!sudo apt install tesseract-ocr\n",
+        "!sudo apt-get install poppler-utils\n",
+        "!cd docqa && pip install .[all] "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!docqa scan \"who authored this paper?\" https://arxiv.org/pdf/2101.07597.pdf"
+      ],
+      "metadata": {
+        "id": "bKRRY5u2DV52"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

setup.py

@@ -14,10 +14,10 @@
 
 install_requires = [
     "torch >= 1.0",
-    "git+https://github.com/impira/transformers@153d1361c7dcc91c7735cae73e1f594cfcab3e21",
+    "transformers @ git+https://github.com/impira/transformers@153d1361c7dcc91c7735cae73e1f594cfcab3e21",
     "pdf2image",
     "pdfplumber",
-    "Pillow",
+    "pillow-simd",
     "pydantic",
     "pytesseract",  # TODO: Test what happens if the host machine does not have tesseract installed
     "requests",
@@ -59,7 +59,7 @@
     ],
     package_dir={"": "src"},
     packages=setuptools.find_packages(where="src"),
-    python_requires=">=3.8.0",
+    python_requires=">=3.7.0",
     entry_points={
         "console_scripts": ["docqa = docqa.cmd.__main__:main"],
     },

src/docqa/document.py

@@ -1,6 +1,7 @@
+import abc
 import logging
 import os
-from functools import cached_property
+
 from io import BytesIO
 from typing import List, Tuple
 
@@ -10,6 +11,13 @@
 from .ext import transformers
 
 
+try:
+  from functools import cached_property as cached_property
+except ImportError:
+  #for python 3.7 support fall back to just property
+  cached_property = property
+
+
 class UnsupportedDocument(Exception):
     def __init__(self, e):
         self.e = e
@@ -83,11 +91,12 @@ def apply_tesseract(*args, **kwargs):
     return transformers.apply_tesseract(*args, **kwargs)
 
 
-class Document:
+class Document(metaclass=abc.ABCMeta):
     def __init__(self, b):
         self.b = b
 
     @property
+    @abc.abstractmethod
     def context(self) -> Tuple[(str, List[int])]:
         raise NotImplementedError