metricstream_poc

Install dependencies

pip install -r requirements.txt

Add pdf contract files

Create a directory called data at the same level as the python notebook or script.
Drop the contract files in data (note: currently only pdf is supported).

Download best-matching version of specific model for your spaCy installation

python -m spacy download en_core_web_sm

Out-of-the-box: download best-matching default model and create shortcut link

python -m spacy download en

Test model load

import spacy
nlp = spacy.load("en_core_web_sm")

Test the code via flask web app

• navigate to the test folder
  
• Create a directory called data at the same level as the python notebook or script.
  
• Drop the contract files in data (note: currently only pdf is supported).
• start the test web app: python server.py
  
• open this url in web browser: http://127.0.0.1:5000/
  
• To test word search, enter a dictionary of words to search. An example is captured in the text box.
  Syntax: {'legal': 'anti-bribery', 'financial': 'escrow','financial': 'perpetual','SLA': 'breach','SLA': 'uptime'}
  which is key/value pairs (eg: category, word to search)