Add elm ords install instructions

Author: ppinchuk

README.rst

@@ -33,6 +33,9 @@ Installing ELM
 
 .. inclusion-install
 
+NOTE: If you are installing ELM to run ordinance scraping and extraction,
+see the `ordinance-specific installation instructions <https://github.com/NREL/elm/blob/main/elm/ords/README.md>`_.
+
 Option #1 (basic usage):
 
 #. ``pip install NREL-elm``

elm/ords/README.md

@@ -0,0 +1,23 @@
+# Welcome to Energy Language Model - OrdinanceGPT
+
+The ordinance web scraping and data extraction portion of this codebase required a few extra dependencies that do not come out-of-the-box with the base ELM software.
+To set up ELM for ordinances, first create a conda environment. Then, _before installing ELM_, run the poppler installation:
+
+    $ conda install -c conda-forge poppler
+
+Then, install `pdftotext`:
+
+    $ pip install pdftotext
+
+(OPTIONAL) If you want to have access to Optical Character Recognition (OCR) for PDF parsing, you should also install pytesseract during this step:
+
+    $ pip install pytesseract pdf2image
+
+At this point, you can install ELM per the [front-page README](https://github.com/NREL/elm/blob/main/README.rst) instructions.
+
+After ELM installs successfully, you must instantiate the playwright module, which is used for web scraping.
+To do so, simply run:
+
+    $ playwright install
+
+Now you are ready to run ordinance retrieval and extraction. See the [example](https://github.com/NREL/elm/blob/main/examples/ordinance_gpt/README.rst) to get started.

requirements.txt

@@ -11,7 +11,6 @@ nrel-rex
 nltk
 numpy
 pandas
-pdftotext
 playwright
 PyPDF2
 python-slugify