nlr-elm 0.0.35__tar.gz

nlr_elm-0.0.35/LICENSE.txt

@@ -0,0 +1,28 @@
+BSD 3-Clause License
+
+Copyright (c) 2023, Alliance for Sustainable Energy LLC, All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

nlr_elm-0.0.35/PKG-INFO

@@ -0,0 +1,156 @@
+Metadata-Version: 2.4
+Name: nlr_elm
+Version: 0.0.35
+Summary: Energy Language Model
+Home-page: https://github.com/NatLabRockies/elm
+Author: Grant Buster
+Author-email: grant.buster@nlr.gov
+License: BSD 3-Clause
+Keywords: elm
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.9
+License-File: LICENSE.txt
+Requires-Dist: openai>=1.1.0
+Requires-Dist: aiohttp
+Requires-Dist: beautifulsoup4
+Requires-Dist: camoufox
+Requires-Dist: click
+Requires-Dist: crawl4ai
+Requires-Dist: ddgs
+Requires-Dist: fake_useragent>=2.0.3
+Requires-Dist: google-api-python-client
+Requires-Dist: google-search-results
+Requires-Dist: html2text
+Requires-Dist: httpx
+Requires-Dist: langchain-text-splitters
+Requires-Dist: lxml
+Requires-Dist: matplotlib
+Requires-Dist: networkx
+Requires-Dist: nlr-rex
+Requires-Dist: nltk
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: tf-playwright-stealth
+Requires-Dist: PyPDF2
+Requires-Dist: python-slugify
+Requires-Dist: rebrowser-playwright
+Requires-Dist: scipy
+Requires-Dist: scrapling
+Requires-Dist: tabulate
+Requires-Dist: tavily-python
+Requires-Dist: tiktoken
+Provides-Extra: dev
+Requires-Dist: openai>=1.1.0; extra == "dev"
+Requires-Dist: aiohttp; extra == "dev"
+Requires-Dist: beautifulsoup4; extra == "dev"
+Requires-Dist: camoufox; extra == "dev"
+Requires-Dist: click; extra == "dev"
+Requires-Dist: crawl4ai; extra == "dev"
+Requires-Dist: ddgs; extra == "dev"
+Requires-Dist: fake_useragent>=2.0.3; extra == "dev"
+Requires-Dist: google-api-python-client; extra == "dev"
+Requires-Dist: google-search-results; extra == "dev"
+Requires-Dist: html2text; extra == "dev"
+Requires-Dist: httpx; extra == "dev"
+Requires-Dist: langchain-text-splitters; extra == "dev"
+Requires-Dist: lxml; extra == "dev"
+Requires-Dist: matplotlib; extra == "dev"
+Requires-Dist: networkx; extra == "dev"
+Requires-Dist: nlr-rex; extra == "dev"
+Requires-Dist: nltk; extra == "dev"
+Requires-Dist: numpy; extra == "dev"
+Requires-Dist: pandas; extra == "dev"
+Requires-Dist: tf-playwright-stealth; extra == "dev"
+Requires-Dist: PyPDF2; extra == "dev"
+Requires-Dist: python-slugify; extra == "dev"
+Requires-Dist: rebrowser-playwright; extra == "dev"
+Requires-Dist: scipy; extra == "dev"
+Requires-Dist: scrapling; extra == "dev"
+Requires-Dist: tabulate; extra == "dev"
+Requires-Dist: tavily-python; extra == "dev"
+Requires-Dist: tiktoken; extra == "dev"
+Requires-Dist: pytest>=5.2; extra == "dev"
+Requires-Dist: pytest-mock; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: flaky>=3.8.1; extra == "dev"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+***************************
+Energy Language Model (ELM)
+***************************
+
+.. image:: https://github.com/NatLabRockies/elm/workflows/Documentation/badge.svg
+    :target: https://natlabrockies.github.io/elm/
+
+.. image:: https://github.com/NatLabRockies/elm/workflows/pytests/badge.svg
+    :target: https://github.com/NatLabRockies/elm/actions?query=workflow%3A%22pytests%22
+
+.. image:: https://github.com/NatLabRockies/elm/workflows/Lint%20Code%20Base/badge.svg
+    :target: https://github.com/NatLabRockies/elm/actions?query=workflow%3A%22Lint+Code+Base%22
+
+.. image:: https://img.shields.io/pypi/pyversions/NLR-elm.svg
+    :target: https://pypi.org/project/NLR-elm/
+
+.. image:: https://badge.fury.io/py/NLR-elm.svg
+    :target: https://badge.fury.io/py/NLR-elm
+
+.. image:: https://zenodo.org/badge/690793778.svg
+  :target: https://zenodo.org/doi/10.5281/zenodo.10070538
+
+The Energy Language Model (ELM) software provides interfaces to apply Large Language Models (LLMs) like ChatGPT and GPT-4 to energy research. For example, you might be interested in:
+
+- `Converting PDFs into a text database <https://natlabrockies.github.io/elm/_autosummary/elm.pdf.PDFtoTXT.html#elm.pdf.PDFtoTXT>`_
+- `Chunking text documents and embedding into a vector database <https://nrenatlabrockiesl.github.io/elm/_autosummary/elm.embed.ChunkAndEmbed.html#elm.embed.ChunkAndEmbed>`_
+- `Performing recursive document summarization <https://natlabrockies.github.io/elm/_autosummary/elm.summary.Summary.html#elm.summary.Summary>`_
+- `Building an automated data extraction workflow using decision trees <https://natlabrockies.github.io/elm/_autosummary/elm.tree.DecisionTree.html#elm.tree.DecisionTree>`_
+- `Building a chatbot app that interfaces with reports from OSTI <https://github.com/NatLabRockies/elm/tree/main/examples/energy_wizard>`_
+
+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/NatLabRockies/elm/blob/main/elm/ords/README.md>`_.
+
+Option #1 (basic usage):
+
+#. ``pip install NLR-elm``
+
+Option #2 (developer install):
+
+#. from home dir, ``git clone git@github.com:NatLabRockies/elm.git``
+#. Create ``elm`` environment and install package
+    a) Create a conda env: ``conda create -n elm``
+    b) Run the command: ``conda activate elm``
+    c) ``cd`` into the repo cloned in 1.
+    d) Prior to running ``pip`` below, make sure the branch is correct (install
+       from main!)
+    e) Install ``elm`` and its dependencies by running:
+       ``pip install .`` (or ``pip install -e .`` if running a dev branch
+       or working on the source code)
+
+.. inclusion-acknowledgements
+
+Acknowledgments
+===============
+
+This work was authored by the National Laboratory of the Rockies, operated by Alliance for Energy Innovation, LLC, for the U.S. Department of Energy (DOE) under Contract No. DE-AC36-08GO28308. Funding provided by the DOE Wind Energy Technologies Office (WETO), the DOE Solar Energy Technologies Office (SETO), and internal research funds at the National Laboratory of the Rockies. The views expressed in the article do not necessarily represent the views of the DOE or the U.S. Government. The U.S. Government retains and the publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this work, or allow others to do so, for U.S. Government purposes.

nlr_elm-0.0.35/README.rst

@@ -0,0 +1,61 @@
+***************************
+Energy Language Model (ELM)
+***************************
+
+.. image:: https://github.com/NatLabRockies/elm/workflows/Documentation/badge.svg
+    :target: https://natlabrockies.github.io/elm/
+
+.. image:: https://github.com/NatLabRockies/elm/workflows/pytests/badge.svg
+    :target: https://github.com/NatLabRockies/elm/actions?query=workflow%3A%22pytests%22
+
+.. image:: https://github.com/NatLabRockies/elm/workflows/Lint%20Code%20Base/badge.svg
+    :target: https://github.com/NatLabRockies/elm/actions?query=workflow%3A%22Lint+Code+Base%22
+
+.. image:: https://img.shields.io/pypi/pyversions/NLR-elm.svg
+    :target: https://pypi.org/project/NLR-elm/
+
+.. image:: https://badge.fury.io/py/NLR-elm.svg
+    :target: https://badge.fury.io/py/NLR-elm
+
+.. image:: https://zenodo.org/badge/690793778.svg
+  :target: https://zenodo.org/doi/10.5281/zenodo.10070538
+
+The Energy Language Model (ELM) software provides interfaces to apply Large Language Models (LLMs) like ChatGPT and GPT-4 to energy research. For example, you might be interested in:
+
+- `Converting PDFs into a text database <https://natlabrockies.github.io/elm/_autosummary/elm.pdf.PDFtoTXT.html#elm.pdf.PDFtoTXT>`_
+- `Chunking text documents and embedding into a vector database <https://nrenatlabrockiesl.github.io/elm/_autosummary/elm.embed.ChunkAndEmbed.html#elm.embed.ChunkAndEmbed>`_
+- `Performing recursive document summarization <https://natlabrockies.github.io/elm/_autosummary/elm.summary.Summary.html#elm.summary.Summary>`_
+- `Building an automated data extraction workflow using decision trees <https://natlabrockies.github.io/elm/_autosummary/elm.tree.DecisionTree.html#elm.tree.DecisionTree>`_
+- `Building a chatbot app that interfaces with reports from OSTI <https://github.com/NatLabRockies/elm/tree/main/examples/energy_wizard>`_
+
+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/NatLabRockies/elm/blob/main/elm/ords/README.md>`_.
+
+Option #1 (basic usage):
+
+#. ``pip install NLR-elm``
+
+Option #2 (developer install):
+
+#. from home dir, ``git clone git@github.com:NatLabRockies/elm.git``
+#. Create ``elm`` environment and install package
+    a) Create a conda env: ``conda create -n elm``
+    b) Run the command: ``conda activate elm``
+    c) ``cd`` into the repo cloned in 1.
+    d) Prior to running ``pip`` below, make sure the branch is correct (install
+       from main!)
+    e) Install ``elm`` and its dependencies by running:
+       ``pip install .`` (or ``pip install -e .`` if running a dev branch
+       or working on the source code)
+
+.. inclusion-acknowledgements
+
+Acknowledgments
+===============
+
+This work was authored by the National Laboratory of the Rockies, operated by Alliance for Energy Innovation, LLC, for the U.S. Department of Energy (DOE) under Contract No. DE-AC36-08GO28308. Funding provided by the DOE Wind Energy Technologies Office (WETO), the DOE Solar Energy Technologies Office (SETO), and internal research funds at the National Laboratory of the Rockies. The views expressed in the article do not necessarily represent the views of the DOE or the U.S. Government. The U.S. Government retains and the publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this work, or allow others to do so, for U.S. Government purposes.

nlr_elm-0.0.35/elm/__init__.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+"""
+Energy Language Model
+"""
+
+import os
+import logging
+from functools import partial, partialmethod
+from elm.base import ApiBase
+from elm.chunk import Chunker
+from elm.embed import ChunkAndEmbed
+from elm.pdf import PDFtoTXT
+from elm.summary import Summary
+from elm.tree import DecisionTree
+from elm.wizard import EnergyWizard
+from elm.web.osti import OstiRecord, OstiList
+
+__author__ = """Grant Buster"""
+__email__ = "Grant.Buster@nlr.gov"
+
+ELM_DIR = os.path.dirname(os.path.realpath(__file__))
+TEST_DATA_DIR = os.path.join(os.path.dirname(ELM_DIR), 'tests', 'data')
+
+logging.TRACE = 5
+logging.addLevelName(logging.TRACE, 'TRACE')
+logging.Logger.trace = partialmethod(logging.Logger.log, logging.TRACE)
+logging.trace = partial(logging.log, logging.TRACE)