======
pdfgpt
======
.. image:: https://img.shields.io/pypi/v/pdfgpt.svg
:target: https://pypi.python.org/pypi/pdfgpt
.. image:: https://readthedocs.org/projects/pdfgpt/badge/?version=latest
:target: https://pdfgpt.readthedocs.io/en/latest/?version=latest
:alt: Documentation Status
.. image:: https://pepy.tech/badge/pdfgpt
:target: https://pepy.tech/badge/pdfgpt
:alt: Downloads
.. image:: https://static.pepy.tech/badge/pdfgpt/month
:target: https://pepy.tech/badge/pdfgpt/month
:alt: Downloads
pdfgpt is a Python package that provides users with the ability to engage in natural language conversations with their PDF documents.
* Free software: MIT license
* Documentation: https://pdfgpt.readthedocs.io.
**Source:** Openai - https://github.com/openai/openai-cookbook
How to install
---------------
**Environments -> base (root) -> open terminal -> pip install pdfgpt**
* pip install pdfgpt
Example
-------
.. code-block:: python
from pdfgpt import *
d = PDFBot(openai_key='OPENAI_KEY')
print('Example')
extracted_text, num_pages = d.generateText(file_path='tests/epanet_matlab_toolkit.pdf')
df = d.generateEmbeddings(extracted_text)
print('USER: What is EPANET?')
prompt = d.generatePrompt(df, num_pages, 'What is EPANET?')
response = d.sendPrompt(prompt, model="gpt-3.5-turbo")
print('AI')
print(response, '\n')
What is EPANET?
EPANET is a software for modeling water distribution systems' hydraulic and quality dynamics, initially developed by the US Environmental Protection Agency in the C programming language in 1994. It uses a geometric representation of the pipe network, along with a set of initial conditions, rules of operation, and uses this information to compute flows, pressures, and water quality throughout the network, for a certain period of time.
.. code-block:: python
print('USER: Give me the command to load a network?')
prompt = d.generatePrompt(df, num_pages, 'Give me the command to load a network?')
response = d.sendPrompt(prompt, model="gpt-3.5-turbo", temperature=0.9)
print('AI')
print(response)
What is the command to load a network?
The command to load a network is:
G = epanet( ’BWSN_Network_1 .inp’);%Load EPANET Input file
G.loadMSXFile( ’Arsenite .msx’);%Load MSX file
Features
--------
* TODO
Credits
-------
This package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.
.. _Cookiecutter: https://github.com/audreyr/cookiecutter
.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage
=======
History
=======
0.1.0 (2023-05-11)
------------------
* First release on PyPI.
Raw data
{
"_id": null,
"home_page": "https://github.com/Mariosmsk/pdfgpt",
"name": "pdfgpt",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "pdfgpt",
"author": "Marios S. Kyriakou",
"author_email": "kiriakou.marios@ucy.ac.cy",
"download_url": "https://files.pythonhosted.org/packages/4e/95/cdee5b5f8019764ce8e33aa6957fc9d194762b38600d5ddea60d2dbf9101/pdfgpt-0.2.2.tar.gz",
"platform": null,
"description": "======\r\npdfgpt\r\n======\r\n\r\n\r\n.. image:: https://img.shields.io/pypi/v/pdfgpt.svg\r\n :target: https://pypi.python.org/pypi/pdfgpt\r\n\r\n.. image:: https://readthedocs.org/projects/pdfgpt/badge/?version=latest\r\n :target: https://pdfgpt.readthedocs.io/en/latest/?version=latest\r\n :alt: Documentation Status\r\n\r\n.. image:: https://pepy.tech/badge/pdfgpt\r\n :target: https://pepy.tech/badge/pdfgpt\r\n :alt: Downloads\r\n\r\n.. image:: https://static.pepy.tech/badge/pdfgpt/month\r\n :target: https://pepy.tech/badge/pdfgpt/month\r\n :alt: Downloads\r\n\r\npdfgpt is a Python package that provides users with the ability to engage in natural language conversations with their PDF documents.\r\n\r\n\r\n* Free software: MIT license\r\n* Documentation: https://pdfgpt.readthedocs.io.\r\n\r\n**Source:** Openai - https://github.com/openai/openai-cookbook\r\n\r\nHow to install\r\n---------------\r\n\r\n**Environments -> base (root) -> open terminal -> pip install pdfgpt**\r\n\r\n* pip install pdfgpt\r\n\r\nExample\r\n-------\r\n\r\n.. code-block:: python\r\n\r\n from pdfgpt import *\r\n\r\n d = PDFBot(openai_key='OPENAI_KEY')\r\n\r\n print('Example')\r\n extracted_text, num_pages = d.generateText(file_path='tests/epanet_matlab_toolkit.pdf')\r\n df = d.generateEmbeddings(extracted_text)\r\n\r\n print('USER: What is EPANET?')\r\n prompt = d.generatePrompt(df, num_pages, 'What is EPANET?')\r\n response = d.sendPrompt(prompt, model=\"gpt-3.5-turbo\")\r\n print('AI')\r\n print(response, '\\n')\r\n\r\nWhat is EPANET?\r\n\r\nEPANET is a software for modeling water distribution systems' hydraulic and quality dynamics, initially developed by the US Environmental Protection Agency in the C programming language in 1994. It uses a geometric representation of the pipe network, along with a set of initial conditions, rules of operation, and uses this information to compute flows, pressures, and water quality throughout the network, for a certain period of time.\r\n\r\n.. code-block:: python\r\n\r\n print('USER: Give me the command to load a network?')\r\n prompt = d.generatePrompt(df, num_pages, 'Give me the command to load a network?')\r\n response = d.sendPrompt(prompt, model=\"gpt-3.5-turbo\", temperature=0.9)\r\n print('AI')\r\n print(response)\r\n\r\nWhat is the command to load a network?\r\n\r\nThe command to load a network is:\r\n\r\nG = epanet( \u00e2\u20ac\u2122BWSN_Network_1 .inp\u00e2\u20ac\u2122);%Load EPANET Input file\r\n\r\nG.loadMSXFile( \u00e2\u20ac\u2122Arsenite .msx\u00e2\u20ac\u2122);%Load MSX file\r\n\r\nFeatures\r\n--------\r\n\r\n* TODO\r\n\r\nCredits\r\n-------\r\n\r\nThis package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.\r\n\r\n.. _Cookiecutter: https://github.com/audreyr/cookiecutter\r\n.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage\r\n\r\n\r\n=======\r\nHistory\r\n=======\r\n\r\n0.1.0 (2023-05-11)\r\n------------------\r\n\r\n* First release on PyPI.\r\n\r\n\r\n",
"bugtrack_url": null,
"license": "MIT license",
"summary": "pdfgpt is a Python package that provides users with the ability to engage in natural language conversations with their PDF documents.",
"version": "0.2.2",
"project_urls": {
"Homepage": "https://github.com/Mariosmsk/pdfgpt"
},
"split_keywords": [
"pdfgpt"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "4e95cdee5b5f8019764ce8e33aa6957fc9d194762b38600d5ddea60d2dbf9101",
"md5": "6004c263563e70970e64c97b0c529990",
"sha256": "e6e28302261cc766b90e21dd2e5618f9ec7c1e7b5f412aa27120dab0eaa35fc5"
},
"downloads": -1,
"filename": "pdfgpt-0.2.2.tar.gz",
"has_sig": false,
"md5_digest": "6004c263563e70970e64c97b0c529990",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 3272691,
"upload_time": "2023-07-06T13:18:41",
"upload_time_iso_8601": "2023-07-06T13:18:41.369732Z",
"url": "https://files.pythonhosted.org/packages/4e/95/cdee5b5f8019764ce8e33aa6957fc9d194762b38600d5ddea60d2dbf9101/pdfgpt-0.2.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-07-06 13:18:41",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Mariosmsk",
"github_project": "pdfgpt",
"travis_ci": true,
"coveralls": false,
"github_actions": false,
"requirements": [],
"tox": true,
"lcname": "pdfgpt"
}
JSON
