├── requirements.txt ├── README.md ├── LICENSE ├── .gitignore └── app.py /requirements.txt: -------------------------------------------------------------------------------- 1 | openai 2 | spacy 3 | streamlit 4 | nltk 5 | gensim 6 | wordcloud 7 | python-dotenv -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # GPT3-Powered-Text-Analytics-App 2 | A GPT3 powered text analytics app built using low-code python library "Streamlit". 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2023 AI Anytime 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | import openai 3 | from wordcloud import WordCloud 4 | from dotenv import load_dotenv 5 | import os 6 | import re 7 | import json 8 | import spacy 9 | from spacy import displacy 10 | 11 | 12 | load_dotenv() 13 | 14 | # Set up OpenAI API credentials 15 | openai.api_key = os.getenv("OPENAI_API_KEY") 16 | 17 | HTML_WRAPPER = """
{}
""" 18 | 19 | #function for generating the word cloud 20 | def generate_wordcloud(text): 21 | # Create and generate a word cloud image 22 | wordcloud = WordCloud(width=800, height=800, 23 | background_color='black', min_font_size=10).generate(text) 24 | # Save the wordcloud image to disk 25 | wordcloud.to_file("wordcloud.png") 26 | # Return the image path 27 | return "wordcloud.png" 28 | 29 | def ner(text): 30 | nlp = spacy.load('en_core_web_sm') 31 | doc = nlp(text) 32 | html =displacy.render(doc, style='ent', jupyter=False) 33 | html = html.replace("\n\n","\n") 34 | st.write(HTML_WRAPPER.format(html),unsafe_allow_html=True) 35 | 36 | #function to extract key findings from text using Da-Vinci003 37 | def extract_key_findings(text): 38 | response = openai.Completion.create( 39 | model="text-davinci-003", 40 | prompt="Please find the key insights from the below text in maximum of 5 bullet points and also the summary in maximum of 3 sentences:\n"+text, 41 | temperature=0.7, 42 | max_tokens=256, 43 | top_p=1, 44 | frequency_penalty=0, 45 | presence_penalty=0) 46 | return response['choices'][0]['text'] 47 | 48 | #function to extract the most positive words from the text using Da-Vinci003 49 | def most_positive_words(text): 50 | response = openai.Completion.create( 51 | model="text-davinci-003", 52 | prompt="Please extract the most positive keywords from the below text\n"+text, 53 | temperature=0.7, 54 | max_tokens=256, 55 | top_p=1, 56 | frequency_penalty=0, 57 | presence_penalty=0) 58 | return response['choices'][0]['text'] 59 | 60 | # Streamlit Code 61 | st.set_page_config(layout="wide") 62 | 63 | st.title("GPT3 Powered Text Analytics App :page_with_curl:") 64 | 65 | with st.expander("About this application"): 66 | st.markdown("This app is built using the [OpenAI GPT3](https://platform.openai.com/), Streamlit, and Spacy.") 67 | 68 | 69 | input_text = st.text_area("Enter your text to analyze") 70 | 71 | if input_text is not None: 72 | if st.button("Analyze Text"): 73 | st.markdown("**Input Text**") 74 | st.info(input_text) 75 | col1, col2, col3 = st.columns([1,2,1]) 76 | with col1: 77 | st.markdown("**Key Findings based on your Text**") 78 | st.success(extract_key_findings(input_text)) 79 | with col2: 80 | st.markdown("**Output Text**") 81 | st.image(generate_wordcloud(input_text)) 82 | with col3: 83 | st.markdown("**Most Positive Words**") 84 | st.success(most_positive_words(input_text)) 85 | 86 | st.markdown("**Named Entity Recognition**") 87 | ner(input_text) 88 | --------------------------------------------------------------------------------