Initial Commit and updated Requirements

.dockerignore

@@ -0,0 +1,2 @@
+# ignore to pull into container
+.env-template

.env-template

@@ -0,0 +1,2 @@
+# Add your API Key below
+API_KEY_OPENAI = "YOUR KEY IS HERE"

.gitignore

@@ -0,0 +1,164 @@
+# Ignore .env fiile
+.env
+
+# Ignore others
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.10-bullseye
+
+WORKDIR /app
+
+COPY . /app
+
+RUN pip install -r requirements.txt
+
+EXPOSE 8501
+
+CMD ["streamlit", "run", "main.py"]

main.py

@@ -0,0 +1,88 @@
+#! /usr/bin/env Python3
+"""
+Tolken Calculation for OpenAI Models
+
+Based on notes found in:
+https://github.com/openai/openai-cookbook/blob/297c53430cad2d05ba763ab9dca64309cb5091e9/examples/How_to_count_tokens_with_tiktoken.ipynb
+
+"""
+
+from os import getenv
+from dotenv import load_dotenv
+import streamlit as st
+import tiktoken
+import openai
+
+load_dotenv('./.env')
+
+openai.api_key = getenv('API_KEY_OPENAI')
+
+if openai.api_key:
+    print("API KEY LOADED")
+else:
+    st.error('No API Key found')
+
+st.title('ChatGPT TokenCalculator')
+
+def load():
+    """_summary_
+
+    Returns:
+        _type_: _description_
+    """    
+    upload_file = st.file_uploader('Please upload a .txt or .pdf File', ['.txt', '.pdf'])
+    return upload_file
+
+def num_tokens_from_string(string: str, encoding_name: str) -> int:
+    """Returns the number of tokens in a text string."""
+    encoding = tiktoken.get_encoding(encoding_name)
+    num_tokens = len(encoding.encode(string))
+    return num_tokens
+
+def get_model_encoding(model):
+    """_summary_
+
+    Args:
+        model (_type_): _description_
+
+    Returns:
+        _type_: _description_
+    """
+    encoding = tiktoken.encoding_for_model(model)
+    return encoding 
+
+def get_models():
+    """_summary_
+
+    Yields:
+        _type_: _description_
+    """
+    models = openai.Engine.list()
+    for model in models['data']:
+        yield model['id']
+
+file = load()
+if file is not None:
+    st.write("File Loaded")
+    file_output = file.read().decode()
+
+    tab1, tab2, tab3  = st.tabs(["OpenAI Model and Encoding", "Number of Tokens", "Encodings"])
+
+    with tab1:
+        st.subheader("OpenAI Model and Encoding")
+        model = st.selectbox('Choose OpenAI Model', list(get_models()))
+        encoding = get_model_encoding(model)
+        st.write(f"The {model} model uses {encoding.name} for encoding.")
+
+    with tab2:
+        st.subheader("Word Block")
+        word_block = list(file_output.split())
+        st.write(f"Word count: {len(word_block)}")
+        num_tokens_from_string = num_tokens_from_string(file_output, encoding.name)
+        st.write(f"There are {num_tokens_from_string} token(s) in the file.")
+        st.write(f"File Output:\n\n{file_output}")
+
+    with tab3:
+        encoded_list = encoding.encode(file_output)
+        st.subheader(f"Text Turned into Encoded Tokens - {num_tokens_from_string} token(s)")
+        st.table(encoded_list)

requirements.txt

@@ -0,0 +1,5 @@
+# Required Modules
+openai==0.27.8
+streamlit==1.23.1
+tiktoken==0.4.0
+python-dotenv==1.0.0