Initial commit

.github/workflows/ci.yaml

@@ -0,0 +1,38 @@
+name: Python application
+
+on:
+  push:
+    branches: [ "main" ]
+    paths-ignore:
+        - 'README.md'  
+  pull_request:
+    branches: [ "main" ]
+    paths-ignore:
+        - 'README.md'  
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest] 
+        python-version: ["3.8", "3.9"]
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip uninstall tox-gh-actions -y
+        pip install tox-gh-actions
+        pip install -r requirements.txt
+    - name: Test with tox
+      run: tox

.github/workflows/python-publish.yaml

@@ -0,0 +1,50 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.8'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 pytest
+        pip install -r requirements.txt
+        pip install build
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        pytest -v    
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

.gitignore

@@ -0,0 +1,162 @@
+# 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/
+
+src/pineconeutils/__pycache__

README.md

@@ -0,0 +1,77 @@
+# PineconeUtils
+
+PineconeUtils is a Python module designed to handle and process data for embedding and indexing using Pinecone, Cohere, and OpenAI services. This utility module makes it easy to load, chunk, prepare, and upsert data into a Pinecone index, making it ideal for applications involving text embedding and retrieval systems(RAG).
+
+## Features
+
+- Load text data from `.txt`, `.docx`, and `.pdf` files.
+- Chunk text data for processing.
+- Prepare embeddings using either Cohere or OpenAI models.
+- Upsert prepared data into a Pinecone index.
+
+## Installation
+
+To install PineconeUtils, you can use pip:
+
+```bash
+pip install pineconeutils
+```
+
+
+# Usage
+Here's a quick example of how to use PineconeUtils:
+
+## Setup
+First, ensure you have the necessary API keys and setup information:
+```bash
+pinecone_api_key = "your_pinecone_api_key"
+cohere_api_key = "your_cohere_api_key"
+openai_api_key = "your_openai_api_key"
+index_name = "your_index_name"
+namespace_id = "your_namespace_id"
+```
+
+# Load Data
+Load data from a supported file format:
+
+```bash
+from pineconeutils import PineconeUtils
+
+# Create instance of PineconeUtils
+pinecone = PineconeUtils(pinecone_api_key=cohere_api_key, openai_api_key=openai_api_key, index_name=index_name, namespace_id=namespace_id)
+
+path = "path_to_your_file.docx"
+data = pinecone.load_data(path)
+print("Loaded Data:", data)
+```
+
+# Process Data
+## Chunk and prepare data for embedding:
+
+```bash
+chunks = pinecone.chunk_data(data, chunk_size=100, chunk_overlap=10)
+print("Data Chunks:", chunks)
+
+prepared_data = pinecone.prepare_data(chunks, model="text-embedding-ada-002", service="openai")
+```
+
+# Upsert Data
+## Upsert data into Pinecone index:
+
+```bash
+successful = pinecone.upsert_data(prepared_data)
+print("Data upsertion was", "successful" if successful else "unsuccessful")
+```
+
+# Development
+
+To contribute to the development of PineconeUtils, you can clone the repository and submit pull requests.
+
+# Support
+If you encounter any issues or have questions, please file an issue on the GitHub repository.
+
+# License
+This project is licensed under the MIT License - see the LICENSE file for details.
+
+
+