CSVAlchemy
A Python SDK for processing and analyzing spreadsheets using LLMs.
Installation
pip install CSVAlchemy-sdk
Overview
CSVAlchemy provides Excel processing capabilities. The library helps you efficiently process, analyze, and extract insights from spreadsheet data.
Features
- Spreadsheet Processing - Handle Excel and CSV files with advanced features
- Data Extraction - Extract structured data from complex spreadsheets
- Formula Extraction - Extract all the formula's from you spreadsheets
- Pivot Table Support - Process and analyze pivot tables
- Chart Analysis - Extract and encode chart data
- Conditional Formatting - Capture conditional formatting rules
- API Client - Easy-to-use client for the CSVAlchemy API
CSVAlchemy Feature Comparison
| Feature | Support |
|---|---|
| Excel (.xlsx) Processing | ✓ |
| Formula Extraction | ✓ |
| Merged Cell Detection | ✓ |
| Header Detection | ✓ (configurable) |
| Structural Anchor Extraction | ✓ |
| Python SDK | ✓ |
| Customizable Configuration | ✓ |
| Error Handling Modes | ✓ (configurable) |
| Parallel Processing | ✓ (configurable) |
| Memory Optimization | ✓ (chunking configurable) |
| Comprehensive Logging | ✓ |
| Open Source | ✓ (MIT License) |
Usage
from CSVAlchemy.core import encode_workbook
from CSVAlchemy.utils import load_workbook_from_file
from CSVAlchemy.config import get_config
config = get_config()
print("Default config:", config)
try:
# Replace with path to your test Excel file
workbook = load_workbook_from_file("Company_Financial_Data_For_PE.xlsx")
encoded_data = encode_workbook(workbook, config)
print(f"Processed {len(encoded_data['sheets'])} sheets")
except Exception as e:
print(f"Error processing workbook: {e}")
Contributing to CSVAlchemy
We welcome contributions from the community! This guide will help you set up your local development environment and understand our contribution process.
Local Development Setup
-
Fork and Clone the Repository
git clone https://github.com/Unsiloed-ai/spreadsheet-llm.git cd spreadsheet-llm
-
Set Up a Virtual Environment
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install Development Dependencies
pip install -e ".[dev]"
-
Run Tests to Verify Setup
pytest
Development Workflow
-
Create a Feature Branch
git checkout -b feature/your-feature-name
-
Make Your Changes
- Write code following our style guidelines
- Add tests for new functionality
- Update documentation as needed
-
Run Tests and Linting
# Run tests pytest # Run linting flake8 # Run formatter black .
-
Commit Your Changes
git add . git commit -m "Add a descriptive commit message"
-
Push to Your Fork
git push origin feature/your-feature-name
-
Create a Pull Request
Go to the original repository and create a pull request from your fork.
Code Style Guidelines
- Follow PEP 8 standards
- Use Black for code formatting
- Write docstrings for all functions, classes, and methods
- Include type hints according to PEP 484
Pull Request Process
- Ensure all tests pass and code is properly formatted
- Update documentation if necessary
- Link any related issues in your PR description
- Wait for review from maintainers
- Address any requested changes
- Once approved, your PR will be merged
Running the API Locally
To run the API server locally during development:
python run.py
The API will be available at http://localhost:8000 with interactive documentation at http://localhost:8000/docs.
Building the Package Locally
To build the package locally:
python -m build
Contact
If you have questions or need help, please:
- Open an issue on GitHub
- Contact the maintainers at hello@unsiloed-ai.com
Thank you for contributing to CSVAlchemy!
License
This project is licensed under the MIT License - see the LICENSE file for details.
About
Developed by Unsiloed AI
Metadata
Release files for CSVAlchemy-sdk 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| csvalchemy_sdk-0.1.3.tar.gz | 13.7 kB | Without provenance | Details for csvalchemy_sdk-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| csvalchemy_sdk-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for csvalchemy_sdk-0.1.3-py3-none-any.whl |
Total release size: 29.0 kB
Release files / csvalchemy_sdk-0.1.3.tar.gz
| Download URL | csvalchemy_sdk-0.1.3.tar.gz |
|---|---|
| Size | 13.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fbd9723681e8429695235118227d261967d7b1f8c1127424c552bc8de24dd563
|
|
BLAKE2b-256 checksum How to use checksums |
b9d737230c141b6a628bfc6a94ffada13ceb159bc153ea9f1143af22d30333b4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.9.6
|
Release files / csvalchemy_sdk-0.1.3-py3-none-any.whl
| Download URL | csvalchemy_sdk-0.1.3-py3-none-any.whl |
|---|---|
| Size | 15.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8061be98c9639bdfe4e2567a407bb43cf3494d080465238b036d4e923f48805e
|
|
BLAKE2b-256 checksum How to use checksums |
631316965926b6f92c61c41396062ddbdd215dcce48ca816d8baca2b0536fac3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.9.6
|
Security for CSVAlchemy-sdk 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.