Metadata-Version: 2.4
Name: tablassert
Version: 7.0.0
Summary: Add your description here
License-File: LICENSE
Requires-Python: >=3.13
Requires-Dist: diskcache>=5.6.3
Requires-Dist: duckdb>=1.5.0
Requires-Dist: fastexcel>=0.19.0
Requires-Dist: loguru>=0.7.3
Requires-Dist: mkdocs>=1.6.1
Requires-Dist: onnxruntime>=1.24.3
Requires-Dist: optimum-onnx>=0.1.0
Requires-Dist: orjson>=3.11.7
Requires-Dist: playwright>=1.58.0
Requires-Dist: polars>=1.39.0
Requires-Dist: pyarrow>=23.0.1
Requires-Dist: pydantic>=2.12.5
Requires-Dist: pyexcel>=0.7.4
Requires-Dist: pyyaml>=6.0.3
Requires-Dist: rapidfuzz>=3.14.3
Requires-Dist: scikit-learn>=1.8.0
Requires-Dist: sentence-transformers>=5.3.0
Requires-Dist: sqlite-utils>=3.39
Requires-Dist: typer>=0.24.1
Requires-Dist: xxhash>=3.6.0
Description-Content-Type: text/markdown

# Tablassert

### By Skye Lane Goetz, Gwênlyn Glusman, and Jared C. Roach

Tablassert is a highly performant declarative knowledge graph backend designed to extract knowledge assertions from tabular data while exporting NCATS Translator-compliant Knowledge Graph Exchange (KGX) NDJSON.

## Documentation

**[Full Documentation](https://skyeav.github.io/Tablassert/)**

Complete guides covering installation, configuration, tutorials, and API reference.

## Quick Start

```bash
# Clone repository
git clone https://github.com/SkyeAv/Tablassert.git
cd Tablassert

# Install with UV (requires Python 3.13+)
uv sync

# Run CLI
uv run tablassert --help
```

Or install the CLI directly from PyPI:

```bash
# Option A: UV tool install
uv tool install tablassert

# Option B: pip install
pip install tablassert

tablassert --help
```

## Usage (With UV)

### Prerequisites

- Python 3.13 or higher
- UV package manager

### Method 1: Development Installation (Recommended)

Best for exploring Tablassert or active development.

```bash
# Clone and install dependencies
git clone https://github.com/SkyeAv/Tablassert.git
cd Tablassert
uv sync

# Run CLI through UV
uv run tablassert build-knowledge-graph /path/to/graph-config.yaml
```

### Method 2: Install from PyPI

Recommended for most users.

```bash
# Option A: UV tool install
uv tool install tablassert

# Option B: pip install
pip install tablassert

tablassert build-knowledge-graph /path/to/graph-config.yaml
```

### Method 3: Install from GitHub main

Use this when you want the latest main-branch build before a tagged release.

```bash
uv tool install git+https://github.com/SkyeAv/Tablassert.git@main
tablassert build-knowledge-graph /path/to/graph-config.yaml
```

### Method 4: Local source install

For contributors testing local changes.

```bash
# Clone repository
git clone https://github.com/SkyeAv/Tablassert.git
cd Tablassert

# Install CLI tool from local source
uv tool install .

# CLI is now available
tablassert build-knowledge-graph /path/to/graph-config.yaml
```

## Key Features

- **Declarative Configuration:** YAML-based, no code required
- **Entity Resolution:** Maps text to biological entities (genes, diseases, chemicals)
- **Quality Control:** Three-stage validation (exact → fuzzy → BERT embeddings)
- **KGX Compliance:** NCATS Translator-compatible NDJSON output
- **Performance:** Parallel processing with disk caching

## Contributors

[Skye Lane Goetz](mailto:sgoetz@isbscience.org) - Institute for Systems Biology, CalPoly SLO

[Gwênlyn Glusman](mailto:gglusman@isbscience.org) - Institute for Systems Biology

Jared C. Roach - Institute for Systems Biology
