Metadata-Version: 2.4
Name: agba-engine
Version: 5.1.2
Summary: Multi-Modal, Diacritic-Preserving Cultural Heritage Retrieval Framework
Author-email: Aruna Olanrewaju Kabiru <only1mooseylion@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/AgbaVLMengine/Agba-Engine
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.0.0
Requires-Dist: huggingface-hub
Requires-Dist: pillow
Requires-Dist: numpy

# 🏛️ Agba Engine (`agba-engine`)

**Version:** 5.1.2  
**Author & Lead Architect:** Aruna Olanrewaju Kabiru  
**License:** `RAIL-Cultural-Heritage-v1.0` *(Prohibits unauthorized commodification & identity distortion)*

`agba-engine` is a multi-modal, diacritic-preserving retrieval framework designed for indexing global heritage assets, indigenous scripts, and tonal orthographies without semantic stripping.

---

## 📦 Installation

```bash
pip install agba-engine==5.1.2
```

---

## 🚀 Quickstart & Usage Examples

### Example 1: Diacritic-Preserving Text Indexing with Rich Metadata
Standard LLM tokenizers flatten tonal marks. Agba Engine maintains parallel canonical and ASCII representation vectors alongside rich cultural descriptions.

```python
from agba_engine.core.engine import AgbaSearchEngine

engine = AgbaSearchEngine()
query_text = "Fìlà Gọ̀bị́"
results = engine.search_by_text(query_text, top_k=3)

top_match = results[0]
print(f"ID: {top_match['id']}")
print(f"Class: {top_match['classification']}")
print(f"Description: {top_match['description']}")
print(f"Score: {top_match['score']:.4f}")
```

### Example 2: Cross-Modal Visual Retrieval
Perform similarity search across physical heritage artifacts using vision feature tensors.

```python
import torch
from agba_engine.core.engine import AgbaSearchEngine

engine = AgbaSearchEngine()
image_tensor = torch.randn(1, 512)
matches = engine.search_by_vision(image_tensor, top_k=3)

print(f"Top Match: {matches[0]['id']} ({matches[0]['classification']})")
```

---

## 🛠️ API Reference & Key Functions

| Method / Property | Return Type | Description |
| :--- | :--- | :--- |
| `AgbaSearchEngine()` | `Object` | Initializes core engine & fetches remote weights if missing locally. |
| `.search_by_text(query, top_k=5)` | `List[Dict]` | Executes text retrieval returning canonical tonal scripts, classifications, descriptions, and scores. |
| `.search_by_vision(tensor, top_k=5)` | `List[Dict]` | Queries visual vector space returning top matched cultural regalia metadata. |
| `.version` | `str` | Returns active engine build version (`5.1.2`). |
| `.ethical_license` | `str` | Returns active governance framework parameters. |

---

## 🌐 Enterprise & Quad-Vector Audio Alignment
The open-source core provides tri-vector functionality (Canonical Text, ASCII, and Vision).  
For high-density **Quad-Vector Audio Integration** (including *Gangan pitch-contour mapping* and spoken native vocalization models for archives and museums), visit our Hugging Face Space or contact the author.
