README.md

---
title: ATLES-ECHO Embedding Service
emoji: 🧠
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: true
license: apache-2.0
short_description: Semantic embeddings with ATLES Champion model
---

# 🧠 ATLES-ECHO Embedding Service

Generate high-quality semantic embeddings using the **ATLES Champion** embedding model.

## Features

- **🔤 Single Embedding**: Generate embedding for any text
- **⚖️ Compare Similarity**: Compare semantic similarity between two texts  
- **📦 Batch Embed**: Process multiple texts at once (up to 10)

## Model Details

| Property | Value |
|----------|-------|
| **Model** | [spartan8806/atles-champion-embedding](https://huggingface.co/spartan8806/atles-champion-embedding) |
| **Dimension** | 768 |
| **Base Model** | all-mpnet-base-v2 |
| **Parameters** | 110M |
| **Training** | H200 GPU (30 minutes) |

## Performance (MTEB STS-B)

- **Pearson**: 0.8445 (Top-10 worldwide)
- **Spearman**: 0.8374

## About ATLES

ATLES-ECHO is the semantic memory core of the ATLES ecosystem - your AI digital twin that learns from your digital life while keeping everything private and local.

**Ecosystem Components:**
- 🧠 **ECHO** - Semantic memory and embeddings
- 🦅 **Phoenix** - AI council for decision making
- 🔬 **SENTINEL** - Research and knowledge gathering
- 📚 **MENTOR** - Code understanding and assistance

## API Usage

This space provides a visual interface. For programmatic access, use the model directly:

```python
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("spartan8806/atles-champion-embedding")
embedding = model.encode("Your text here", normalize_embeddings=True)
```

## License

Apache 2.0 - Free for commercial and personal use.

---

Built with ❤️ by [spartan8806](https://huggingface.co/spartan8806)