# Text Embeddings Skill

Generate text embeddings using Ollama's local embedding models and store them in SQLite for semantic search and similarity calculations.

## Quick Start

```bash
# 1. Start Ollama server
nohup ollama serve > /dev/shm/ollama.log 2>&1 &

# 2. Pull an embedding model
ollama pull embeddinggemma

# 3. Embed your texts
python3 scripts/batch_embed.py --input /path/to/articles --output articles.db --model embeddinggemma

# 4. Search semantically
python3 scripts/search_similar.py --query "programming" --db articles.db
```

## Scripts

- `embed_text.py` — Generate embeddings for arbitrary text
- `search_similar.py` — Find similar texts by semantic search
- `batch_embed.py` — Batch process files or directories

See [SKILL.md](SKILL.md) for full documentation.