# Embeddings

> Explains dense vector embeddings, their key concepts, common use cases, and best practices for semantic search and RAG applications.

- Skill: `neuralblitz/embeddings` (Agent Skill)
- Install (CLI): `npx skillmds@latest add neuralblitz/embeddings`
- Raw SKILL.md: https://api.skillmd.com/api/skills/neuralblitz/embeddings/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML, RAG & Embeddings
- Tags: Chunking, Cosine Similarity, Embeddings, Image Embeddings, Semantic Search, Text Embeddings, Vector Representations
- Author: NeuralBlitz (https://skillmd.com/u/neuralblitz)
- Updated: 2026-08-22
- Page: https://skillmd.com/skills/neuralblitz/embeddings

---

# Embeddings

Embeddings are dense vector representations of text, images, or other data that capture semantic meaning. They're the foundation of semantic search and RAG applications.

## Key Concepts

- Text embeddings (text-embedding-ada-002, e5, bge)
- Image embeddings (CLIP, ResNet)
- Dimensionality reduction
- Similarity computation
- Batch processing

## Common Use Cases

- Semantic search
- Text classification
- Clustering
- Duplicate detection
- RAG systems

## Best Practices

- Choose model based on use case
- Normalize vectors for cosine similarity
- Handle long texts with chunking
- Cache embeddings when possible
- Monitor embedding drift

## Resources

- OpenAI Embeddings, Hugging Face, Cohere
- Related Skills: vector-databases, nlp, machine-learning