---
version: 4.1.0-fractal
name: embedding-strategies
description: Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
---

# Embedding Strategies

Guide to selecting and optimizing embedding models for vector search applications.

## Do not use this skill when

- The task is unrelated to embedding strategies
- You need a different domain or tool outside this scope

## Instructions

- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.
- If detailed examples are required, open `resources/implementation-playbook.md`.

## Use this skill when

- Choosing embedding models for RAG
- Optimizing chunking strategies
- Fine-tuning embeddings for domains
- Comparing embedding model performance
- Reducing embedding dimensions
- Handling multilingual content

## Core Concepts

## 🧠 Knowledge Modules (Fractal Skills)

### 1. [1. Embedding Model Comparison](./sub-skills/1-embedding-model-comparison.md)
### 2. [2. Embedding Pipeline](./sub-skills/2-embedding-pipeline.md)
### 3. [Template 1: OpenAI Embeddings](./sub-skills/template-1-openai-embeddings.md)
### 4. [Template 2: Local Embeddings with Sentence Transformers](./sub-skills/template-2-local-embeddings-with-sentence-transformers.md)
### 5. [Template 3: Chunking Strategies](./sub-skills/template-3-chunking-strategies.md)
### 6. [Template 4: Domain-Specific Embedding Pipeline](./sub-skills/template-4-domain-specific-embedding-pipeline.md)
### 7. [Template 5: Embedding Quality Evaluation](./sub-skills/template-5-embedding-quality-evaluation.md)
### 8. [Do's](./sub-skills/dos.md)
### 9. [Don'ts](./sub-skills/donts.md)