---
name: estrategias-embeddings
description: Guía técnica para seleccionar y optimizar modelos de embeddings en aplicaciones de búsqueda semántica y RAG. Cubre comparativa de modelos, estrategias de chunking, preprocesamiento y mejores prácticas para dominios específicos.
license: MIT
metadata:
  id: 465fcc33
  slug: estrategias-embeddings
  titulo: "Estrategias de Embeddings para RAG y Búsqueda Semántica"
  servicio: IA-Ingenieria-MLOps
  categoria_recurso: IA-Generativa
  tipo: referencia
  nivel: avanzado
  idioma: es
  idioma_original: en
  acceso: gratis
  precio_eur: 0
  plataformas: [Claude Code, Codex CLI, OpenCode, Cursor, Gemini CLI]
  dependencias: [voyage-ai, openai-embeddings, sentence-transformers]
  licencia: { spdx: MIT, redistribuible: true, uso_comercial: true }
  fuente:
    repo: wshobson/agents
    url: https://github.com/wshobson/agents/tree/main/plugins/llm-application-dev/skills/embedding-strategies
    commit: cc37bfd
    autor: wshobson
    nombre_original: embedding-strategies
    duplicados_en: []
  seguridad: { veredicto: seguro, riesgo: bajo, escaneado: "2026-06-14", motor: "grep-estatico+auditor-llm" }
  ficha:
    que_hace: "Guia al ingeniero en la seleccion del modelo de embedding optimo y la configuracion del pipeline de vectorizacion para sistemas RAG."
    como_lo_hace: "Proporciona una tabla comparativa de modelos (Voyage, OpenAI, BGE, MiniLM), un diagrama del pipeline y un conjunto de reglas do/don't para chunking, normalizacion y cacheo."
  content_hash: "465fcc335535c490838bf392dac920ed2c57eb98a1e8a229e64c92a4f65f7b80"
  version: 1.0.0
---

# Embedding Strategies

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

## When to Use This Skill

- 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

### 1. Embedding Model Comparison (2026)

| Model                      | Dimensions | Max Tokens | Best For                            |
| -------------------------- | ---------- | ---------- | ----------------------------------- |
| **voyage-3-large**         | 1024       | 32000      | Claude apps (Anthropic recommended) |
| **voyage-3**               | 1024       | 32000      | Claude apps, cost-effective         |
| **voyage-code-3**          | 1024       | 32000      | Code search                         |
| **voyage-finance-2**       | 1024       | 32000      | Financial documents                 |
| **voyage-law-2**           | 1024       | 32000      | Legal documents                     |
| **text-embedding-3-large** | 3072       | 8191       | OpenAI apps, high accuracy          |
| **text-embedding-3-small** | 1536       | 8191       | OpenAI apps, cost-effective         |
| **bge-large-en-v1.5**      | 1024       | 512        | Open source, local deployment       |
| **all-MiniLM-L6-v2**       | 384        | 256        | Fast, lightweight                   |
| **multilingual-e5-large**  | 1024       | 512        | Multi-language                      |

### 2. Embedding Pipeline

```
Document → Chunking → Preprocessing → Embedding Model → Vector
                ↓
        [Overlap, Size]  [Clean, Normalize]  [API/Local]
```

## Templates and detailed worked examples

Full template library and detailed worked examples live in `references/details.md`. Read that file when you need the concrete templates.

## Best Practices

### Do's

- **Match model to use case**: Code vs prose vs multilingual
- **Chunk thoughtfully**: Preserve semantic boundaries
- **Normalize embeddings**: For cosine similarity search
- **Batch requests**: More efficient than one-by-one
- **Cache embeddings**: Avoid recomputing for static content
- **Use Voyage AI for Claude apps**: Recommended by Anthropic

### Don'ts

- **Don't ignore token limits**: Truncation loses information
- **Don't mix embedding models**: Incompatible vector spaces
- **Don't skip preprocessing**: Garbage in, garbage out
- **Don't over-chunk**: Lose important context
- **Don't forget metadata**: Essential for filtering and debugging