embedding-strategies

What this skill does

# 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

### Template 1: Voyage AI Embeddings (Recommended for Claude)

```python
from langchain_voyageai import VoyageAIEmbeddings
from typing import List
import os

# Initialize Voyage AI embeddings (recommended by Anthropic for Claude)
embeddings = VoyageAIEmbeddings(
    model="voyage-3-large",
    voyage_api_key=os.environ.get("VOYAGE_API_KEY")
)

def get_embeddings(texts: List[str]) -> List[List[float]]:
    """Get embeddings from Voyage AI."""
    return embeddings.embed_documents(texts)

def get_query_embedding(query: str) -> List[float]:
    """Get single query embedding."""
    return embeddings.embed_query(query)

# Specialized models for domains
code_embeddings = VoyageAIEmbeddings(model="voyage-code-3")
finance_embeddings = VoyageAIEmbeddings(model="voyage-finance-2")
legal_embeddings = VoyageAIEmbeddings(model="voyage-law-2")
```

### Template 2: OpenAI Embeddings

```python
from openai import OpenAI
from typing import List
import numpy as np

client = OpenAI()

def get_embeddings(
    texts: List[str],
    model: str = "text-embedding-3-small",
    dimensions: int = None
) -> List[List[float]]:
    """Get embeddings from OpenAI with optional dimension reduction."""
    # Handle batching for large lists
    batch_size = 100
    all_embeddings = []

    for i in range(0, len(texts), batch_size):
        batch = texts[i:i + batch_size]

        kwargs = {"input": batch, "model": model}
        if dimensions:
            # Matryoshka dimensionality reduction
            kwargs["dimensions"] = dimensions

        response = client.embeddings.create(**kwargs)
        embeddings = [item.embedding for item in response.data]
        all_embeddings.extend(embeddings)

    return all_embeddings


def get_embedding(text: str, **kwargs) -> List[float]:
    """Get single embedding."""
    return get_embeddings([text], **kwargs)[0]


# Dimension reduction with Matryoshka embeddings
def get_reduced_embedding(text: str, dimensions: int = 512) -> List[float]:
    """Get embedding with reduced dimensions (Matryoshka)."""
    return get_embedding(
        text,
        model="text-embedding-3-small",
        dimensions=dimensions
    )
```

### Template 3: Local Embeddings with Sentence Transformers

```python
from sentence_transformers import SentenceTransformer
from typing import List, Optional
import numpy as np

class LocalEmbedder:
    """Local embedding with sentence-transformers."""

    def __init__(
        self,
        model_name: str = "BAAI/bge-large-en-v1.5",
        device: str = "cuda"
    ):
        self.model = SentenceTransformer(model_name, device=device)
        self.model_name = model_name

    def embed(
        self,
        texts: List[str],
        normalize: bool = True,
        show_progress: bool = False
    ) -> np.ndarray:
        """Embed texts with optional normalization."""
        embeddings = self.model.encode(
            texts,
            normalize_embeddings=normalize,
            show_progress_bar=show_progress,
            convert_to_numpy=True
        )
        return embeddings

    def embed_query(self, query: str) -> np.ndarray:
        """Embed a query with appropriate prefix for retrieval models."""
        # BGE and similar models benefit from query prefix
        if "bge" in self.model_name.lower():
            query = f"Represent this sentence for searching relevant passages: {query}"
        return self.embed([query])[0]

    def embed_documents(self, documents: List[str]) -> np.ndarray:
        """Embed documents for indexing."""
        return self.embed(documents)


# E5 model with instructions
class E5Embedder:
    def __init__(self, model_name: str = "intfloat/multilingual-e5-large"):
        self.model = SentenceTransformer(model_name)

    def embed_query(self, query: str) -> np.ndarray:
        """E5 requires 'query:' prefix for queries."""
        return self.model.encode(f"query: {query}")

    def embed_document(self, document: str) -> np.ndarray:
        """E5 requires 'passage:' prefix for documents."""
        return self.model.encode(f"passage: {document}")
```

### Template 4: Chunking Strategies

```python
from typing import List, Tuple
import re

def chunk_by_tokens(
    text: str,
    chunk_size: int = 512,
    chunk_overlap: int = 50,
    tokenizer=None
) -> List[str]:
    """Chunk text by token count."""
    import tiktoken
    tokenizer = tokenizer or tiktoken.get_encoding("cl100k_base")

    tokens = tokenizer.encode(text)
    chunks = []

    start = 0
    while start < len(tokens):
        end = start + chunk_size
        chunk_tokens = tokens[start:end]
        chunk_text = tokenizer.decode(chunk_tokens)
        chunks.append(chunk_text)
        start = end - chunk_overlap

    return chunks


def chunk_by_sentences(
    text: str,
    max_chunk_size: int = 1000,
    min_chunk_size: int = 100
) -> List[str]:
    """Chunk text by sentences, respecting size limits."""
    import nltk
    sentences = nltk.sent_tokenize(text)

    chunks = []
    current_chunk = []
    current_size = 0

    for sentence in sentences:
        sentence_size = len(sentence)

        if current_size + sentence_size > max_chunk_size and current_chunk:
            chunks.append(" ".join(current_chunk))
            current_chunk = []
            current_size = 0

        current_chunk.append(sentence)
        current_size += sentence_size

    if current_chunk:
        chunks.append(" ".join(current_chunk))

    return chunks


def chunk_by_semantic_sections(
    text: str,
    headers_pattern: str = r'^#{1,3}\s+.+$'
) -> List[Tuple[str, str]]:
    """Chunk markdown by headers, preserving hierarchy."""
    lines = text.split('\n')
    chunks = []
    current_header = ""
    current_content = []

    for line in lines:
        if re.match(headers_pattern, line, re.MULTILINE):
            if current_content:
                chunks.append((current_header, '\n'.join(current_content)))
            current_header = line
            current_content = []
        else:
            current_content.append(line)

    if current_content:
        chunks.append((current_header, '\n'.join(current_content)))

    return chunks


def recursive_character_splitter(
    text: str,
    chunk_size: int = 1000,
    chunk_overlap: int