Embedding Strategies

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

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."""
    # 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:
            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 OpenAI
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
    )

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)

    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 BGE-style prefix."""
        # BGE models benefit from query prefix
        if "bge" in self.model.get_sentence_embedding_dimension():
            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 inst