Details

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")

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
    )

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}")

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"

import re
from typing import List, Optional
from dataclasses import dataclass

@dataclass
class EmbeddedDocument:
    id: str
    document_id: str
    chunk_index: int
    text: str
    embedding: List[float]
    metadata: dict

class DomainEmbeddingPipeline:
    """Pipeline for domain-specific embeddings."""

    def

import numpy as np
from typing import List, Dict

def evaluate_retrieval_quality(
    queries: List[str],
    relevant_docs: List[List[str]],  # List of relevant doc IDs per query
    retrieved_docs: List[List[str]],  # List of retrieved doc IDs per query
    k: int = 10
) -> Dict[str, float]:
    """Evaluate embedding quality for retrieval."""

    def precision_at_k(relevant: