File size: 1,846 Bytes
23a5cce | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | """
Base Embedding Provider - Abstract Interface for Semantic Grounding
"""
from abc import ABC, abstractmethod
from typing import List, Dict, Any, Optional
import time
class EmbeddingProvider(ABC):
"""Abstract base class for embedding providers."""
def __init__(self, config: Optional[Dict[str, Any]] = None):
self.config = config or {}
self.provider_id = self.__class__.__name__
self.created_at = time.time()
@abstractmethod
def embed_text(self, text: str) -> List[float]:
"""Generate embedding vector for a single text."""
pass
@abstractmethod
def embed_batch(self, texts: List[str]) -> List[List[float]]:
"""Generate embedding vectors for multiple texts."""
pass
@abstractmethod
def get_dimension(self) -> int:
"""Get the dimension of embedding vectors."""
pass
def calculate_similarity(self, embedding1: List[float], embedding2: List[float]) -> float:
"""Calculate cosine similarity between two embeddings."""
import math
# Dot product
dot_product = sum(a * b for a, b in zip(embedding1, embedding2))
# Magnitudes
magnitude1 = math.sqrt(sum(a * a for a in embedding1))
magnitude2 = math.sqrt(sum(b * b for b in embedding2))
# Avoid division by zero
if magnitude1 == 0 or magnitude2 == 0:
return 0.0
return dot_product / (magnitude1 * magnitude2)
def get_provider_info(self) -> Dict[str, Any]:
"""Get provider metadata."""
return {
"provider_id": self.provider_id,
"dimension": self.get_dimension(),
"created_at": self.created_at,
"config_keys": list(self.config.keys()),
} |