""" Text embedding encoder using network service. Generates embeddings via HTTP API service running on localhost:5001. """ import sys import requests import time import threading import numpy as np import pickle import redis from datetime import timedelta from typing import List, Union, Dict, Any, Optional import logging logger = logging.getLogger(__name__) # Try to import REDIS_CONFIG, but allow import to fail try: from config.env_config import REDIS_CONFIG except ImportError: REDIS_CONFIG = {} class BgeEncoder: """ Singleton text encoder using network service. Thread-safe singleton pattern ensures only one instance exists. """ _instance = None _lock = threading.Lock() def __new__(cls, service_url='http://localhost:5001'): with cls._lock: if cls._instance is None: cls._instance = super(BgeEncoder, cls).__new__(cls) logger.info(f"Creating BgeEncoder instance with service URL: {service_url}") cls._instance.service_url = service_url cls._instance.endpoint = f"{service_url}/embedding/generate_embeddings" # Initialize Redis cache try: cls._instance.redis_client = redis.Redis( host=REDIS_CONFIG.get('host', 'localhost'), port=REDIS_CONFIG.get('port', 6479), password=REDIS_CONFIG.get('password'), decode_responses=False, # Keep binary data as is socket_timeout=REDIS_CONFIG.get('socket_timeout', 1), socket_connect_timeout=REDIS_CONFIG.get('socket_connect_timeout', 1), retry_on_timeout=REDIS_CONFIG.get('retry_on_timeout', False), health_check_interval=10 # 避免复用坏连接 ) # Test connection cls._instance.redis_client.ping() cls._instance.expire_time = timedelta(days=REDIS_CONFIG.get('cache_expire_days', 180)) logger.info("Redis cache initialized for embeddings") except Exception as e: logger.warning(f"Failed to initialize Redis cache for embeddings: {e}, continuing without cache") cls._instance.redis_client = None return cls._instance def _call_service(self, request_data: List[Dict[str, Any]]) -> List[Dict[str, Any]]: """ Call the embedding service API. Args: request_data: List of dictionaries with id and text fields Returns: List of dictionaries with id and embedding fields """ try: response = requests.post( self.endpoint, json=request_data, timeout=60 ) response.raise_for_status() return response.json() except requests.exceptions.RequestException as e: logger.error(f"BgeEncoder service request failed: {e}", exc_info=True) raise def encode( self, sentences: Union[str, List[str]], normalize_embeddings: bool = True, device: str = 'cpu', batch_size: int = 32 ) -> np.ndarray: """ Encode text into embeddings via network service with Redis caching. Args: sentences: Single string or list of strings to encode normalize_embeddings: Whether to normalize embeddings (ignored for service) device: Device parameter ignored for service compatibility batch_size: Batch size for processing (used for service requests) Returns: numpy array of shape (n, 1024) containing embeddings """ # Convert single string to list if isinstance(sentences, str): sentences = [sentences] # Check cache first cached_embeddings = [] uncached_indices = [] uncached_texts = [] for i, text in enumerate(sentences): cached = self._get_cached_embedding(text, 'en') # Use 'en' as default language for title embedding if cached is not None: cached_embeddings.append((i, cached)) else: uncached_indices.append(i) uncached_texts.append(text) # Prepare request data for uncached texts request_data = [] for i, text in enumerate(uncached_texts): request_item = { "id": str(uncached_indices[i]), "name_zh": text } # Add English and Russian fields as empty for now # Could be enhanced with language detection in the future request_item["name_en"] = None request_item["name_ru"] = None request_data.append(request_item) # Process response embeddings = [None] * len(sentences) # Fill in cached embeddings for idx, cached_emb in cached_embeddings: embeddings[idx] = cached_emb # If there are uncached texts, call service if uncached_texts: try: # Call service response_data = self._call_service(request_data) # Process response for i, text in enumerate(uncached_texts): original_idx = uncached_indices[i] # Find corresponding response by ID response_item = None for item in response_data: if str(item.get("id")) == str(original_idx): response_item = item break if response_item: # Try Chinese embedding first, then English, then Russian embedding = None for lang in ["embedding_zh", "embedding_en", "embedding_ru"]: if lang in response_item and response_item[lang] is not None: embedding = response_item[lang] break if embedding is not None: embedding_array = np.array(embedding, dtype=np.float32) embeddings[original_idx] = embedding_array # Cache the embedding self._set_cached_embedding(text, 'en', embedding_array) else: logger.warning(f"No embedding found for text {original_idx}: {text[:50]}...") embeddings[original_idx] = np.zeros(1024, dtype=np.float32) else: logger.warning(f"No response found for text {original_idx}") embeddings[original_idx] = np.zeros(1024, dtype=np.float32) except Exception as e: logger.error(f"Failed to encode texts: {e}", exc_info=True) # Fill missing embeddings with zeros for idx in uncached_indices: if embeddings[idx] is None: embeddings[idx] = np.zeros(1024, dtype=np.float32) # Convert to numpy array return np.array(embeddings, dtype=np.float32) def encode_batch( self, texts: List[str], batch_size: int = 32, device: str = 'cpu' ) -> np.ndarray: """ Encode a batch of texts efficiently via network service. Args: texts: List of texts to encode batch_size: Batch size for processing device: Device parameter ignored for service compatibility Returns: numpy array of embeddings """ return self.encode(texts, batch_size=batch_size, device=device) def _get_cache_key(self, query: str, language: str) -> str: """Generate a cache key for the query""" return f"embedding:{language}:{query}" def _get_cached_embedding(self, query: str, language: str) -> Optional[np.ndarray]: """Get embedding from cache if exists (with sliding expiration)""" if not self.redis_client: return None try: cache_key = self._get_cache_key(query, language) cached_data = self.redis_client.get(cache_key) if cached_data: logger.debug(f"Cache hit for embedding: {query}") # Update expiration time on access (sliding expiration) self.redis_client.expire(cache_key, self.expire_time) return pickle.loads(cached_data) return None except Exception as e: logger.error(f"Error retrieving embedding from cache: {e}") return None def _set_cached_embedding(self, query: str, language: str, embedding: np.ndarray) -> bool: """Store embedding in cache""" if not self.redis_client: return False try: cache_key = self._get_cache_key(query, language) serialized_data = pickle.dumps(embedding) self.redis_client.setex( cache_key, self.expire_time, serialized_data ) logger.debug(f"Successfully cached embedding for query: {query}") return True except (redis.exceptions.BusyLoadingError, redis.exceptions.ConnectionError, redis.exceptions.TimeoutError, redis.exceptions.RedisError) as e: logger.warning(f"Redis error storing embedding in cache: {e}") return False except Exception as e: logger.error(f"Error storing embedding in cache: {e}") return False