Spaces:
Sleeping
Sleeping
File size: 3,272 Bytes
14f13a5 |
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 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
"""
Embedding generation for RAG system.
Handles text-to-vector conversion using sentence-transformers.
"""
from typing import List, Union
import logging
from sentence_transformers import SentenceTransformer
import numpy as np
logger = logging.getLogger(__name__)
class EmbeddingGenerator:
"""
Generates embeddings for text using sentence-transformers.
Features:
- Batch processing for efficiency
- Caching of model
- Normalized embeddings for cosine similarity
"""
def __init__(self, model_name: str = "sentence-transformers/all-MiniLM-L6-v2"):
"""
Initialize embedding generator.
Args:
model_name: HuggingFace model identifier
"""
self.model_name = model_name
logger.info(f"Loading embedding model: {model_name}")
try:
self.model = SentenceTransformer(model_name)
self.embedding_dim = self.model.get_sentence_embedding_dimension()
logger.info(f"Model loaded. Embedding dimension: {self.embedding_dim}")
except Exception as e:
logger.error(f"Failed to load embedding model: {e}")
raise
def embed_text(self, text: Union[str, List[str]]) -> np.ndarray:
"""
Generate embeddings for text.
Args:
text: Single text string or list of strings
Returns:
Numpy array of embeddings (shape: [n_texts, embedding_dim])
"""
if isinstance(text, str):
text = [text]
if not text:
raise ValueError("No text provided for embedding")
try:
# Generate embeddings
embeddings = self.model.encode(
text,
normalize_embeddings=True, # For cosine similarity
show_progress_bar=len(text) > 10,
batch_size=32
)
logger.debug(f"Generated embeddings for {len(text)} texts")
return embeddings
except Exception as e:
logger.error(f"Embedding generation failed: {e}")
raise
def embed_query(self, query: str) -> np.ndarray:
"""
Generate embedding for a single query.
Args:
query: Query text
Returns:
1D numpy array of embedding
"""
embedding = self.embed_text(query)
return embedding[0] # Return single embedding
def embed_documents(self, documents: List[str]) -> np.ndarray:
"""
Generate embeddings for a batch of documents.
Args:
documents: List of document texts
Returns:
2D numpy array of embeddings
"""
return self.embed_text(documents)
def create_embedding_generator(model_name: str = None) -> EmbeddingGenerator:
"""
Factory function to create embedding generator.
Args:
model_name: Optional model name override
Returns:
EmbeddingGenerator instance
"""
from src.config import settings
model = model_name or settings.embedding_model
return EmbeddingGenerator(model_name=model)
|