A8acc005 A48e 4a04 Bb6a 1ab7e9feac51

Source document

Here is the code again for your reference: ```python import numpy as np from sentence_transformers import SentenceTransformer from concurrent.futures import ThreadPoolExecutor, as_completed # Load the model once model = SentenceTransformer('paraphrase-MiniLM-L6-v2') def vectorize_document(doc): return model.encode(doc) def vectorize_pipeline(docs, max_workers=None): vectors = [] with ThreadPoolExecutor(max_workers=max_workers) as executor: futures = {executor.submit(vectorize_document, doc): doc for doc in docs} for future in as_completed(futures): try: vectors.append(future.result()) except Exception as e: print(f"Error processing document: {e}") return vectors def vectorize_in_batches(docs, batch_size=100): vectors = [] for i in range(0, len(docs), batch_size): batch_docs = docs[i:i+batch_size] batch_vectors = model.encode(batch_docs) vectors.extend(batch_vectors) return vectors # Example usage docs = ["Actual document text 1", "Actual document text 2", ...] # Replace with actual documents