from sentence_transformers import SentenceTransformer

model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
sentence = (
    "Sentence Transformers truncates input tokens when a document is longer "
    "than the configured sequence length. "
)
long_text = sentence * 20

print(f"original max_seq_length={model.max_seq_length}")
model.max_seq_length = 128
features = model.preprocess([long_text])
print(f"updated max_seq_length={model.max_seq_length}")
print(f"tokenized sequence length={features['input_ids'].shape[1]}")
embedding = model.encode([long_text], show_progress_bar=False)
print(f"embedding shape={embedding.shape}")