def get_text_embedding()

in use-cases/rag-pipeline/embedding-models/multimodal-embedding/src/blip2_server.py [0:0]

• 8 lines of code
• 2 McCabe index (conditional complexity)

def get_text_embedding(caption):
    """Generates text embeddings for a given caption.

    Args:
        caption: The input caption as a string.

    Returns:
        A torch.Tensor containing the text embeddings.

    Raises:
        ValueError: If there is an error generating the text embedding.
    """

    try:
        text_input = txt_processors["eval"](caption)
        sample = {"text_input": [text_input]}
        features_text = model.extract_features(sample, mode="text")
        return features_text.text_embeds
    except Exception as e:
        raise ValueError(f"Error generating text embedding: {e}")