def get_embedding_chunked()

in embeddings/retrieve_embeddings.py [0:0]

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

def get_embedding_chunked(textinput, batch_size): 
    for i in range(0, len(textinput), batch_size):
        request = [x["content"] for x in textinput[i : i + batch_size]]
        response = embedder.create(request) # Vertex Textmodel Embedder 

        # Store the retrieved vector embeddings for each chunk back.
        for x, e in zip(textinput[i : i + batch_size], response):
            x["embedding"] = e

    # Store the generated embeddings in a pandas dataframe.
    out_df = pd.DataFrame(textinput)
    return out_df