The representation vector of the 10th text chunk has 358 dimensions

Short Course Q&A Advanced Retrieval for AI with Chroma
1

In the second video, minute 7, Anton Troynikov says that the representation vector of the 10th text chunk has dimensions of 358. But when I run
len(embedding_function([token_split_texts[10]][0]))
I get 946. Is my understanding of the number of dimensions of a vectorial representation of a text chunk wrong? Shouldn’t it just be the length?

2

I think there is a mistake in the code you have written.
Try this:
print(len(embedding_function([token_split_texts[10]])[0]))

3

Thank you. I modified my code to this:

arr = np.array(embedding_function(token_split_texts[10]))
arr.shape

and got (946, 384).
I still don’t understand how to interpret this. There are 946 vectors of dimension 384? It still doesn’t make sense that the vector should have a dimension of 358.