Add Colbert MLX

[ToluClassics]

Could probably do with some redesign but here's a first pass at integrating MLX into Pyserini with ColBERT.

The tests and test outputs are similar to the same tests for the PyTorch hugging face implementation

[ToluClassics]

Side Note: We have some duplicated code e.g.

pyserini/pyserini/encode/_tct_colbert.py

Line 72 in 184a212

class TctColBertQueryEncoder(QueryEncoder):

and

pyserini/pyserini/search/faiss/_searcher.py

Line 147 in 184a212

class TctColBertQueryEncoder(QueryEncoder):

Is there a particular reason we are keeping both?

[lintool]

@jacklin64 @justram can either of you take a look at this?

[ToluClassics]

Bump on this @jacklin64 @justram .

Evaluating with this

python -m pyserini.search.faiss  \
    --index msmarco-v1-passage.tct_colbert.hnsw \
    --topics msmarco-passage-dev-subset \
    --encoder castorini/tct_colbert-msmarco \ 
    --encoder-class mlx_tct_colbert \
    --output runs/run.msmarco-passage.tct_colbert.hnsw.tsv \
    --output-format msmarco \
    --use_mlx 

Results:
#####################
MRR @10: 0.3344904943830437
QueriesRanked: 6980