Large document fix

[jamescalam]

Large documents chunking memory error

@ashraq1455 encountered an error where if a document were sufficiently large enough the worker would shutdown. The suspected cause was due to our semantic_chunkers.StatisticalChunker encoding sentence embeddings and storing all of them in-memory at the same time for the chunking methodology to run.

The proposed solution here would be to add a “rolling window” of focus that embeds a maximum number of sentences at any one time. This fix should be applied to both ConsecutiveChunker and StatisticalChunker in the semantic_chunkers library.