Evaluate similarity search performance with NLP-based splitting

[tomdyson]

e.g.

pip install spacy
python -m spacy download en_core_web_sm

and in Dockerfile:

RUN pip install spacy
RUN python -m spacy download en_core_web_sm

In microllama.py:

from langchain.text_splitter import SpacyTextSplitter

and

splitter = CharacterTextSplitter(... -> splitter = SpacyTextSplitter(...

Index creation takes roughly twice as long.