speed up chunking & add separator chunking

[rangehow]

Hey, so this PR's got two main changes:

1. We're now converting docs to tokens in bulk, which is giving us a sweet 3X speed boost when dealing with a ton of docs (we tested it with 30k) by chunking_by_token_size. It's not gonna make much difference for small-scale stuff, but 30k is still pretty much toy-level (both industry and research usually work with way more). So yeah, this is definitely a solid upgrade.

2. We've added support for separator-based splitting without needing any extra dependencies. This splitting method tries to keep the grammar structure intact, meaning you'll always get complete clauses or sentences (if without any overlap). We tweaked the logic from langchain, so it might not be exactly the same, but it does what it says on the tin.

[codecov]

Codecov Report

Attention: Patch coverage is 97.36842% with 1 line in your changes missing coverage. Please review.

Project coverage is 94.36%. Comparing base (ad74d13) to head (bcfe5bf).
Report is 3 commits behind head on main.

Files with missing lines	Patch %	Lines
nano_graphrag/_op.py	97.22%	1 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff           @@
##             main      #48   +/-   ##
=======================================
  Coverage   94.36%   94.36%           
=======================================
  Files          11       11           
  Lines        1189     1189           
=======================================
  Hits         1122     1122           
  Misses         67       67           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[rangehow]

NOW I GUESS ALL SHOULD BE WELL : )

[gusye1234]

Great works! Few typing errors I think