Jack 4b4a6e72f0 fix(chunker): unify TokenChunker merge and strip coord tags in Python JSON path (#18002) ...

Unifies the Go TokenChunker merge path on a single `mergeUnits` core and
fixes coordinate-tag drift in the Python JSON merge at `overlap > 0`.
Rebased on top of #17979 (delimiter_mode convergence).

2026-08-07 21:55:07 +08:00

..

__init__.py

fix(chunker): unify TokenChunker merge and strip coord tags in Python JSON path (#18002)

2026-08-07 21:55:07 +08:00

delim.py

refactor(nlp): collapse 6 delimiter-parser implementations into one canonical helper (#17383) (#17387)

2026-08-02 17:07:14 +08:00

query.py

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00

rag_tokenizer.py

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00

search.py

Refactor: Make wiki and web searchable. (#17789)

2026-08-04 18:02:13 +08:00

surname.py

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00

synonym.py

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00

term_weight.py

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00