Ray a0fb863957 fix: restore intended demo paper, retrieve_model exposure, and md summary threshold ... - demos: use the post-cutoff attention-residuals paper (2603.15031) again so answers provably come from retrieval, and run the QA agent on retrieve_model - client: re-expose model / retrieve_model as public attributes (0.2.x surface) - pipeline: markdown summaries go back through generate_summaries_for_structure_md with the 200-token threshold (small nodes skip the LLM call) - README: restore (yes/no, default: X) flag docs with correct defaults; note that retrieve_model drives agent QA		2026-07-19 06:18:35 +08:00
..
__init__.py	feat: add PageIndex SDK with local/cloud dual-mode support (#207)	2026-04-08 20:21:58 +08:00
page_index.py	fix: restore 0.2.x config resolution and legacy submodule attribute access	2026-07-19 03:42:00 +08:00
page_index_md.py	Merge upstream/main into dev; port hardening into index/	2026-07-17 18:11:14 +08:00
pipeline.py	fix: restore intended demo paper, retrieve_model exposure, and md summary threshold	2026-07-19 06:18:35 +08:00
utils.py	fix: restore 0.2.x config resolution and legacy submodule attribute access	2026-07-19 03:42:00 +08:00