PageIndex/pageindex
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
..
backend fix: restore 0.2.x config resolution and legacy submodule attribute access 2026-07-19 03:42:00 +08:00
index fix: restore intended demo paper, retrieve_model exposure, and md summary threshold 2026-07-19 06:18:35 +08:00
parser fix: empty-list scope, get_tree bool casing, md fence tracking; dedupe base URL 2026-07-10 11:17:20 +08:00
storage fix: resolve concurrency and DoS pitfalls from PR #272 review 2026-07-10 14:49:55 +08:00
__init__.py fix: restore 0.2.x config resolution and legacy submodule attribute access 2026-07-19 03:42:00 +08:00
agent.py fix: enforce collection membership on cloud query doc_ids 2026-07-16 14:40:19 +08:00
client.py fix: restore intended demo paper, retrieve_model exposure, and md summary threshold 2026-07-19 06:18:35 +08:00
cloud_api.py fix: restore 0.2.x config resolution and legacy submodule attribute access 2026-07-19 03:42:00 +08:00
collection.py fix: enforce collection membership on cloud doc-scoped operations 2026-07-16 06:20:24 +08:00
config.py fix: default SDK retrieve_model to gpt-5.4 instead of following model 2026-07-16 16:09:07 +08:00
config.yaml fix: default SDK retrieve_model to gpt-5.4 instead of following model 2026-07-16 16:09:07 +08:00
errors.py fix: address max-effort review findings 2026-07-13 18:49:09 +08:00
events.py fix: enforce collection membership on cloud query doc_ids 2026-07-16 14:40:19 +08:00
page_index.py Merge commit from fork 2026-07-17 13:57:21 +08:00
page_index_md.py fix(markdown): skip empty bold headings 2026-07-16 19:36:52 +08:00
retrieve.py fix: CMYK image drop, empty-doc crash, page_index shadowing, sqlite hardening, flaky tests 2026-07-09 11:58:59 +08:00
tokens.py refactor(sdk): typed returns, protocol contract, parser layering 2026-07-07 12:15:34 +08:00
types.py fix: CMYK image drop, empty-doc crash, page_index shadowing, sqlite hardening, flaky tests 2026-07-09 11:58:59 +08:00
utils.py fix: address xhigh review findings for PR #272 2026-07-16 01:31:57 +08:00