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
..
documents	Restructure examples directory and improve document storage (#189)	2026-03-28 04:28:59 +08:00
tutorials	Simplify root directory	2026-03-27 03:30:13 +08:00
agentic_vectorless_rag_demo.py	fix: restore intended demo paper, retrieve_model exposure, and md summary threshold	2026-07-19 06:18:35 +08:00
cloud_demo.py	fix: restore intended demo paper, retrieve_model exposure, and md summary threshold	2026-07-19 06:18:35 +08:00
demo_legacy_sdk.py	chore: move legacy SDK e2e script into examples/	2026-05-15 18:08:29 +08:00
demo_query_modes.py	fix: enforce collection membership on cloud query doc_ids	2026-07-16 14:40:19 +08:00
local_demo.py	fix: restore intended demo paper, retrieve_model exposure, and md summary threshold	2026-07-19 06:18:35 +08:00