PageIndex/pageindex/backend
Ray 3ff04d501a fix: address max-effort review findings
- clamp LLM-derived page indices in _get_text_of_pages and
  get_text_of_pdf_pages_with_labels; dedupe get_text_of_pdf_pages
- guard _normalize_tree and folders/documents iterations against
  explicit nulls in cloud API responses
- coerce cloud OCR page numbers to int before filtering in
  get_page_content
- folder cache: raise on missing folder id instead of caching None;
  stop caching name-not-found so later lookups can succeed
- defang doc_id in agent doc-context prompt
- append api-key hint to 401 errors (request, legacy and streaming
  paths)
- remove stale legacy JSON workspace sample data unreadable by the
  SQLite storage
2026-07-13 18:49:09 +08:00
..
__init__.py feat: add PageIndex SDK with local/cloud dual-mode support (#207) 2026-04-08 20:21:58 +08:00
cloud.py fix: address max-effort review findings 2026-07-13 18:49:09 +08:00
local.py fix: empty-list scope, get_tree bool casing, md fence tracking; dedupe base URL 2026-07-10 11:17:20 +08:00
protocol.py refactor(sdk): typed returns, protocol contract, parser layering 2026-07-07 12:15:34 +08:00