PageIndex/pageindex
Ray ad7f152ea7 fix: whitelist parser metadata to its documented fields before storing
The unfiltered metadata spread let a custom parser overwrite managed
columns — stashing 'file_path' in metadata silently repointed the stored
row at the user's original file, which delete_document would then
unlink. ParsedDocument documents page_count/line_count as the only
persisted metadata; merge exactly those.
2026-07-21 17:59:04 +08:00
..
backend fix: whitelist parser metadata to its documented fields before storing 2026-07-21 17:59:04 +08:00
index chore: drop the pymupdf extra — image extraction detects the library at runtime 2026-07-19 16:31:37 +08:00
parser chore: fix stale 'optional extra' wording in comment 2026-07-19 16:32:58 +08:00
storage feat: restore status and page/line counts in local get_document 2026-07-19 15:25:25 +08:00
__init__.py chore: drop PAGEINDEX_API_KEY from the .env comment — the library never reads it 2026-07-21 17:10:31 +08:00
agent.py fix: cancel the agent run when a streaming query is abandoned 2026-07-21 17:57:24 +08:00
client.py fix: fail fast when CloudClient gets an empty api_key 2026-07-21 17:10:31 +08:00
cloud_api.py chore: drop the lowercase-summary comment — the server parses bools case-insensitively (0.2.x sent 'True' for years) 2026-07-21 17:10:31 +08:00
collection.py refactor: spell out collection instead of col in examples, README, and docstrings 2026-07-19 15:25:17 +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 chore: trim fix-rationale comments, restore --model help, drop stale gitignore entry 2026-07-19 16:16:09 +08:00
tokens.py refactor(sdk): typed returns, protocol contract, parser layering 2026-07-07 12:15:34 +08:00
types.py feat: restore status and page/line counts in local get_document 2026-07-19 15:25:25 +08:00
utils.py fix: address xhigh review findings for PR #272 2026-07-16 01:31:57 +08:00