xugangqiang 7c99668aee fix(parser): emit xlsx spreadsheets as typed table chunks (#19509)

2026-09-14 15:10:48 +08:00

..

advanced_rag

fix(wiki): stamp retrieval fields so compiled pages are searchable (#18787)

2026-09-14 12:56:29 +08:00

app

Fix the remaining rag/app chunkers treating an empty upload as a missing binary (#19256)

2026-09-08 11:02:07 +08:00

flow

fix(parser): emit xlsx spreadsheets as typed table chunks (#19509)

2026-09-14 15:10:48 +08:00

graphrag

fix: replace editdistance with rapidfuzz for python 3.13 wheel support (#18132)

2026-08-11 21:44:36 +08:00

llm

feat: add AnonRouter model provider (#19561)

2026-09-14 11:31:02 +08:00

nlp

[Refactor] Use regex to do hightlight (#19488)

2026-09-10 16:34:09 +08:00

prompts

fix(token_utils): build the tiktoken encoder on first use, not at import (#18986)

2026-09-04 15:46:30 +08:00

svr

fix(dataflow): preserve scalar text output shape (#18921)

2026-09-11 11:55:12 +08:00

utils

fix: fix security issue in ob_conn_base.py (#19524)

2026-09-14 11:49:38 +08:00

conftest.py

refactor(nlp): collapse 6 delimiter-parser implementations into one canonical helper (#17383) (#17387)

2026-08-02 17:07:14 +08:00

test_delim.py

refactor(nlp): collapse 6 delimiter-parser implementations into one canonical helper (#17383) (#17387)

2026-08-02 17:07:14 +08:00

test_delimiter_case_sensitive.py

Fix: delimiter is chunk boundary, drop token_size atom-split (OVER_CAP default) (#17808)

2026-08-05 11:50:07 +08:00

test_doc_exists_cache.py

fix(search): honor the cached document-deleted flag so deleted docs stay pruned (#19070)

2026-09-01 12:54:00 +08:00

test_docx_question_level.py

fix(rag/nlp): handle non-numbered DOCX heading styles (#16219)

2026-06-29 15:21:17 +08:00

test_feishu_wiki_sync_adapter.py

feat(data-source): add Feishu Wiki file connector (#19425)

2026-09-14 09:50:59 +08:00

test_feishu_wiki_sync_failure.py

feat(data-source): add Feishu Wiki file connector (#19425)

2026-09-14 09:50:59 +08:00

test_find_codec.py

test(rag/nlp): cover the BOM and LookupError branches of decode_text (#19292)

2026-09-08 11:02:37 +08:00

test_flow_chunker_import.py

fix(tests): isolate token chunker imports (#18018)

2026-08-13 15:43:11 +08:00

test_is_english.py

fix(rag/nlp): treat string input as one phrase in is_english (#16308)

2026-06-25 20:07:09 +08:00

test_laws_docx_tables.py

Fix: resolve model_id to model before judge parse method (#17493)

2026-07-29 09:34:52 +08:00

test_merge_paragraphs.py

Fix: delimiter is chunk boundary, drop token_size atom-split (OVER_CAP default) (#17808)

2026-08-05 11:50:07 +08:00

test_naive_dispatch.py

fix: surface MinerU API error bodies and re-raise parser failures (#17308)

2026-09-14 11:37:17 +08:00

test_naive_merge.py

fix(chunker): unify TokenChunker merge and strip coord tags in Python JSON path (#18002)

2026-08-07 21:55:07 +08:00

test_paper_chunk_size.py

fix(paper): bound title-pivot merge by chunk_token_num (#12109) (#16959)

2026-09-08 18:47:43 +08:00

test_prune_deleted_chunks.py

fix(wiki): stamp retrieval fields so compiled pages are searchable (#18787)

2026-09-14 12:56:29 +08:00

test_rank_feature_scores.py

Fix tag_feas code injection in retrieval ranking (#13923)

2026-04-15 16:31:11 +08:00

test_rerank_by_model_input.py

feat(nlp): rerank on natural chunk text, not tokenized content_ltks (#16961)

2026-09-11 16:59:06 +08:00

test_search_fusion_weight.py

Refactor: expose knn top_k and knn num_candidaties (#18737)

2026-08-25 17:16:36 +08:00

test_search_pagination.py

Refactor: rename prefetch_size to rerank_candidates (#18718)

2026-08-25 11:35:53 +08:00

test_sync_data_source.py

Custom the file extension when saving DB fields, and Parse HTML fragments not just full HTML doc (#15998)

2026-09-14 10:20:35 +08:00