Jonathan Chang 9d1006e4ec fix: The output of the parser in the ingestion pipeline contains HTML tags (#14920) ...

## Summary
This change fixes ingestion quality issues where MinerU parser output
may contain HTML fragments (for example, table-related tags like `<tr>`,
`<td>`, `<br>`), which were previously passed directly into
chunking/tokenization and degraded chunk quality.

The fix adds a sanitization step in the MinerU parser path so parsed
sections are normalized to clean text before chunking.

## Change Type (select all)
- [x] Bug fix
- [x] Ingestion pipeline improvement
- [x] Parser/chunking quality fix

## Related Issue
- https://github.com/infiniflow/ragflow/issues/14831

2026-05-25 16:06:36 +08:00

..

test_agent_app

feat: add tag management for Agents with filtering and sorting (#14774) (#14799)

2026-05-13 21:41:32 +08:00

test_auth_app

tests: improve RAGFlow coverage based on Codecov report (#13219)

2026-02-26 19:03:26 +08:00

test_canvas_app

fix(agent): support iteration item aliases in child nodes (#14146)

2026-05-12 13:05:21 +08:00

test_chunk_app

Fix: shared dataset chunk index lookup (#14764)

2026-05-11 13:50:08 +08:00

test_chunk_feedback

Consolidate set_meta into update_document (#14045)

2026-04-13 12:47:17 +08:00

test_connector_app

Feat: full optimization on connector dashboard (#14979)

2026-05-19 10:07:11 +08:00

test_dataset_management

Fix: restore embedding model switching for datasets with existing chunks (#14732)

2026-05-09 18:48:57 +08:00

test_document_app

Revert "fix(api): infer /documents/{id}/download Content-Type from filename when ext is omitted (#15052)" (#15138)

2026-05-22 11:46:01 +08:00

test_file_app

Fix IDOR: Add permission checks to file ancestry endpoints (#14725)

2026-05-09 16:03:23 +08:00

test_llm_app

Adds gpt-5.4-mini and gpt-5.4-nano (#14908)

2026-05-14 10:16:24 +08:00

test_mcp_server_app

fix: The output of the parser in the ingestion pipeline contains HTML tags (#14920)

2026-05-25 16:06:36 +08:00

test_memory_app

Fix: validate memory tenant model IDs on update and enforce tenant scope in memory pipeline (#14923)

2026-05-19 10:11:46 +08:00

test_message_app

fix: support dense_vector from ES fields response (ES 9.x compatibility) (#13972)

2026-04-09 17:44:13 +08:00

test_plugin_app

API refactor: stats_api and plugin_api (#14324)

2026-04-23 17:16:04 +08:00

test_search_app

fix(api): authorize owner_ids for list chats and search apps (#14775)

2026-05-13 09:43:44 +08:00

test_system_app

fix(auth): fall back to session-based auth in _load_user (#14569)

2026-05-11 09:59:52 +08:00

test_user_app

Refactor user REST API (#14334)

2026-04-24 10:25:15 +08:00

conftest.py

Refa: migrate chunk APIs to RESTful routes (#14291)

2026-04-23 14:17:23 +08:00

test_common.py

Refa: migrate document preview/download to RESTful API (#14633)

2026-05-08 13:26:13 +08:00