mtfyun/ragflow
1
0 Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-11-11 22:01:50 +08:00
Code Issues Packages Projects Releases Wiki Activity
9,370 Commits 3 Branches 194 Tags
349ecfb5cc75fe02fffdcb8fa5d6b2d6ea2ddae9
Commit Graph
1437 Commits
Author SHA1 Message Date
Ehsan c71bb0198f fix(api): return document metadata from /dify/retrieval (#19686) 2026-09-16 19:08:02 +08:00
Öndery 98ebe5f66f Fix: keep file API responsive during large connector ingest (#19632) 
Fix large connector sync blocking event loop — offloaded document writes/DB work to threads, batched metadata refresh, added configurable batch size and sync timeout cancellation.
 2026-09-16 19:02:21 +08:00
xugangqiang e83c1963de feat(ingestion): stop persisting business data in pipeline operation-log DSL (#19631) 2026-09-16 14:07:21 +08:00
Sbaaoui Idriss d8b072fd9d fix(auth): separate OAuth JIT provisioning policy (#19651) 2026-09-15 19:40:21 +08:00
huyua9 b692b5fef9 fix(api): preserve parent-child config on partial updates (#18949) 
Fix partial parser_config updates wrongly disabling parent-child parser. Flattening now only runs when parent_child is explicitly present.
 2026-09-15 14:18:28 +08:00
Jin Hai 7218db7557 PY: refactor (#19599) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-09-14 18:52:59 +08:00
Sbaaoui Idriss 9e932547e5 fix(storage):preserve errors during backend retries (#19578) 2026-09-14 14:39:30 +08:00
Harsh Kashyap 9ec20a97e9 fix(api): treat an empty metadata_condition.conditions list as no filter (#19368) 
Fix #19366 — empty metadata_condition no longer treated as active filter (was scoping to -999, returning zero chunks, and dropping document_ids).
 2026-09-14 14:13:06 +08:00
Harsh Kashyap af61e3fcd6 fix(api): validate embedding check sample count (#19574) 
Fix #19567 — validate check_num before sampler use. Non-integer/zero/negative values now return clear argument errors.
 2026-09-14 13:53:11 +08:00
Guofang.Tang 984d8ab510 fix(agent): make Python webhook trace appends atomic (#19091) 
Fix Python webhook trace race — now uses Valkey WATCH transaction with retry instead of GET/SET, preventing concurrent overwrites.
 2026-09-14 12:59:09 +08:00
Sourav Rajvi b15b159d07 feat(api): add image_update_mode for chunk image updates (#18889) 
Fix #18585 — chunk PATCH now supports image_update_mode: append (default), replace, remove.
 2026-09-14 12:57:13 +08:00
Yingfeng 1f5d33333a Add claim/evidence to tree/pageindex compilation pipeline (#19267) 2026-09-11 22:37:33 +08:00
Sbaaoui Idriss bcf33c6238 fix(structure-graph): discover buckets from raw rows (#19523) 2026-09-11 13:37:01 +08:00
buua436 2aedd79b8f refa: remove unused knowledge compilation code (#19437) 2026-09-11 10:15:53 +08:00
Harsh Kashyap 19ec6245c4 fix(api): authorize task cancellation by dataset access (#19359) 2026-09-11 09:53:09 +08:00
buua436 7e86beadd1 fix: route navigation API through tree search (#19493) 2026-09-10 17:13:57 +08:00
K.P 8efa7383e6 fix: prevent IndexError in PUT /api/v1/searches/<id> when search not found (#16027) 
Fix #16011 — check search exists before indexing [0]; returns proper error instead of 500.
 2026-09-09 15:31:41 +08:00
Harsh Kashyap fb2f881871 fix(api): authorize dataset and workspace commit routes (#19357) 
Fixes #19356

The file-commit endpoints resolved a dataset or folder id but never
checked that the caller can access it. Any logged-in user could read
another tenant's commit history, diffs, and file contents, pull version
history for any file id, and create commits in a workspace they don't
own. Sibling artifact routes in dataset_api.py apply
KnowledgebaseService.accessible for the same data; these did not.
 2026-09-09 10:33:23 +08:00
euvre 3931c69a5b fix(api): return "search not found" instead of IndexError when updating a missing search (#19380) 2026-09-09 10:02:06 +08:00
Gonghan-Princess 24c115bf92 feat(channels): allow chat channels to connect to agents (#19307) 2026-09-08 18:44:59 +08:00
Sbaaoui Idriss a670f5260b fix(docs): document dataset language create and update behavior (#19372) 
### Summary

The API docs now describe the optional language field for dataset
creation and updates. They document trimming, validation limits,
defaults, and unchanged update behavior.
 2026-09-08 16:26:42 +08:00
buua436 7b01906d45 fix: filter structure alteration by document products (#19346) 2026-09-08 13:23:28 +08:00
MarMar Labs 6c280f10a0 fix(api): accept repeated memory_type and tenant_id filters when listing memories (#19281) 
Fix GET /api/v1/memories list filters — memory_type, tenant_id, owner_ids, ids now read all repeated query keys (was only first). Matches /datasets//documents pattern.
 2026-09-08 11:48:16 +08:00
Wang Qi b7e577ce48 Refactor: combine 3 retrieval/search API as one (#19303) 2026-09-08 11:41:46 +08:00
Manan Bansal 03d861a926 fix(api): allow setting language on dataset creation (#15703) (#16242) 
Fix #15703 — dataset create endpoint now accepts language.
 2026-09-08 10:53:40 +08:00
ÖnderyandCursor 38230c45d3 feat(llm): forward OpenAI user on embedding and parse requests (#19065) 
Add user attribution to embedding calls — forwards user on OpenAI-compatible providers via current_llm_user(). Excludes LocalAI/Xinference (reject unknown fields). Accepts user_id on ingest/parse/chunk endpoints; redacts from logs. Omitted = unchanged. Go/vision/TTS/ASR out of scope.

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-07 19:30:33 +08:00
Wang Qi f8b0a1de19 Refactor: update dataset API should not have ext (#19272) 2026-09-07 14:25:15 +08:00
MarMar Labs fa52804fa3 fix(api): return the full error tuple when both id and ids are given to list documents (#19280) 
Fix dataset document list endpoint unpack error when both id and ids provided — helper returned 2 values but caller expects 4. Now returns 4.
 2026-09-07 10:58:05 +08:00
Lynn ff69dba542 Fix: apply dia.llm_id overrides (#19214) 
### Summary

As title, from #15610
 2026-09-04 17:46:49 +08:00
buua436 f4bafa1596 fix: exclude empty documents from structure alteration (#19246) 2026-09-04 17:06:38 +08:00
Lynn 2f8dab2199 Fix: upload image to model in chat (#19257) 2026-09-04 16:37:25 +08:00
buua436 447f87d79f feat: adapt knowledge compilation concurrency (#19156) 2026-09-04 11:17:56 +08:00
表面谢金城Jin Hai
 		68cdb795f5 Fix OAuth redirect URI examples (#15683) 
Fix OAuth callback URL examples in docs — now use /api/v1/auth/oauth/<channel>/callback (was stale /v1/user/oauth/callback).

Co-authored-by: 谢金城 <xiejincheng@xgd.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
 2026-09-03 15:20:42 +08:00
mkaaadandcoderabbitai[bot] d29a4fc26b fix(py-go-connector): enforce kb authorization in rebuild (#19190) 
Based on community PR #15272 by @rene0422

---------

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2026-09-03 12:01:28 +08:00
Sbaaoui Idriss f8fc130162 fix(searchbots): enforce KB authorization before retrieval (#19165) 2026-09-03 11:10:57 +08:00
Yingfeng a11c27e01d Adjust navigation tools for agentic search (#19172) 2026-09-03 10:43:00 +08:00
Wang Qi 6ec9c6a737 Fix: get rid of graphrag raptor in parser_config in REST API (#19161) 2026-09-03 09:40:52 +08:00
Lynn c534144a4c Fix: restrict tenant updates to the current user's own tenant (#19155) 
### Summary

As title.
 2026-09-02 19:08:27 +08:00
buua436 cf441d4c72 fix: align wiki alteration provenance (#19140) 2026-09-02 18:03:15 +08:00
Wang Qi b4a3ff3c64 Fix: link to existing dataset clean the document chunks (#19143) 2026-09-02 16:00:37 +08:00
Wang Qi 61492c0362 Refactor: add total/returned entities/relations 2 (#19114) 
Follow on #19095
 2026-09-02 14:28:58 +08:00
Jin Hai 988dfda4c9 Fix: Use default pipeline configuration when parsing documents via HTTP API- #13297 (#19116) 
Refer to #13297

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-09-02 06:12:17 +08:00
Wang Qi fe63e09781 Refactor: add total/returned entities/relations (#19095) 2026-09-01 16:01:59 +08:00
MarMar Labs 5e1898e293 fix(dify): search the dataset owner's index, not the caller's (#18987) 
Fix team-member Dify retrieval searching wrong tenant index. Changed tenant_id to kb.tenant_id in both retrieval_by_children and kg_retriever.
 2026-08-31 17:11:40 +08:00
Tai AnAnai-GuoJin Hai
 		b149a392f4 fix(api): return parsing-status counts at the top level of each dataset (#17595) (#17611) 
Fix #17595 — parsing status counts now return as top-level fields per documentation, not nested under parsing_status.

Signed-off-by: Anai-Guo <antai12232931@anaiguo.com>
Signed-off-by: Anai-Guo <antai12232931@outlook.com>
Co-authored-by: Anai-Guo <antai12232931@anaiguo.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-31 13:52:08 +08:00
Wang Qi 66113709cc Feature: add highlight for retrieval testing and search (#18981) 2026-08-28 19:26:41 +08:00
天海蒼灆andCursor 9ca62e8da3 fix: include filename in file download Content-Disposition header (#17105) 
### Summary

GET /api/v1/files/{id} now sets attachment filename for both Python and
Go handlers so browsers can save downloads with the correct name.

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-28 14:42:04 +08:00
Jin Hai d37486e295 Python && Go: fix parse status (#18841) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-28 12:47:41 +08:00
MarMar Labs 439c3be9cb fix(dataset): rebuild the navigation tree in the dataset owner index (#18932) 
Fix generate_nav tenant mismatch: wipe used dataset owner's tenant_id but rebuild used caller's. Team members could delete owner's navigation tree and rebuild into their own. Now both use kb.tenant_id.
 2026-08-28 11:58:31 +08:00
Wang Qi f74e04581a Refactor: add page_size support (#18876) 2026-08-28 09:37:44 +08:00