zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-08-17 05:56:16 +08:00
Code Issues Packages Projects Releases Wiki Activity
8,339 Commits 5 Branches 109 Tags
c6ba54bc7236dcbf463a9e94072103cb8d64f7d8
Commit Graph

8339 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
S
c6ba54bc72 fix: stop three recurring errors on doc delete (#17685) (#17686) 
Follow-up to #17526 ("Refactor: merge dataset scope graph"), which introduced two code paths that touch Infinity columns the deployed schema does not declare. This PR makes the runtime robust against the old schema while also adding the new column to the new schema so freshly created tables are correct.
nightly 		2026-08-16 09:25:51 +08:00
qinling0210
554fb1133a Search in navigation tree & store graph content in nav_doc (#18303) 
### Summary

Search in navigation tree & store graph content in nav_doc during parse
 2026-08-14 22:26:57 +08:00
euvre
00df872e03 fix(search): show honest empty state when mind map has no content (#18294) 2026-08-14 20:22:29 +08:00
euvre
0df1b24f76 fix(web): show queued memory extraction tasks as pending instead of failed (#18297) 2026-08-14 20:22:00 +08:00
balibabu
a897a25aa7 Fix:The dialog will display the referenced documentation even if the API does not return any documentation data. (#18298) 2026-08-14 20:18:55 +08:00
chanx
c9fda1c26c Fix: hide top-k under the rerank model (#18302) 
### Summary

Fix: hide top-k under the rerank model
 2026-08-14 20:16:37 +08:00
buua436
024c35f085 fix: track wiki chunk changes incrementally (#18285) 2026-08-14 20:11:55 +08:00
euvre
34e59c8ec9 fix(web): enlarge card '...' edit button hit area (#18262) 2026-08-14 20:07:12 +08:00
Jin Hai
fa5762336b Go: fix context, part2 (#18296) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-14 19:42:41 +08:00
euvre
01d351b54a Go: align cancel-parse error with Python for un-started documents (#18245) 2026-08-14 19:22:36 +08:00
euvre
b1fd00074e fix(web): preserve leading whitespace in chunk card content (#18215) 2026-08-14 19:17:25 +08:00
balibabu
98b3785eff Fix: Prevent the tool operator from being dragged and connected by other operators. (#18290) 2026-08-14 19:12:58 +08:00
buua436
1c402be21d fix: hide wiki mode on python backend (#18289) 2026-08-14 19:12:45 +08:00
balibabu
3a8ea35965 Fix: If the model is removed from the supplier list, an error should occur when accessing the search and memory pages. (#18270) 2026-08-14 19:07:57 +08:00
Jack
2678a0c5f5 deepdoc: send lossless PNG instead of JPEG to the DeepDoc inference service (#18282) 2026-08-14 18:49:33 +08:00
euvre
3d50f8bcfc fix(go-agent): forward sys.files uploads to vision LLMs (#18246) 2026-08-14 18:26:09 +08:00
euvre
3fbc6346d0 fix(agent): keep agent chat sidebar scroll container shrinkable (#18252) 2026-08-14 18:24:26 +08:00
euvre
94f535f364 fix(web): make the selected agent-explore session visually distinct (#18253) 2026-08-14 18:24:20 +08:00
chanx
6a35e8d806 fix(web): clarify batch model action labels (#18283) 2026-08-14 18:22:35 +08:00
chanx
ed4e1c03c0 fix(web): scope answer loading placeholder to the last message (#18284) 2026-08-14 18:22:20 +08:00
balibabu
6445390c24 The tool operators that allow the agent to be collapsed and hidden (#18288) 2026-08-14 18:22:06 +08:00
Jin Hai
2c775d0549 Go: fix context (#18291) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-14 17:50:13 +08:00
Haruko386
5bb5ba2216 fix: return total numbers of the search result (#18071) 
### Summary

As title
 2026-08-14 17:44:38 +08:00
Haruko386
d77b514d3e feat[syncer]: add checkpoint resume run for Github (#18260) 
### Summary

As title

---------

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2026-08-14 17:44:25 +08:00
Haruko386
a2e6ddb56d feat[syncer]: add checkpoint resume run for RSS (#18257) 
### Summary

As title

---------

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2026-08-14 17:44:10 +08:00
Haruko386
cdbd82df4f fix: return total number of docs when sync has no update (#18255) 
### Summary

As title

---------

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2026-08-14 17:43:55 +08:00
euvre
ea3a2b2676 fix(web): pass pdf.js cMap/standard font URLs so CID-font PDFs render in preview (#18249) 2026-08-14 17:08:46 +08:00
euvre
24033bf199 fix(web): add tooltip to web search toggle in chat input box (#18276) dev-20260814-2 2026-08-14 16:58:50 +08:00
euvre
fe963e69ba fix: route TokenChunker delimiter_mode "one" to OneChunker in Go ingestion (#18121) 2026-08-14 16:55:32 +08:00
Jack
ae256bcf59 feat(chunker): add ManualChunker for manual-layout PDFs (#18272) 
Add `ManualChunker`, the Go port of Python's `manual` doc-type chunk method (`rag/app/manual.py`). Like `GroupTitleChunker` it merges adjacent text records into heading-bounded groups, but it first re-sorts the records into physical reading order before grouping.
 2026-08-14 16:55:08 +08:00
Lynn
471070c2c8 Fix: return error when no valid speech text in intranscription response (#18277) 2026-08-14 16:27:34 +08:00
euvre
e1330423ac fix(agent): keep think tags in persisted agent session messages (#18222) 2026-08-14 16:00:08 +08:00
euvre
14c5a61350 fix(web): render file-type icons for mp3/svg and fall back to a default file icon (#18230) 2026-08-14 15:59:17 +08:00
euvre
0d198fccec Fix DateTimeTzField crashing on driver-native datetimes and unparseable values (#18264) 2026-08-14 15:56:05 +08:00
balibabu
e4df8ebc5c Fix: Delete unused wiki template pages. (#18275) 2026-08-14 15:55:12 +08:00
YanZhang
1097cc9c84 docs: add compilation docs & fix some issues (#18268) 
add chat channel images
add compilation docs
fixed incorrect section organization of agent docs 
fixed duplicate text issues.
 2026-08-14 15:46:30 +08:00
euvre
5d408d0aa6 fix(web): widen max_tokens number input in LLM settings popover (#18265) 2026-08-14 14:52:26 +08:00
euvre
91bfcdf3f4 fix: update Tongyi Qianwen API key URL to bailian console (#18266) 2026-08-14 14:51:52 +08:00
balibabu
3fdf29b609 Fix: Editing a document slice requires showing the wiki's update button (#18267) 2026-08-14 14:48:59 +08:00
buua436
15a63bc15c fix: exclude disabled documents from wiki compilation (#18261) 2026-08-14 13:45:14 +08:00
Jack
c23d5fc819 fix(parser): support .msg parsing and make email attachments retrievable (#18198) 
- Add Go `EmailParser` support for Outlook `.msg` (OLE2/CFB) files via
the `gomsg` library, in addition to the existing `.eml` (RFC 5322)
support. The `.msg` hard-error is gone; emails with `.msg` attachments
are now ingested end-to-end.
- Re-chunk email attachments into retrievable text (user-oriented). Each
attachment is re-parsed by its file extension through the shared parser
registry and folded back into the same document, so attachment content
becomes searchable. This mirrors Python's legacy `rag/app/email.py`.
Binary attachments (images/audio/video/folders) are skipped by design.
- Restore a corrupted `sample.msg` test fixture and add guards so binary
fixtures are never mangled again (`.gitattributes` marks `*.msg` binary;
`check_files.py` skips NUL-byte files). Also made `check_files.py`
ruff-clean.
 2026-08-14 10:38:38 +08:00
Zhichang Yu
620f807cb5 Port agentic search high/ultra research loop to Go (#18242) 
Implement two-level research loop, sufficiency ladder, AutoRater, grounded review, pipeline, inspector tools, and graph exploration for high/ultra agentic search modes.
 2026-08-14 10:16:46 +08:00
chanx
5e871986e2 refactor(web): drop per-model checkbox selection from batch actions (#18233) dev-20260814 2026-08-14 09:49:36 +08:00
Lynn
58abab50cc Fix: reject move to current location request (#18234) 2026-08-14 09:34:20 +08:00
chanx
1127ce0cb0 fix(web): enable client pagination in admin user detail tables (#18238) 2026-08-14 09:34:06 +08:00
Jack
423c8489b5 fix(chunker): carry overlap-head PDF positions into new chunk (#18148) (#18227) 
When `TokenChunker` starts a fresh chunk with an overlap prefix (Go `computeOverlapPrefix` / Python visible-text cut), the previous chunk's **tail PDF coordinates were dropped**. As a result, the overlap head of a PDF chunk is displayed but **not highlighted** — the highlight box is shifted/truncated relative to the displayed span (infiniflow/ragflow#18148).
 2026-08-13 22:18:33 +08:00
Jin Hai
811f9dd0df Go: refactor embed and rerank interface (#18240) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-13 22:14:23 +08:00
Jin Hai
e2acf3aebb Go: add error logs when fail to init infinity (#18235) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-13 20:17:53 +08:00
mkaaad
3ce1b9be3d Add MySQL and PostgreSQL connectors to Go syncer (#18162) 
As title

---------

Co-authored-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-13 20:16:44 +08:00
qinling0210
c5ff2bced5 Refine agentic RAG phase logging (#18228) 
### Summary

Refine agentic RAG phase logging

example:
```
2026-08-13 17:25:06,733 INFO     2434554 [Agentic RAG] LLM usage by phase:                                                             phase            llm_calls prompt_tok   output_tok  total_tok    time(s)
  formalize              1        389          151        540        1.7
  route                  1        287          234        521        2.7
  planner                1      11857          832      12689        6.8
  orchestrator round 1       0          0            0          0      171.5
    claim_research (2)       8      82519        23146     105665      131.0
    sufficiency            2      10122         1709      11831       15.0
    grounded               1       5846         3232       9078       24.7
  finalize               2       9945         2228      12173       19.9
  total: 16 LLM calls, 152497 tokens
```
 2026-08-13 20:15:24 +08:00