zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-08-13 04:13:35 +08:00
Code Issues Packages Projects Releases Wiki Activity
8,183 Commits 5 Branches 106 Tags
4a8bb1b72ae8f4d48fffa0a66d527b8dc52a9889
Commit Graph

8183 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jack
4a8bb1b72a test(parser): add shared golden-doc + alignment helpers (#18098) 
Centralize the shared golden-doc + alignment helpers in `align_test.go` so the format-specific PRs (text&code, markdown golden, HTML) reuse one implementation instead of each carrying their own copy of the scaffolding.
 2026-08-11 18:00:25 +08:00
dependabot[bot]
f0d1ff52ab chore(deps): bump fast-uri from 3.1.0 to 3.1.5 in /web (#18103) 
Bumps [fast-uri](https://github.com/fastify/fast-uri) from 3.1.0 to

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-08-11 17:52:30 +08:00
qinling0210
d49af7f218 Generate navigation, navigation search (#18096) 
### Summary
2 API

POST /api/v1/datasets/{dataset_id}/navigation

GET
/api/v1/datasets/{dataset_id}/navigation/search?q={query}&mode={mode}&top_k={topk}


2 cli

uv run --no-sync python3 admin/client/ragflow_cli.py -h 127.0.0.1 -p
9380 -t user

ragflow> GENERATE NAVIGATION OF DATASET 'frames tree';

ragflow> NAVIGATION SEARCH 'Christie introduced blockchain-based digital
passports' IN DATASET 'frames tree' MODE 'all' topk 20;

(mode: chunk, nav_cluster, nav_doc, navigation_tree, all)
 2026-08-11 17:48:24 +08:00
Jack
a399b93143 Test(chunker): add golden parity harness, fixtures, and live Go<->Python tool (#17735) 
Golden-parity test infrastructure for the **Go `TokenChunker` ↔ Python alignment**.
It runs the Go chunker over a committed case set (`testdata/parity/cases/`) and diffs each output against a captured Python golden (`testdata/parity/golden/`), honoring a `known_diffs.json` ratchet (`extra_fields` / `chunk_count` / `chunk_text`) so accepted divergences are tracked rather than silently widening.
 2026-08-11 17:46:34 +08:00
chanx
ba671861e2 Fix: stabilize agent log handleSearch and preserve page_size on reset (#18087) 2026-08-11 17:25:24 +08:00
balibabu
7793d3c01c Fix: Retrieve the latest timeline data after cancelling the timeline task. (#18102) 2026-08-11 17:25:09 +08:00
balibabu
5dde775e19 Fix: If a message contains multiple files, they need to be displayed with automatic line wrapping. (#18109) 2026-08-11 17:24:47 +08:00
Lynn
59a524de70 Fix: remove some deprecated model (#18105) 2026-08-11 17:24:23 +08:00
Wang Qi
8e04f95773 Fix to force logout user when set user as inactive (#893) (#18104) 2026-08-11 17:00:57 +08:00
Jin Hai
d7661b676d Go: fix context and warnings (#18097) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-11 16:18:49 +08:00
chanx
2409248801 fix: show filtered session count in session list header (#18094) 2026-08-11 16:14:08 +08:00
chanx
d33f87d3ca feat: rename agent log export button to export current page (#18090) 2026-08-11 16:13:56 +08:00
euvre
82d038543a fix: wrap long log messages in agent pipeline log sheet (#17782) 2026-08-11 16:08:43 +08:00
Haruko386
dd52dee600 feat[Go]: monitoring NATs and refactoring concurrency logic (#18049) 
### Summary

As title
 2026-08-11 14:36:11 +08:00
Jin Hai
25b579ac6c TS: more license declarations (#18081) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-11 14:21:14 +08:00
balibabu
61fa96ee06 Fix: Click the blank area to prevent UpdateLogSheet from closing. (#18085) 2026-08-11 14:09:54 +08:00
balibabu
398d81f587 Fix: Move the content of the "Token Size" tab from the token chunker operator to the "Delimiter" tab. #17888 (#17975) 2026-08-11 14:07:15 +08:00
euvre
d33b937be6 fix(web): prevent column shift in data source log table (#17940) 2026-08-11 13:59:51 +08:00
buua436
5fd66154f3 fix: improve structure keyword search (#18055) 2026-08-11 13:58:00 +08:00
Zhichang Yu
64533e5b5e Refactor splitByTokens and wire wiki incremental compile (#18083) 
Port dataset-level wiki incremental compile and refactor splitByTokens
token budgeting. Includes replace-only wiki merge, KNN dedup routing,
and template/config wiring.
 2026-08-11 13:46:55 +08:00
balibabu
f83c4f97c1 Fix: After creating a wiki template and deleting the model instance, the default model appears empty, but it can still be edited and saved successfully. (#18075) 2026-08-11 13:45:04 +08:00
Yingfeng
f1641228e2 Refine agentic search & orchestration loop (#18057) 
## Summary

This PR improves the RAGFlow agentic-search path in three areas: it
stops the outer agent from re-looping over the same rag call, lets the
medium thinking mode discover and follow new sub-claims mid-loop, and
strengthens retrieval by having the LLM emit synonym-rich queries with
time/date/number terms boosted.

1. Avoid the outer re-loop — keep all multi-hop cycles inside agentic
RAG

2. Dynamic claims in medium mode — keep querying newly discovered
sub-questions
medium now enables allows_dynamic_claims. During orchestration, when
claim analysis discovers a new required sub-question
(discovered_claims), the loop spawns it as a new ClaimTarget and
continues searching it in subsequent cycles (bounded by the
dynamic-claim budget) instead of stopping. Also added:

3. Stronger query strategy — synonym-rich queries + time/date/number
weighting

LLM-generated synonyms: the claim-analysis prompt now instructs the
model to write each next_queries entry as a retrieval-boosted query that
actively folds in entity aliases, DATE/TIME synonyms (e.g. 1994 → 1994,
66th Academy Awards), and number/unit variants (e.g. 1.95 m → 6 ft 5
in).

Time/date/number boosting: query.py boosts numeric/date tokens to a high
weight (_NUM_DATE_TOKEN_RE).
 2026-08-11 13:40:11 +08:00
chanx
f930b1c1bc Fix: New sessions will automatically carry over messages from the previous session by default. (#18078) 2026-08-11 13:38:46 +08:00
chanx
e0d199ea7b fix(floating-selection-toolbar): adjust dropdown direction based on available space (#18053) 2026-08-11 13:31:42 +08:00
chanx
11c9649a6c Fixed: Updated the text color style of the copy button. (#18062) 2026-08-11 13:30:57 +08:00
Wang Qi
bd876c796e Fix: restrict xxx_ids to limit 100 (#18074) 2026-08-11 13:28:52 +08:00
Wang Qi
d7d6bb5b6a Fix max chunk_ids = 100 (#18080) 2026-08-11 13:13:08 +08:00
Jin Hai
fc44d2fe3f Go: fix context (#18076) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
dev-20260811-2 		2026-08-11 11:54:57 +08:00
jay77721
9f0663d4d0 fix(ingestion): avoid duplicate chunk text injection in Extractor prompts (#18034) 2026-08-11 11:53:34 +08:00
chanx
d199f4b867 fix(search): pass selected pageSize when retrieving chunks on document change (#18072) 2026-08-11 11:45:21 +08:00
chanx
cad2833c16 fix: Remove unused constant files (#18069) 
### Summary

fix: Remove unused constant files
 2026-08-11 11:16:06 +08:00
Jin Hai
cb3de6ae98 TS: add apache license (#18064) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-11 11:15:45 +08:00
Jin Hai
8379836179 Go: add context to test (#18070) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-11 11:12:34 +08:00
Jack
d6f6b6231f Fix(parser): don't collapse markdown doc into one item when a table is present (#18014) 2026-08-11 10:21:42 +08:00
Jack
dc73163908 Fix(tokenizer): pin alignment guards (#18011) 2026-08-11 10:09:07 +08:00
Jin Hai
e551167697 TS: fix comments (#18067) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-11 10:00:54 +08:00
Lynn
15ab2b3ee2 Fix: update tree when delete skill node (#18063) 2026-08-11 09:49:22 +08:00
Jin Hai
38c5d7c338 Go: fix context (#18061) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
dev-20260811 		2026-08-10 20:49:32 +08:00
Wang Qi
a0438517bc Fix add agent update validation check (#18056) 2026-08-10 20:12:51 +08:00
Lynn
7ac59d1a36 Fix: set column type priority (#18054) 2026-08-10 20:08:06 +08:00
Wang Qi
b978f94fa6 Fix: restrict max_retries as non-negative integer (#18051) 2026-08-10 20:02:24 +08:00
Wang Qi
df32ffbe57 Fix: restrict keywords_similarity_weight [0,1] (#18044) 2026-08-10 20:01:45 +08:00
Jin Hai
dbd062f65e Go: fix context (#18060) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-10 19:11:43 +08:00
Jin Hai
cb649e8d56 Go: fix warning (#18058) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-10 18:50:37 +08:00
Ziyang Guo
eb184c839c chore(wiki): remove stray debug print (#18020) 
### Summary

Remove a stray `print()` from the Wiki source-context fallback.
 2026-08-10 18:22:44 +08:00
Jin Hai
c697fcff41 Go: fix go context (#18052) 
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-08-10 18:04:17 +08:00
maoyifeng
6f9d158e30 CI: Optimize per-install tools (#18039) 
1.  ss already installed in runner, quit the install step
2. tiktoken is already installed in runner,  skip the install step
 2026-08-10 17:55:57 +08:00
buua436
6f50e478e0 fix: exclude disabled documents from dataset structures (#18041) 2026-08-10 17:50:34 +08:00
chanx
23369586c0 fix(chat): preserve in-flight SSE stream when switching conversations (#18037) 2026-08-10 17:29:24 +08:00
chanx
6b73341827 fix(search-page): add overflow-x-auto and min-width to prevent layout issues (#18050) 2026-08-10 17:28:05 +08:00