RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
Commits on main
feat(setting-model): disable XunFei Spark provider configuration (#20753)
d542485 chanx committed 1 month ago
feat(dataset-overview): show datasource sync logs on dataset logs page (#20738)
82d1c26 chanx committed 1 month ago
fix(parser): drop hard image edge/pixel limit, add opt-in raster byte ceiling (#20745)
fd77f9d xugangqiang committed 1 month ago
feat(parser): emit structured TableData instead of HTML for tables (#20741)
97b648f xugangqiang committed 1 month ago
fix(retrieval): search each tenant index once to stop duplicate chunks (#20731)
2438c0d Vedant committed 1 month ago
fix(agent): write version_title in CreateAgentSession so Explore sessions keep it (#20739)
b0dcd51 ciel committed 1 month ago
fix(dataset): treat empty avatar as a clear signal on update (#20724)
e0b91cc ciel committed 1 month ago
Feat: Display the built-in pipeline canvas in read-only mode. (#20742)
992577d balibabu committed 1 month ago
CI: optimize, Change the ci build global lock to a host lock (#20729)
49a338f maoyifeng committed 1 month ago
feat(go): MonkeyOCR env keys and tenant provisioning (#20468)
38e6356 Sourav Rajvi committed 1 month ago
fix(agentic): preserve final answers after conversation reloads (#20718)
e79c970 Sbaaoui Idriss committed 1 month ago
fix(chunk): count merge budget in runes, not bytes (#20690)
637224d Zheng Haoran committed 1 month ago
fix(agent): cap Wikipedia extracts by runes instead of bytes (#19959)
b01ad15 Marcel Jiron · MarMar Labs committed 1 month ago
fix(chat): cap TTS text at 500 characters instead of 500 bytes (#20344)
ee8ed21 Marcel Jiron · MarMar Labs committed 1 month ago
fix(deepdoc): judge PDF header/footer and TOC removal against the full document instead of the parsed page subset (#20719)
accddd3 ciel committed 1 month ago
fix(wiki): tokenize GetWikiGraph keyword to match pre-tokenized content_ltks (#20722)
fb125d0 qinling0210 committed 1 month ago
Fix: On the multi-model comparison page, the "Apply," "Delete," and "Add" buttons should be disabled whenever any of the models is generating output. (#20723)
8207010 balibabu committed 1 month ago
CLI dataset document pagination is sent as HTTP headers (#20493)
1dc6f3e Taranum Wasu committed 1 month ago