infiniflow/ragflow v1.0.0 on GitHub

What's Changed

fix(parser): keep recovered PDF TOC leader lines out of the body guard by @jay77721 in #21768
CI: Fix log tee failure by @myf-bee in #21791
Update release notes of 1.0.0.rc3 by @yingfeng in #21793
feat: add Wally as a model provider by @adityabatra072 in #21719
add audit hooks to file APIs by @JinHai-CN in #21807
add log hooks by @JinHai-CN in #21822
i18n: translate pipeline version and parser settings strings in tr-TR by @bakiburakogun in #21819
fix(models): honour context cancellation in driver HTTP requests by @ccclucky in #21643
feat(vastbase): support Vastbase G100 as the metadata database in Go by @FengYikai710 in #20913
fix: README.md by @eridan-ltu in #21828
fix(chunker): prevent PDF child chunks from overwriting each other by @jay77721 in #21773
test(sdk): remove explicit Python SDK test skips by @6ba3i in #21783
fix(syncer): retain Dropbox checkpoints on download failure by @Zhi-Xiang-Guo in #21809
fix(api): keep the datasets API error response body shape by @simpleqt in #21831
perf(web): virtualize chat message lists by @dcc123456 in #21790
CI: add check for ASCII, disallow none ASCII code check-in by @wangq8 in #21784
fix(anthropic): support struct json schema in tool parameters by @Sanderhoff-alt in #21638
feat(parser): hand off Markdown and HTML remote images as media refs by @jay77721 in #21764
fix(paddleocr): handle submit request creation errors by @QAQadws in #21839
fix(deepdoc): add cgo constraints to native configuration tests by @QAQadws in #21837
fix: SoMark web page is missing by @fenglingxiansheng in #21710
fix(agent): clamp dataset navigation max_docs to the default budget by @flyingwhit in #21755
feat(admin): add user search, status filtering, sorting, and CLI pagination by @QAQadws in #21729
feat(chat): add AnySearch web search provider by @GunaPalanivel in #20633
refa: consolidate model access and tenant defaults by @buua436 in #21740
fix(ingestion): stop MinerU JSON path from inlining zip figure bytes by @Souravrajvi0 in #21803
fix(tool): cap tool HTTP response bodies at 4 MiB in arxiv, querit, duckduckgo and yahoo_finance by @flyingwhit in #21769
fix(models): publish the provider catalog through an atomic pointer and drop the dao-side cache so concurrent readers and publishers no longer race by @flyingwhit in #21749
fix(agent): resolve DeepL and QWeather credentials from node config or DEEPL_API_KEY/QWEATHER_API_KEY instead of model-visible params by @flyingwhit in #21735
fix(dify): keep retrieval unscoped when metadata conditions are empty by @MoonPointer-Byte in #21766
test(retrieval) : add unit tests for retrieval and reranker by @zzy1017-crypto in #21611
fix(agent): prevent checkpoint crashes and propagate component errors by @6ba3i in #21854
fix(agent): detect webhook Begin in saved canvases by @6ba3i in #21849
fix(file): record commit deletions without a missing status column by @ccclucky in #21796
fix(tokenizer): replace the default fields instead of appending by @ccclucky in #21799
test(mediacache): cover real Kvrocks lifecycle and index boundary by @jay77721 in #21851
fix(user): use string for user id in DAO and handler lookups by @xugangqiang in #21792
fix(build): adjust onnxruntime static link flags on Darwin arm64 by @Sanderhoff-alt in #21162
release dockerhub image remove unnecessary tag by @myf-bee in #21860
fix(chunk): number paragraph chunks by their position by @Steve-20-ai in #21823
perf(chunker): coalesce PDF renders and share crop workers by @jay77721 in #21850
fix(web): restore entity type colors in knowledge graphs by @okht in #21443
fix(chunker): align PDF child previews with source positions by @jay77721 in #21853
fix(cli): list only accepted commands in \help by @mmporong in #21503
fix(channels): stop leaking a goroutine per WhatsApp events reconnect by @flyingwhit in #21863
fix(channel): add limit check to qqbot response by @flyingwhit in #21859
refactor(kvrocks): remove unused Client.GetOrCreateKey by @Sanderhoff-alt in #21298
refa: remove permission service wrappers by @buua436 in #21856
fix(ingestion): settle a terminal task's open run before deletion by @ccclucky in #21798
fix(agent): resolve single-brace variable references by @6ba3i in #21865
Revert "CI: add check for ASCII, disallow none ASCII code check-in" by @wangq8 in #21873
test: gate community-only tenant cases from EE by @buua436 in #21874
Update docs by @yingfeng in #21876
feat(ingestion): emit structured lifecycle events for document-parse tasks by @xugangqiang in #21711
refactor by @JinHai-CN in #21875
fix(agent): serialize HTTP fields and preserve errors by @6ba3i in #21857
fix(agent): resolve nested subagent components by @6ba3i in #21872
fix(agent): normalize Invoke proxy URLs and avoid panics by @QAQadws in #21855
fix(deepseek): validate and normalize thinking effort by @QAQadws in #21852
fix(test): remove two races that reddened the ingestion packages by @ccclucky in #21716
fix(gmail): retain complete MIME payload when loading threads by @Zhi-Xiang-Guo in #21811
feat: add Synap as a model provider by @jimmyplup in #21818
fix(agentic-rag): make the finalize and claims budgets configurable by @ccclucky in #21879
test(service): gate API-token identity test out of EE builds by @xugangqiang in #21885
feat(document): one-click cancel all documents in parsing queue by @xugangqiang in #21861
fix(docker): stop the SPA fallback from masking stale hashed assets by @ccclucky in #21878
update readme by @JinHai-CN in #21894
feat(go): MonkeyOCR PDF dispatch on Go ingestion path by @Souravrajvi0 in #20469
fix(ingestion): add process_end_at column and keep OSS ingest-log a no-op by @xugangqiang in #21888
Fix: Increase the spacing between the labels and the dropdown menus for the PDF and table parsers. by @cike8899 in #21882
refa: derive permission identity from context by @buua436 in #21892
Refactor: refine response data by @wangq8 in #21858
Revert "fix(ingestion): add process_end_at column and keep OSS ingest-log a no-op" by @JinHai-CN in #21897
fix(agent): use stored log titles in tables and exports by @6ba3i in #21890
fix(agent): pass scalar thresholds to memory retrieval by @6ba3i in #21889
add sync audit hook by @JinHai-CN in #21901
Fix: Variables within the "Wait for Input" and "Start" components of an agent are not accessible in the floating window. by @cike8899 in #21900
remove codecov upload by @JinHai-CN in #21902
refactor(common): revert OSS ingest-log collection from #21711 (keep instrumentation only) by @xugangqiang in #21893
Fix: Delete the agent log entry by @cike8899 in #21910
Stop persisting process_end_at; recover end time from begin + duration by @xugangqiang in #21906
feat: add user ownership to resources by @buua436 in #21914
Feat: Add a cancel button to pause tasks that are currently running or queued. by @cike8899 in #21917
Fix: The referenced content in chat and agent messages is being obscured. by @cike8899 in #21918
Fix: disable ciation not working in agentic chat by @wangq8 in #21913
fix(parser): detect Office content before selecting Go parsers by @jay77721 in #21909
feat(web): add enterprise (ee) seam layer for build-time overlays by @dcc123456 in #21908
refa: derive service identity from context by @buua436 in #21904
fix(service): purge engine data from RemoveDocumentKeepFile (#20659) by @Harsh23Kashyap in #20768
fix(ingestion): share extractor concurrency across tag extraction by @jay77721 in #21891
fix(dao): include skill spaces in auto migration by @buua436 in #21921
fix(es): preserve dataset and document scope in single chunk updates by @zzy1017-crypto in #21842
fix(whatsapp): escape the gateway events session key once by @flyingwhit in #21871
docs：Restructure the Team documentation and align sharing configuration across Dataset, Agent, and Memory. by @Yannnnnnny in #21922
fix(file): scope commit changes to the target folder tree by @ccclucky in #21795
feat(ocr): make MinerU parser timeout configurable via environment and setup by @superwiboy in #21832
Refactor: Better no such name by @wangq8 in #21925
Fix: Adjust layout of DatasetFilter component to conditionally render FilterPopover and SearchInput by @dcc123456 in #21924
Fix: Agent – Incomplete display of blueprint examples when creating a wiki template in Compiler by @cike8899 in #21919
fix(agent): populate structured output and resolve deferred @structured by @huang-aoqin in #20679
feat(gpustack): rework provider setup and fix driver issues by @lemisky in #21903
fix(agent): runtime fixes for tool naming, legacy sessions, tenant scoping and MCP SSRF by @techpreneur-a in #20558
fix(ingestion): pass the MinerU timeout to the MonkeyOCR file_parse upload by @ccclucky in #21930
refa: derive service identity from request context by @buua436 in #21923
fix(retrieval): bound rerank and KNN candidate windows by @zzy1017-crypto in #21907
feat(ingestion): recognize image tables through the DeepDoc page pipeline by @jay77721 in #21911
doc: fix typos by @JinHai-CN in #21947
Fix: Variables inserted using shortcuts fail to display in the message node. by @cike8899 in #21946
Fix: Chat embedded in a website: automatically scrolls down when a question is answered. by @cike8899 in #21940
refa: derive service identity from context by @buua436 in #21942
Fix: Long messages in floating embedded pages overflow the message box. by @cike8899 in #21951
Fix: The pipeline name is too long and overflows the release dialog. by @cike8899 in #21957
fix(agent): support String and Object Invoke parameters by @6ba3i in #21953
feat(chunker): support media context in title and manual pipelines by @ZXLyyds100 in #21111
refa: derive connector, MCP, and memory identity from context by @buua436 in #21952
allow chinese words as model instance name by @JinHai-CN in #21948
Fix: add system_settings seeder by @Lynn-Inf in #21955
perf(pdf): read page directives once per document by @jay77721 in #21950
Fix: honor ALLOW_ANY_HOST by @wangq8 in #21949
Fix: File Management - Move - Folder name is too long, causing visual clipping (clipping through UI elements) by @cike8899 in #21962
Filter agent version, allow filter with alias by @wangq8 in #21943
refactor(extractor): resolve chat model config once per run by @xugangqiang in #21960
Fix: Add a text description to the cancel-parsing button. by @cike8899 in #21966
Fix: when agentic chat fail, show the real error by @wangq8 in #21964
refactor(deepdoc): drop dead covered-slice+sort in GroupCells span injection by @xugangqiang in #21954
refactor(ingestion): consolidate unique* string dedup helpers into common by @xugangqiang in #21961
Fix: allow to move to root directory by @wangq8 in #21969
ci: web not run go test by @myf-bee in #21958
Fix: The messages in the embedded chat interface are positioned too close to the right edge. by @cike8899 in #21974
feat(observability): carry user_name/tenant_name through IngestionLog by @xugangqiang in #21968
i18n: translate GPUStack provider setup and parse cancel strings in tr-TR by @bakiburakogun in #21963
feat(ingestion): record pipeline version on operation logs by @jay77721 in #21916
fix(agentic_rag): make the decisionhead package compile without cgo by @ccclucky in #21932
fix(deepdoc): keep DLA-labeled body prose out of table captions by @jay77721 in #21979
deepdoc/pdf: extend TableBuilder with FinalizeGrid and AttachSpanInfo by @xugangqiang in #21980
Fix: agent session by default should not return dsl by @wangq8 in #21989
Fix: Deleting a pipeline bound to a dataset should not trigger an error when navigating to the file list page of a different dataset. by @cike8899 in #21985
fix(sdk): guard Session._structure_answer against KeyError on non-streaming agent responses by @sandiyochristan in #21933
fix(storage): add Content-MD5 to S3 batch delete requests by @liuzelei in #21877
fix(go): paginate the Anthropic models list by @pcbeingused333 in #21899
fix(chunker): bound the crop page cache by bytes and release pages when a crop task panics by @Xavierando in #21880
refactor(structure): read STRUCT_MAX_CHUNKS_PER_BATCH via common.GetEnvInt by @xugangqiang in #21984
docs: Documentation Updates and UI Alignment by @Yannnnnnny in #21986
fix(nlp): add retrieval prune logic and tests by @zzy1017-crypto in #21627
fix: align version catalog test with EE permissions by @buua436 in #22011
Fix: Dataset file configuration: switching from "pipeline" to "built-in" also triggers an exclamation mark warning. by @cike8899 in #22010
Fix: If the title of an agent operator is too long, it overflows beyond the boundaries of the sheet. by @cike8899 in #22013
fix(web): hide Agent-related content in chat channel connect dialog by @dcc123456 in #22015
Fix: Increase the right-hand margin on the agent share page. by @cike8899 in #22016
Fix: second sort key for memory messages by @Lynn-Inf in #22004
Upgrade office_oxide to v0.1.16 and drop temporary caption/table fixes by @xugangqiang in #21978
refa: remove remaining identity arguments by @buua436 in #22005
fix(es): return error on item-level failures in metadata bulk write by @zzy1017-crypto in #21956
fix(ingestion): preserve PDF sentences across page boundaries by @jay77721 in #21982
refactor(ingestion): consolidate duplicated meta-reader helpers into kccommon by @xugangqiang in #21983
Add Somark VerifyOCRConnection by @fenglingxiansheng in #21927
fix(knowledge-compiler): honor node settings and degrade missing vector mapping by @buua436 in #22026
fix(web): pass through 413/504 responses without a duplicate error toast by @dcc123456 in #22024
fix(core): enforce consistent name and alias length limits by @jay77721 in #22020
fix(parser): preserve Office table cell spans by @jay77721 in #22012
Fix: The model category filter does not change based on the system language, and there is no clear visual indicator to show which item is currently selected. by @cike8899 in #22038
fix(channels): propagate delivery errors without exposing credentials by @6ba3i in #22033
fix(parser): keep the paragraphs of a Markdown blockquote apart by @L4XB in #21347
Fix: The agent operator name is too long, causing the icon to be compressed. by @cike8899 in #22042
feat(doc-generator): render markdown and expose html decorations by @6ba3i in #22040
fix(channels): support WhatsApp gateways through Docker by @6ba3i in #22032
Refactor: restrict page_size max value 100 by @wangq8 in #22036
docs: record name column widening in database change log by @jay77721 in #22030
Feat: Image parsing: DeepDoc is distinguished from other OCR models and is offered as a separate option. by @cike8899 in #22047
Bump Infinity to v0.7.5 by @qinling0210 in #22022
fix(admin): return every user when the list is unpaged by @ccclucky in #21723
docs: add tutorial in quickstart by @Yannnnnnny in #22027
docs：add use cases for common scenarios by @Yannnnnnny in #22054
fix(models): support the MinerU 4.1 Tasks API in ParseMinerUV1 by @ccclucky in #21995
Fix: Align the agent operator title to the left. by @cike8899 in #22051
fix(pregel): preserve slice types during state reduction by @6ba3i in #22014
Add RenderVH dispatch hook to ConstructTable for EE V/H tables by @xugangqiang in #22055
fix: seed user rows in tenant service tests by @buua436 in #22060
Resolve the comments by @wangq8 in #22059
fix: restore harness interrupt resume and events by @buua436 in #22050
refactor(common): move IngestionLog and ingest-log sink out of stub.go by @xugangqiang in #22006
fix(chat): always conjoin the authorized kb_id filter to SQL retrieval by @zzy1017-crypto in #21866
fix(web): harden rename flows and dialog UX by @dcc123456 in #22068
feat(channels): support agent workflows and isolate startup failures by @6ba3i in #22031
Revert "fix(web): hide Agent-related content in chat channel connect dialog" by @wangq8 in #22069
fix(storage): use bounded synchronous MinIO health probes by @liuzelei in #21945
refactor(ingestion): drop Python/migration-history comments from tree sub-package by @xugangqiang in #22008
fix: harden native analyzer conversions and JSON output by @buua436 in #22070
fix: harden agent export, timeout, and artifact handling by @buua436 in #22037
fix: clean agent subgraphs and repair frontend requests by @buua436 in #22048
fix(pregel): propagate conditional edge and branch errors by @6ba3i in #22074
fix(web): use secondary buttons for tenant table actions by @dcc123456 in #22079
fix(agent): preserve Markdown headings and lists in DOCX by @6ba3i in #22078
Docs: Get rid of (optional) by @wangq8 in #22085
feat(parser): add MiniCPM-OCR as a PDF parser by @Caldalis in #21785
add more glm models by @JinHai-CN in #22087
Provision native libs from versioned user cache (offline CI, drop /opt pre-bake) by @xugangqiang in #22023
Fix: handle Vite preload errors with automatic reload by @cike8899 in #22086
fix: resolve template, rerank, and migration regressions by @buua436 in #22083
fix(agent): preserve nested Markdown lists in PDF exports by @6ba3i in #22084
fix: scope upload quotas and lock WeCom listener binding by @buua436 in #22076
fix: harden OAuth, gateway auth, and provider parsing by @buua436 in #22072
Fix: long name error by @wangq8 in #22088
fix(es): prevent Lucene injection in session_id and enforce dataset scope in DeleteChunks by @zzy1017-crypto in #21981
fix(web): truncate overflowing titles in embedded chat headers by @dcc123456 in #22091
fix: prefix agent channel sessions with the chat channel name by @flyingwhit in #22090
feat(chatchannel): stream Feishu, WeCom and DingTalk replies by @flyingwhit in #22041
fix(channels): truncate Telegram and Discord upstream error bodies to 200 bytes by @flyingwhit in #22075
fix(channels): apply saved agent updates to existing conversations by @6ba3i in #22093
Revert "Provision native libs from versioned user cache (offline CI, drop /opt pre-bake)" by @xugangqiang in #22097
fix(web): refresh tenant user list after removing a member by @dcc123456 in #22096
fix(test): fix always-true assertions in reranker normalize test by @zzy1017-crypto in #22039
fix(dataset): sync folder rename in same transaction to prevent binding loss by @zzy1017-crypto in #22021
refactor(ingestion): centralize component names and identity checks by @jay77721 in #22081
fix(deepdoc): preserve missed PDF table rows and merged headers by @jay77721 in #22073
fix(channels): strip citations from outgoing replies by @6ba3i in #22106
fix(syncer): retry startup task publication failures by @6ba3i in #22101
fix: align ChatChannel permission tests by @buua436 in #22107
fix(infinity): decode tag_feas on chunk search reads by @ccclucky in #21782
Release notes 1.0 GA by @wangq8 in #22109
Docs: Update version references to v1.0.0 in READMEs and docs by @asiroliu in #22108
update macos runner to macos-15 for arm64 architecture by @myf-bee in #22110

New Contributors

@adityabatra072 made their first contribution in #21719
@eridan-ltu made their first contribution in #21828
@Zhi-Xiang-Guo made their first contribution in #21809
@fenglingxiansheng made their first contribution in #21710
@GunaPalanivel made their first contribution in #20633
@MoonPointer-Byte made their first contribution in #21766
@Steve-20-ai made their first contribution in #21823
@mmporong made their first contribution in #21503
@jimmyplup made their first contribution in #21818
@superwiboy made their first contribution in #21832
@sandiyochristan made their first contribution in #21933
@liuzelei made their first contribution in #21877
@pcbeingused333 made their first contribution in #21899
@Caldalis made their first contribution in #21785

Full Changelog: v1.0.0-rc3...v1.0.0