infiniflow/ragflow v0.26.2

on GitHub

Summary

Released on June 29, 2026.

New features

• Chat channels:
  • Integrates WhatsApp via a QR code scan. #16238
  • Integrates DingTalk via bot API credentials. #16183
  • Integrates WeCom via WebSocket connection. #16175
• File parsing: Adds fallback logic for PP-OCRv6 and similar text recognition models, and integrates image parsing within the PaddleOCR pipeline. #16150

Improvements

• Datasets
  • Adds an edge-case check to the file ingestion logic to safely link empty folders to a dataset. #16296
  • Adds pagination to the get_flatted_meta_by_kbs() method to prevent CRUD failures relating to datasets with more than 10,000 documents. #16095
• Chat channels: Ensures end-user conversation histories persist across restarts but still separate when a channel is bound to a new dialog. #16274

i18n

• Expands i18n coverage and refines translations for the Korean UI. #16203；
• Adds missing French translations for chat channels, username validation, and model editing. #16217

Bug fixes

• File parsing:
  • A ValueError was raised during .docx parsing on 'Heading' styles. #16284
  • Tables in .docx files were silently removed by the laws document parser. #16155
  • Lone Markdown headers were separated from their subsequent sections when a DeepDoc delimiter was set. #16109
  • Markdown tables appeared twice in chunk results, once as a standalone chunk and again within a regular text chunk. #16143
• MCP
  • The MCP server hung indefinitely when encountering empty document pages; the final page of documents was silently dropped due to flawed pagination. #16285
  • The MCP connection and dataset discovery process failed because the server's hardcoded fetch limit exceeded the introduced page_size restriction. #16148
• Dataflow
  • Restores the dataflow rerun endpoint and ensures the ingestion response includes the DSL payload to reliably render the timeline and parser views. #16292
  • Restores dataflow parser defaults and returns the actual SSE payload, ensuring pipeline runs correctly surface message IDs and log updates. #16290
• LLM: Failed to use the new gemini-3.5-flash model via the Google Cloud (Vertex AI) provider using eu or us region endpoint. This is resolved by explicitly multi-region routing requests to the required aiplatform.<region>.rep.googleapis.com domains instead of synthesized <region>-aiplatform.googleapis.com hosts. #15990
• UI/UX: The metadata add modal sent empty values to the backend. #15229

What's Changed

• Fix the launch script by @wangq8 in #16159
• Refactor(go-cli): improve variable and label naming in CLI parseAddModel by @Hz-186 in #16145
• Fix Chat/Search/Agent bot show image by @wangq8 in #16152
• Fix: MCP dataset discovery fails due to REST API max page size limit … by @xuhaiL in #16148
• Fix: cli points to the wrong api endpoints by @6ba3i in #16171
• feat(go-api): implement Go-side document PATCH API & align parsing/metadata sync behavior by @Hz-186 in #15975
• feat(go-api): migrate MCP server detail and download API to Go by @Hz-186 in #16113
• feat: support wecom websocket channel by @buua436 in #16175
• Fix: Lint error. by @cike8899 in #16172
• fix: fix some bugs in check_conn and drop_inst by @Haruko386 in #16180
• fix(deepdoc): attach lone header lines to the following section when delimiter is set by @jaso0n0818 in #16109
• Go CLI: add support for windows, linux, macos by @Haruko386 in #16082
• Go: add statistics command by @JinHai-CN in #16119
• Fix search rename error with multiple error message (#664) by @wangq8 in #16186
• Go CLI: add support for windows, linux, macos by @Haruko386 in #16184
• fix: use RESTful pipeline detail API with knowledgeId and logId by @euvre in #16182
• Fix: replace tenant_llm apis by @Lynn-Inf in #16131
• fix: add nightly tags by @Haruko386 in #16189
• Go: add command, show tasks summary by @JinHai-CN in #16187
• fix: chat channel defaults and feishu shutdown by @buua436 in #16176
• fix: wrong clang/toolchain for windows by @Haruko386 in #16191
• Go: add command, list, remove, stop tasks by @JinHai-CN in #16190
• feat[Go]: add modelID for delete_model and update_status by @Haruko386 in #16025
• feat[go]: implement /api/v1/datasets/<dataset_id> PUT by @Haruko386 in #16122
• feat[Go]: implement datasets/<dataset_id>/index P/G by @Haruko386 in #16153
• Json add paddleOCR models by @Haruko386 in #16156
• Implement OpenAI chat completions in GO by @qinling0210 in #16177
• fix: hard-coded paths for Windows C compiler by @Haruko386 in #16193
• Fix that agent cannot be the same name by @wangq8 in #16192
• feat: add dingtalk chat channel by @buua436 in #16183
• Go: fix duplicate models by @JinHai-CN in #16197
• Go CLI: add list user commands framework by @JinHai-CN in #16201
• Go CLI: refactor some commands by @JinHai-CN in #16204
• Go CLI: refactor commands by @JinHai-CN in #16213
• Go CLI: admin list configs by @JinHai-CN in #16221
• Fix: preserve tables when parsing DOCX with the laws parser (#16008) by @manan-tech in #16155
• fix: Enhance Windows build process for office_oxide and rag tokenizer by @Haruko386 in #16223
• feat(agent): align Go agent behavior with Python (except retrieval component) by @yuzhichang in #16225
• fix: Enhance Windows build configuration in release.yml by @Haruko386 in #16227
• Fix: metadata add modal sends empty value due to stale closure by @nickmopen in #15229
• Go CLI: Fix alter role by @JinHai-CN in #16226
• fix: fix release workflow for Windows and MAC builds by @Haruko386 in #16235
• feat[Go]: implement api /api/v1/datasets/<dataset_id>/chunks POST by @Haruko386 in #16067
• fix: unable to chat after set model by @Haruko386 in #16195
• feat(go-api): complete chat channel API migration with tests by @Hz-186 in #16139
• feat(go-api): Implement BulkDeleteChats Go API and fix ListChats by @Hz-186 in #16157
• feat(go-api): migrate searchbot share detail endpoint to go by @Hz-186 in #16124
• Add show / set role default models by @JinHai-CN in #16240
• Feat: Add a prefix to the name of the FormField associated with the chat. by @cike8899 in #16178
• i18n(fr): add missing French translations for chat channels, username validation and model editing by @vincentlambert in #16217
• test(go): ensure go unit tests pass by @yuzhichang in #16241
• Go CLI: admin list providers by @JinHai-CN in #16243
• fix: handle SIMDe headers installation for arm64 by @Haruko386 in #16244
• Fix: When re-entering the agent page, the data from the previous session flashes briefly. by @cike8899 in #16251
• fix: propagate contextvars through thread_pool_exec by @vincentlambert in #16247
• refactor(log): unify Go logging to zap with rotation, strip per-package levels by @yuzhichang in #16261
• Go CLI: admin model framework by @JinHai-CN in #16252
• Go: default public key by @JinHai-CN in #16265
• feat: add whatsapp web qr chat channel by @buua436 in #16238
• Fix: add /v1/document/upload_info -> /api/v1/documents/upload back by @wangq8 in #16264
• Go CLI: add response output by @myf-bee in #16263
• feat[Go]: implement <document_id>/chunks/<chunk_id> PATCH by @Haruko386 in #16232
• feat[Go]: implement /datasets/<dataset_id>/documents/batch-update-status by @Haruko386 in #16258
• Document[Go-develop]: update Go development docs by @Haruko386 in #16229
• Go: rename ragflow_cli to ragflow-cli by @JinHai-CN in #16270
• Go: show model and list all models by @JinHai-CN in #16272
• Refactor harness framework by @yingfeng in #16271
• fix(rag/raptor): handle max_cluster edge case in GMM cluster selection by @Harsh23Kashyap in #16199
• fix(paddleocr): support PP-OCRv6 ocrResults fallback and integrate image parsing by @Rander7 in #16150
• Fix release by @JinHai-CN in #16278
• fix(i18n): fix missing i18n coverage and refine Korean translations by @yooxdb in #16203
• fix: support Google Cloud Gemini eu/us multipoint endpoints by @glu000 in #15990
• fix: restore dataflow defaults and SSE response by @buua436 in #16290
• fix: keep chat channel bindings consistent by @buua436 in #16274
• fix: guard against missing component IDs in Switch Flow path to prevent NoneType crash by @OSHA-B in #16279
• fix: restore dataflow rerun and detail payload by @buua436 in #16292
• fix(document_service): prevent NoneType error on progress_msg.strip() by @Dimon0000000 in #16289
• Fix: MCP document metadata cache can loop forever when documents returns an empty docs page by @minion1227 in #16285
• Fix: docx parsing raises ValueError on 'Heading' styles by @minion1227 in #16284
• Fix: paginate get_flatted_meta_by_kbs to support datasets with >10k documents (#16034) by @Dr1985 in #16095
• fix: deduplicate markdown table chunks by @helloxjade in #16143
• Fix: handle empty folder when link to datasets by @wangq8 in #16296
• fix(agent): handle different reference data formats by @Ambercssa in #16276
• Go CLI: fix mode switch by @JinHai-CN in #16294
• Fix: guess volc embedding model by @Lynn-Inf in #16298
• fix(api): use dataset-owner tenant for legacy /chunks docstore cleanup by @kiannidev in #15961
• feat(go-api): migrate datasets tags aggregation API to Go by @Hz-186 in #16181
• feat[Go] implement datasets/<dataset_id>/<index_type> DELETE by @Haruko386 in #16257
• feat(go-api): Align document metadata batch APIs and upload_info with Python by @Hz-186 in #16269
• fix(go): normalizeDatasetID by @Hz-186 in #16301
• Go CLI: refactor by @JinHai-CN in #16299
• feat(go-api): add dataset tags endpoints by @Hz-186 in #16231
• feat(go-api): align chat session get/update with python behavior by @Hz-186 in #16239
• Go CLI: fix key commands by @JinHai-CN in #16306
• fix: new dataset can not update configuration by @Haruko386 in #16291
• implement: <dataset_id>/embedding/check POST by @Haruko386 in #16266
• feat[go]: datasets/<dataset_id>/chunks DELETE by @Haruko386 in #16185
• More resilient graph engine by @yingfeng in #16325
• Go CLI: list provider instance models, sync and list provider by @JinHai-CN in #16311
• Example: list_datasets.sh by @JinHai-CN in #16335
• Add Keenable web search tool to the agent by @ilya-bogin-keenable in #16233
• Fix when empty response not set, it report: ERROR: 'knowledge' by @wangq8 in #16338
• feat: unify provider id or name routing by @buua436 in #16336
• fix(agent): log Wikipedia disambiguation and page errors instead of s… by @Willsgao in #16207
• feat(go-api): add dataset search endpoint by @Hz-186 in #16304
• feat(go-api): implement dataset document upload API by @Hz-186 in #16295
• Go CLI: fix list dataset files by dataset name by @JinHai-CN in #16341
• fix(web): agent log refetch and slider percentage rounding by @dcc123456 in #16344
• feat(go-api): add Go support for POST /api/v1/datasets/{dataset_id}/documents/{document_id}/chunks by @Hz-186 in #16256
• fix(agent): coerce None Switch inputs before string operators by @Harsh23Kashyap in #16320
• fix(agent/tools): PubMed tool always returns "Unknown Authors" by @immuhammadfurqan in #16330
• Fix multimodal chat image routing for VLM channel requests by @6ba3i in #16343
• fix(web): bump lodash past vulnerable range by @Harsh23Kashyap in #16281
• fix(agent/tools): DeepL component fails validation and drops errors by @immuhammadfurqan in #16332
• Fix: Flexible Chat Configuration by @cike8899 in #16293
• Go CLI: fix list provider instance tasks by @JinHai-CN in #16345
• fix(html_parser): preserve original text when splitting oversized blocks by @devYRPauli in #16052
• Go:CLI add new response function by @myf-bee in #16347
• Add env ALLOW_ANY_HOST to skip host check by @wangq8 in #16351
• Fix add VLLM without apikey will fail by @wangq8 in #16352
• Fix [ID:0] not converted to Fig. 1 by @wangq8 in #16357
• Fix: An empty message notification pops up at the top of the agent conversation. by @cike8899 in #16353
• fix(api): align use_sql Markdown separator with Source header by @Harsh23Kashyap in #16317
• feat[Go]: implemet api: Search/Get/Update-Messages by @Haruko386 in #16307
• feat[go]: add router for connectors/<connector_id> PATCH by @Haruko386 in #16358
• fix(deepdoc): keep zero and false Excel cells in call by @Harsh23Kashyap in #16318
• fix: naive_merge splits oversized sections and counts overlap tokens correctly by @cleanjunc in #15802
• fix(web): fix layout issues with text, overflow, and spacing consistency by @yooxdb in #16324
• feat(go-api): Langfuse API key migration behavior by @Hz-186 in #16356
• fix(deepdoc): accept GFM table separators with one or more dashes by @Harsh23Kashyap in #16319
• fix(api): validate immutable document fields when value is zero by @Harsh23Kashyap in #16309
• Revert "fix(deepdoc): keep zero and false Excel cells in call" by @wangq8 in #16366
• fix(rag/nlp): treat string input as one phrase in is_english by @Harsh23Kashyap in #16308
• Refactor: migrate pdf_parser.py to golang by @xugangqiang in #16323
• Go CLI: refactor by @JinHai-CN in #16355
• Go CLI: fix model related commands by @JinHai-CN in #16368
• fix(excel_parser): keep zero-valued cells when building Excel text chunks by @devYRPauli in #16287
• Fix: remove deepdoc dep by @xugangqiang in #16372
• Model config: add tools by @JinHai-CN in #16371
• Go CLI: fix show variable by @JinHai-CN in #16370
• Docs: Added v0.26.2 release notes. by @writinwaters in #16373
• feat: add missing qwen models to all_models.json by @Hz-186 in #16379
• Go CLI: Fix show model and list models by @JinHai-CN in #16380
• Fix missing move and copy methods in Python RAGFlowS3 storage implementation by @ondery in #16350
• Fix document progress not set to fail when embedding model error by @wangq8 in #16381
• feat: add log icon to parsing status display by @dcc123456 in #16383
• fix: tighten loop validation by @buua436 in #16374
• Feat: support new qwen model by @Lynn-Inf in #16385
• Fix: If the type of the loop variable in the Loop operator is set to object, an error occurs when clicking the Variable Replicator operator inside it. by @cike8899 in #16388
• Fix handle move file failed by @wangq8 in #16384
• fix: adjust table height and button position in DatasetTable component by @dcc123456 in #16390
• Feat: Add New API model provider for OpenAI-compatible gateways by @wanghualoong in #15991
• Go CLI: Fix show admin server and api server by @JinHai-CN in #16382
• feat[Go]: implement Add messages for Go by @Haruko386 in #16375
• feat(go-api): add chat update endpoints by @Hz-186 in #16378
• feat[Go]: implement Create-Chat/Session, Delete-Session by @Haruko386 in #16386
• Fix VLM PDF parser only parse first 12 pages, and default page range for PDF files align with backend by @wangq8 in #16394
• fix: remove dup-method by @Haruko386 in #16393

New Contributors

• @xuhaiL made their first contribution in #16148
• @manan-tech made their first contribution in #16155
• @OSHA-B made their first contribution in #16279
• @minion1227 made their first contribution in #16285
• @helloxjade made their first contribution in #16143
• @Ambercssa made their first contribution in #16276
• @ilya-bogin-keenable made their first contribution in #16233
• @immuhammadfurqan made their first contribution in #16330
• @ondery made their first contribution in #16350

Full Changelog: v0.26.1...v0.26.2