RAGFlow Files

1.0.0-rc3 is the third and final release candidate before the official v1.0.0 release. It fixes several issues found in rc2 and introduces new features and enhancements.

Key updates:

1. Introduced the decision model for evidence sufficiency judgment within the agentic tool loop, and the Categorize component for agents.
2. Added support for multiple versions of ingestion pipeline DSL.
3. Chat history now stores and displays prompts, token usage, and execution time.
4. Compatible with existing v1.0.0-rc2 schema, allowing a direct upgrade.

What's Changed

• Fix: An additional retrieval node has appeared in the agent created using the CAJAL Scientific Paper Assistant template. by @cike8899 in https://github.com/infiniflow/ragflow/pull/21079
• fix(agent): preserve and resolve webhook header fields by @T1mn in https://github.com/infiniflow/ragflow/pull/20696
• fix(agent): migrate chunk_summary and title_chunker templates to modular Extractor params by @12britz in https://github.com/infiniflow/ragflow/pull/20754
• fix(s3): honor signature_version and addressing_style for S3-compatible stores by @yaoper in https://github.com/infiniflow/ragflow/pull/20815
• fix(agent): retain webhook completion across incremental polls by @T1mn in https://github.com/infiniflow/ragflow/pull/20697
• fix(mcp): return a private cacheScope from tools/list by @leilei3167 in https://github.com/infiniflow/ragflow/pull/20539
• Fix: The quoted content in agent messages is not displayed correctly. by @cike8899 in https://github.com/infiniflow/ragflow/pull/21070
• fix: use id and kb_id when deleting dataset metadata by @aniketkrs in https://github.com/infiniflow/ragflow/pull/20880
• feat(go): complete the Mistral /v1/ocr client and list mistral-ocr-latest as an ocr model by @Xavierando in https://github.com/infiniflow/ragflow/pull/20531
• fix: expose compile_kwd in dataset search results by @liang0417 in https://github.com/infiniflow/ragflow/pull/20859
• fix(chunker): keep structured tables and images in the title family by @jay77721 in https://github.com/infiniflow/ragflow/pull/21040
• Fix: Error related to the 'UserFillUpForm' type by @cike8899 in https://github.com/infiniflow/ragflow/pull/21062
• Test:migrate router contracts api by @flyingwhit in https://github.com/infiniflow/ragflow/pull/21046
• Test:migrate langfuse routes api by @flyingwhit in https://github.com/infiniflow/ragflow/pull/21050
• fix(metadata): preserve string arrays in in-memory filters by @QAQadws in https://github.com/infiniflow/ragflow/pull/21065
• ci(tests): run migrated Go API tests by @6ba3i in https://github.com/infiniflow/ragflow/pull/21077
• Support jev model interface, part1 by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21087
• fix(kvrocks): propagate SetNX errors by @eleven914 in https://github.com/infiniflow/ragflow/pull/20746
• refactor(parser): introduce typed Position API for DocItem positions by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21049
• Remove RowsToHTML; render PDF tables via canonical RenderTableHTML by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21083
• feat(parser): extract SVG text in Go picture ingestion by @errmakov in https://github.com/infiniflow/ragflow/pull/20523
• fix(agent): bound the self-managed error body drain by @Tong-bit-art in https://github.com/infiniflow/ragflow/pull/21058
• test(api): migrate and improve search API tests, make the Go API suite self-sufficient by @qinling0210 in https://github.com/infiniflow/ragflow/pull/21086
• fix(ingestion): document and validate extractor timeout env by @jay77721 in https://github.com/infiniflow/ragflow/pull/21119
• Add more server types by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21127
• feat: migrate permission schema fields by @buua436 in https://github.com/infiniflow/ragflow/pull/21085
• Add token usage for agentic rag by @yingfeng in https://github.com/infiniflow/ragflow/pull/21134
• feat(pipeline): support image and email in general template by @jay77721 in https://github.com/infiniflow/ragflow/pull/21072
• fix(harness): recognize retryable errors beyond string prefixes by @SiyuanChenToDo in https://github.com/infiniflow/ragflow/pull/21114
• fix(parser): write an email's text output in a fixed field order by @L4XB in https://github.com/infiniflow/ragflow/pull/21100
• fix: release , aliyun Personal ACR does not support image proof lists by @myf-bee in https://github.com/infiniflow/ragflow/pull/21136
• Go: update admin client by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21135
• fix(parser): keep JSON numbers and <, >, & as written in JSON items by @L4XB in https://github.com/infiniflow/ragflow/pull/21101
• test(nlp): stop copying the atomic lookupNum in synonym tests by @12britz in https://github.com/infiniflow/ragflow/pull/21102
• refactor(ingestion): pipeline cleanups by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21084
• fix(parser): decode numeric and all named character references in EPUB text by @L4XB in https://github.com/infiniflow/ragflow/pull/21103
• fix(web): defer retrieval document search until selection settles by @dcc123456 in https://github.com/infiniflow/ragflow/pull/21144
• fix(go-models): unwrap bundled api_key for Azure OpenAI by @errmakov in https://github.com/infiniflow/ragflow/pull/20354
• feat(go-auth): bind tenant context to access tokens and API keys by @buua436 in https://github.com/infiniflow/ragflow/pull/21153
• release: move release workflow from self-hosts to github runner hosts by @myf-bee in https://github.com/infiniflow/ragflow/pull/21155
• Fix template integration tests for typed parser DocItem output by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21141
• refactor(ingestion): cleanup — stdlib reuse and shared component names by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21149
• feat(parser): allow tenant PaddleOCR selection for images by @ZXLyyds100 in https://github.com/infiniflow/ragflow/pull/21113
• fix(parser): read text and inline elements under as one item by @L4XB in https://github.com/infiniflow/ragflow/pull/21108
• docs： Add a Tongyi-Qianwen Base URL reminder to the upgrade guide. by @Yannnnnnny in https://github.com/infiniflow/ragflow/pull/21166
• feat: add TrustedRouter as a model provider by @jperla in https://github.com/infiniflow/ragflow/pull/21105
• refactor(mcp): move MCP client out of utility into internal/mcp/client by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21150
• Fix claim/evidence usage in agentic RAG by @yingfeng in https://github.com/infiniflow/ragflow/pull/21170
• Test: migrate files api by @flyingwhit in https://github.com/infiniflow/ragflow/pull/21054
• fix(web): correct PaddleOCR provider links to AI Studio by @jay77721 in https://github.com/infiniflow/ragflow/pull/21196
• fix(parser): start a new line before every HTML block element by @L4XB in https://github.com/infiniflow/ragflow/pull/21107
• feat(parser): honor MinerU formula and table controls by @ZXLyyds100 in https://github.com/infiniflow/ragflow/pull/21109
• fix(deepdoc): sample English pages deterministically by @leilei3167 in https://github.com/infiniflow/ragflow/pull/20689
• fix(ingestion): port Python's table-tag strip to the tokenizer embedding path by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21156
• Extract shared storage layer: s3Base + retry/move helpers by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21158
• fix(agent/tool): compare hostnames case-insensitively in DoPinned guard by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21171
• fix(api): return nonempty string response messages by @QAQadws in https://github.com/infiniflow/ragflow/pull/21194
• fix(chunker): group DOCX paragraphs into custom-delimiter records by @Souravrajvi0 in https://github.com/infiniflow/ragflow/pull/20713
• Fix(deps): use onnxruntime-v1.29.0-patch2 to restore Clip@13 in minimal ORT by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21051
• feat(parser): add per-method external DeepDoc analyzer dispatch by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21182
• fix(parser): emit DOC tables as structured items instead of plain text by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21201
• fix(parser): caption DOCX tables with their heading hierarchy by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21202
• fix(parser): use selected tenant SoMark and OpenDataLoader instances by @ZXLyyds100 in https://github.com/infiniflow/ragflow/pull/21112
• feat: add EmpirioLabs AI as a model provider by @Adam-Dalloul in https://github.com/infiniflow/ragflow/pull/21192
• Get server type in boostrap by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21204
• rename job release to publish_sdk by @myf-bee in https://github.com/infiniflow/ragflow/pull/21208
• feat: add AI Stupid Level as a model provider by @StudioPlatforms in https://github.com/infiniflow/ragflow/pull/21185
• Add server type to StartServer function as parameter by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21219
• fix(parser): preserve PaddleOCR PDF highlight positions by @jay77721 in https://github.com/infiniflow/ragflow/pull/21205
• feat(agentic-rag): support per-chat prompts and tool selection by @6ba3i in https://github.com/infiniflow/ragflow/pull/21211
• fix(parser): merge .doc header-row table fragments split by office_oxide by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21222
• refactor(ingestion): converge global singletons into injected dependencies by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21203
• fix(ingestion): migrate composite PaddleOCR layout selectors by @jay77721 in https://github.com/infiniflow/ragflow/pull/21236
• Refactor: turn on local as last by @wangq8 in https://github.com/infiniflow/ragflow/pull/21238
• CLI: add show quota by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21243
• refactor(admin): isolate user agent and dataset listings in EE files by @QAQadws in https://github.com/infiniflow/ragflow/pull/21210
• refactor(memory): inject MQ engine into memory publish path by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21244
• fix(retrieval): drop the filter-only fallback by @qinling0210 in https://github.com/infiniflow/ragflow/pull/21240
• Feat: Remove the execution restrictions imposed when an agent fails the checklist validation. by @cike8899 in https://github.com/infiniflow/ragflow/pull/21232
• Fix: Some files in the agent directory are triggering tsc errors. by @cike8899 in https://github.com/infiniflow/ragflow/pull/21212
• fix(agent): render fenced Markdown tables in PDFs by @6ba3i in https://github.com/infiniflow/ragflow/pull/21248
• feat(models): add Radeon Cloud provider for GO by @6ba3i in https://github.com/infiniflow/ragflow/pull/21163
• feat(tenant): add tenant roles and permissions by @buua436 in https://github.com/infiniflow/ragflow/pull/21257
• EE: add function toggle by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21262
• fix(knowledge_compile): widen backlog columns to LONGTEXT by @lorenzozanee in https://github.com/infiniflow/ragflow/pull/20855
• update heartbeat message by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21269
• fix(agent): accept typed slices in ListOperations by @6ba3i in https://github.com/infiniflow/ragflow/pull/21252
• fix(admin): honor ADMIN_DEFAULT_PASSWORD for the first superuser by @leilei3167 in https://github.com/infiniflow/ragflow/pull/20562
• refactor(pipeline): remove dead output_format from ingestion templates by @jay77721 in https://github.com/infiniflow/ragflow/pull/21266
• fix(agent): Render Markdown tables in DOCX exports by @6ba3i in https://github.com/infiniflow/ragflow/pull/21274
• docs: restructure the admin docs to make it more user friendly by @Yannnnnnny in https://github.com/infiniflow/ragflow/pull/21279
• fix(models): restore gpustack rerank and audio support by @gitlawr in https://github.com/infiniflow/ragflow/pull/21233
• fix services stale clean by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21277
• feat(models): add New API model driver by @wanghualoong in https://github.com/infiniflow/ragflow/pull/21226
• fix(parser): break EPUB text at the end of every block element by @L4XB in https://github.com/infiniflow/ragflow/pull/21104
• feat(utility): route WPS private formats to existing office parsers by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21251
• Fix: knowledge compilation skip writting extra field by @wangq8 in https://github.com/infiniflow/ragflow/pull/21278
• fix(ingestion): block video parse while keeping visual upload routing by @jay77721 in https://github.com/infiniflow/ragflow/pull/21245
• Feat: Display both "naive" and "agentic" configurations on the chat settings page. by @cike8899 in https://github.com/infiniflow/ragflow/pull/21285
• refactor(deepdoc): make model filenames, threshold, and post-processing overridable at runtime by @xugangqiang in https://github.com/infiniflow/ragflow/pull/21275
• Fix: 1. update document parser_config does not clean chunks, 2. after update, pop up dialog to notice use to re-parse by @wangq8 in https://github.com/infiniflow/ragflow/pull/21281
• fix server list issue by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21288
• refactor(ingestion): retire ck_type in favor of layout and doc_type by @jay77721 in https://github.com/infiniflow/ragflow/pull/21259
• feat(decision-model): configure the retrieval judge from the UI and cap run cost by @Caobaining1 in https://github.com/infiniflow/ragflow/pull/21250
• refactor(parser): unify PDF JSON post-processing by @jay77721 in https://github.com/infiniflow/ragflow/pull/21228
• fix(cli): send the dataset_id filter and guard the memory lookup type assertion by @lemonzoey in https://github.com/infiniflow/ragflow/pull/21193
• fix(chunker): preserve list-form PDF positions in title chunkers by @jay77721 in https://github.com/infiniflow/ragflow/pull/21258
• Fix: parse api_key and group_id in Minimax config by @Lynn-Inf in https://github.com/infiniflow/ragflow/pull/21289
• Fix: The names of custom pipelines should be displayed as in the original text. by @cike8899 in https://github.com/infiniflow/ragflow/pull/21300
• fix(parser): normalize inline image base64 before chunk upload by @jay77721 in https://github.com/infiniflow/ragflow/pull/21286
• docs: update admin docs with latest release by @Yannnnnnny in https://github.com/infiniflow/ragflow/pull/21302
• fix(agentic-rag): deliver the final answer after a budget stop by @Caobaining1 in https://github.com/infiniflow/ragflow/pull/21301
• fix(agent): fall through when a Switch numeric comparison cannot parse by @RerankerGuo in https://github.com/infiniflow/ragflow/pull/21094
• fix(meta): keep an empty auto meta filter unscoped instead of matching nothing by @martincivan in https://github.com/infiniflow/ragflow/pull/20979
• fix(infinity): treat dropping a missing table as a no-op by @bharadwaj-pendyala in https://github.com/infiniflow/ragflow/pull/20512
• refactor(ingestion): remove all ck_type tombstones by @jay77721 in https://github.com/infiniflow/ragflow/pull/21317
• fix(parser): leave out the content of <template>