infiniflow/ragflow v0.17.1 on GitHub

Summary

Improved parallel performance of document parsing tasks.
Solve the issue of duplicate extraction of knowledge graph.
Improved the quality of English tokenization.
Fixed a series of API call issues.
Fixed the UI display issue of the document parser in the Knowledge Base configuration page.
Solved the problem of previewing images.
Support for parsing XLS (Excel97~2003), and improved error handling mechanism.
Solved the Tavily search bug.
Support Huggingface rerank model.
Support relative time expression for Rewrite operator in Agent.
Updated SiliconFlow model list.
Optimized the table content extraction logic when parsing Markdown document types.

What's Changed

Fix: possible memory leaks close #5277 by @yihong0618 in #5500
Fix email validation regex by @felipehertzer in #5533
Fix: in case running KG repeatly. by @KevinHuSh in #5538
Optimize prompt. by @KevinHuSh in #5541
Feat: Add NextLLMSelect with shadcn-ui. #3221 by @cike8899 in #5542
Fix: bad case for tokenizer. by @KevinHuSh in #5543
Restructured guides by @writinwaters in #5549
Feat: Combine Select and LlmSettingFieldItems into LLMSelect. #3221 by @cike8899 in #5548
Restructured guides by @writinwaters in #5555
Feat: Render RewriteQuestionForm with shadcn-ui #3221 by @cike8899 in #5551
Feat: add 'delete' for agent's sessions api and unify apis of agent sdk by @debugdoctor in #5525
Feat: Render QWeatherForm with shadcn-ui. #3221 by @cike8899 in #5558
Feat: add toc to api doc by @hjlarry in #5552
Made task_executor async to speedup parsing by @yuzhichang in #5530
Feat: Render WikipediaForm and BaiduForm with shadcn-ui. #3221 by @cike8899 in #5564
Minor: Fixed broken links by @writinwaters in #5565
Fix: LLM with ___ return cannot be deleted #5585 by @cike8899 in #5587
Perf: update novita.ai LLM library by @debugdoctor in #5574
Add separate API service resource to Helm chart by @sd109 in #5572
Fix: fix may lose part of information of last stream chunck by @yongtenglei in #5584
Fix: remove KB id restriction while creating chat. by @KevinHuSh in #5588
Introduced jemalloc by @yuzhichang in #5590
Fix nursery.start_soon. Close #5575 by @yuzhichang in #5591
Fix: better start experience PYTHONPATH in shell by @yihong0618 in #5593
Docs: about meta files in API reference. by @KevinHuSh in #5594
Feat: Render MessageForm with shadcn-ui. #3221 by @cike8899 in #5596
Added 0.17.0 release notes by @writinwaters in #5608
Feat: Render DynamicCategorize with shadcn-ui. #3221 by @cike8899 in #5610
Fix：Fix the bug of incorrectly gets the APIToken. by @kunyi-yang in #5597
use to_df replace to_pl when get infinity Result by @dwxiayi in #5604
fix: issue #5600 by @yihong0618 in #5620
Fix: image file can't preview by @hjlarry in #5626
Refactor: Optimize error handling and support parsing of XLS(EXCEL97—2003) files. by @hy89 in #5633
Minor: improve doc and rm unused file by @hjlarry in #5634
Fix: parameter error. by @KevinHuSh in #5641
Refactored DocumentService.update_progress by @yuzhichang in #5642
Feat: Upload file UI/UX enhancements by @Omarlsg98 in #5359
Feat: The parsing method is paper and needs to display Document parser. #5467 by @cike8899 in #5652
fix: issue #5600 by @GuoDapeng in #5645
Fix: tavily search error. by @KevinHuSh in #5653
Fix: search citation issue. by @KevinHuSh in #5657
Docs: updates. by @KevinHuSh in #5661
refactor: no need to inherit in python3 clean the code by @yihong0618 in #5659
Feat: Use react-hook-form to synchronize the data of the categorize form to the agent node. #3221 by @cike8899 in #5665
Miscellaneous updates by @writinwaters in #5670
Feat: support huggingface re-rank model. by @KevinHuSh in #5684
Feat: Add rerank option to huggingface's model type drop-down box. #5658 by @cike8899 in #5689
Minor: improve tips display by @hjlarry in #5631
Refa: remove max tokens since no one needs it. by @KevinHuSh in #5690
Fix: Remove the max token parameter. #5640 #5646 by @cike8899 in #5693
Fix: docs inconsistency. by @KevinHuSh in #5695
Fix: rerank issue. by @KevinHuSh in #5696
Refa: remove dataset language and validate dataset name length. by @KevinHuSh in #5707
Fix: delimiter issue. by @KevinHuSh in #5720
Fix: too long context during KG issue. by @KevinHuSh in #5723
Updated instructions in the UI by @writinwaters in #5733
TEST: Added test cases for Create Dataset HTTP API by @asiroliu in #5724
Fix: Remove the document language parameter. #5640 by @cike8899 in #5728
Fix: empty description by @KevinHuSh in #5747
Fix: can not upload file close #5730 by @yihong0618 in #5742
Fix: API empty field input. by @KevinHuSh in #5748
Fix: Resolve inconsistency in APIToken dialog_id field definition by @zanyatta in #5749
Refa: make Rewrite component effective to relative data expression. by @KevinHuSh in #5752
Fix: add the validation for parser_config. by @KevinHuSh in #5755
Fix: Fixed the issue that files cannot be uploaded on the file management page. #5730 by @cike8899 in #5763
Fix: meta fields updata issue, by @KevinHuSh in #5764
Fix: truncate message issue. by @KevinHuSh in #5765
Feat(api): Add dsl parameters to control whether dsl fields are included by @hy89 in #5769
Feat：Optimize the table extraction logic in the Markdown parser: by @liwenju0 in #5663
Initial draft of Implemnt deep research by @writinwaters in #5774
Fix: truncate message issue. by @KevinHuSh in #5776
TEST: Added test cases for Delete Dataset HTTP API by @asiroliu in #5770
Refa: SiliconFlow model list refresh. by @KevinHuSh in #5825
Fix: empty query issue. by @KevinHuSh in #5830
Feat: When selecting a reordering model, give a prompt that it takes too long. #5834 by @cike8899 in #5835
Refactor graphrag to remove redis lock by @yuzhichang in #5828
Fix: keyword compont display issue #5794 by @cike8899 in #5844
Feat: add sync_dsl parameter to support synchronizing modifications to existing sessions by @hy89 in #5843
TEST: Added test cases for List Dataset HTTP API by @asiroliu in #5856
Agent Update: Fix Role Issue and Enhance KB Search by @zhangcdian in #5842
Feat: Add AvatarGroup component. #3221 by @cike8899 in #5858
Test: Update test cases per PR #5755 by @asiroliu in #5857
Fix: dataset_ids parameter by @RaghavPatidar18 in #5864
Fix: empty dataset parser id. by @KevinHuSh in #5878
Fix: rm for ES sql generation. by @KevinHuSh in #5881
Test: Update test cases per PR #5778 by @asiroliu in #5880
Fix: check desc parameter value. by @KevinHuSh in #5884
Fix: docs updates. by @KevinHuSh in #5889
Refa: add prompt to empty retrieved answwer. by @KevinHuSh in #5892
Test: Update test cases per PR #5748 #5878 by @asiroliu in #5894
Add docs for tag sets by @writinwaters in #5890
UI updates by @writinwaters in #5899
Docs: prepare docs for release v0.17.1 by @KevinHuSh in #5900

New Contributors

@felipehertzer made their first contribution in #5533
@kunyi-yang made their first contribution in #5597
@dwxiayi made their first contribution in #5604
@GuoDapeng made their first contribution in #5645
@asiroliu made their first contribution in #5724
@zanyatta made their first contribution in #5749
@zhangcdian made their first contribution in #5842
@RaghavPatidar18 made their first contribution in #5864

Full Changelog: v0.17.0...v0.17.1