nightly

Release nightly created from 3571270 at 2025-03-12 21:10:56+08:00

v0.17.1

Improvements

• Improves English tokenization quality.
• Improves the table extraction logic in Markdown document parsing.
• Updates SiliconFlow's model list.
• Supports parsing XLS files (Excel97~2003) with improved corresponding error handling.
• Supports Huggingface rerank models.
• Enables relative time expressions ("now", "yesterday", "last week", "next year", and more) in the Rewrite agent component.

Fixed issues

• A repetitive knowledge graph extraction issue.
• Issues with API calling.
• Options in the Document parser dropdown are missing.
• A Tavily web search issue.
• Unable to preview diagrams or images in an AI chat.

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 https://github.com/infiniflow/ra...

v0.17.0

Summary

• AI chat: Implements Deep Research for agentic reasoning. To activate this, enable the Reasoning toggle under the Prompt Engine tab of your chat assistant dialogue.
• AI chat: Leverages Tavily-based web search to enhance contexts in agentic reasoning. To activate this, enter the correct Tavily API key under the Assistant Setting tab of your chat assistant dialogue.
• AI chat: Supports initiating a chat without specifying knowledge bases.
• AI chat: HTML files can also be previewed and referenced, in addition to PDF files.
• Dataset: Adds a Document parser dropdown menu to dataset configurations. This includes a DeepDoc model option, which is time-consuming, a much faster naive option (plain text), which skips DLR (Document Layout Recognition), OCR (Optimal Character Recognition), and TSR (Table Structure Recognition) tasks, and several currently experimental large model options.
• Agent component: (x) or a forward slash / can be used to insert available keys (variables) in the system prompt field of the Generate or Template component.
• Object storage: Supports using Aliyun OSS (Object Storage Service) as a file storage option.
• Models: Updates the supported model list for Tongyi-Qianwen, adding DeepSeek-specific models; adds ModelScope as a model provider.
• APIs: Document metadata can be updated through an API.

What's Changed

• More models for siliconflow. by @KevinHuSh in #4756
• Config chat share by @isthaison in #4700
• Fix Gemini chat issue. by @KevinHuSh in #4757
• optimize TenantLLMService.increase_usage for "can't update token usag… by @DavidSche in #4755
• Refresh Gemini model list. by @KevinHuSh in #4780
• Add a comment to valkey. by @KevinHuSh in #4783
• Fix divided by zero issue. by @KevinHuSh in #4784
• Increase ES update script length. by @KevinHuSh in #4785
• Fix: The requested interface timeout will cause the page to crash #4787 by @cike8899 in #4788
• Inner prompt parameter setting. by @KevinHuSh in #4806
• Feat: Add VariablePickerMenuPlugin to select variables in the prompt text box by menu #4764 by @cike8899 in #4765
• Feat: Fixed the issue where the prompt always displayed the initial value when switching between different generate operators #4764 by @cike8899 in #4808
• Feat: Remove begin's width from agent templates #4764 by @cike8899 in #4809
• Fix KG circle. by @KevinHuSh in #4823
• Fix: Fail to open console with Firefox #4816 by @cike8899 in #4838
• Reformat error message. by @KevinHuSh in #4829
• Feat: Modify the Preset configurations item style to distinguish it from other fields #4844 by @cike8899 in #4845
• Added a release notes by @writinwaters in #4848
• Feat: Add ChatCard #3221 by @cike8899 in #4852
• Make the update script shorter. by @KevinHuSh in #4854
• Feat: Add Sessions component #3221 by @cike8899 in #4865
• fix categorize agent input content not format error by @WANGRUI-ZB in #4842
• Feat: Add ChatBasicSetting component #3221 by @cike8899 in #4876
• Feat: Add hatPromptEngine component #3221 by @cike8899 in #4881
• Fix: Knowledge base page crashes when network connection is lost. #4894 by @cike8899 in #4895
• Changed elasticsearch image url by @yuzhichang in #4897
• fix: big xls file error by @SkyfireWXY in #4859
• Remove use of eval() from operators.py by @panzi in #4888
• Fix xinference chat role order issue. by @KevinHuSh in #4898
• Remove use of eval() from search.py by @panzi in #4887
• Display thinking for deepseek r1 by @KevinHuSh in #4904
• Feat: Add LlmSettingFieldItems component #3221 by @cike8899 in #4906
• Fix: After deleting all conversation lists, the chat input box can still be used for input. #4907 by @cike8899 in #4909
• Organized and add a list of large language models of Nvidia.v1.1 by @DiamondPoirier in #4910
• Add a list of large language models of deepseek and image2text models… by @DiamondPoirier in #4914
• Feat: Add ChatInput component #3221 by @cike8899 in #4915
• Fix DB assistant template error. by @KevinHuSh in #4925
• Feat: Display Think for Deepseek R1 model #4903 by @cike8899 in #4930
• Added a guide on setting metadata by @writinwaters in #4935
• Feat: Bind data to datasets page #3221 by @cike8899 in #4938
• Fixes KeyError: 'content' when using stream=False by @Peterson047 in #4944
• Feat: Add an id to the dataset testing route #3221 by @cike8899 in #4951
• Ignore tenant not found error while increasing token usage. by @KevinHuSh in #4950
• Fix hit cache error while raptoring. by @KevinHuSh in #4955
• format number float by @isthaison in #4954
• Feat: Jump from the chunk page to the dataset page #3221 by @cike8899 in #4961
• add gemini-2.0-flash-thinking-exp-01-21 by @isthaison in #4957
• Feat: Add ParsedPageCard component #3221 by @cike8899 in #4976
• Feat: Add background color to GraphRag configuration #4980 by @cike8899 in #4981
• Added PEP 723 metadata to download_deps.py by @yuzhichang in #4988
• Fix in keywords or question auto-generations. by @KevinHuSh in #5021
• Fix knowledge graph node not found (#4968) by @zhxlp in #4970
• Fix keyerror issue while rebuilding graph. by @KevinHuSh in #5022
• Optimize conversation when uploading attachments by @kuschzzp in #4964
• Feat: add LLM provider PPIO by @saikidev in #5013
• Fix window size of ES issue. by @KevinHuSh in #5026
• Rewrite Support specified language or language according to initial question by @isthaison in #4990
• Remove for KG extraction. by @KevinHuSh in #5027
• Fix: Cannot distinguish between export and import icons #5025 by @cike8899 in #5031
• Ignore exception of empty index. by @KevinHuSh in #5030
• Add another decrypt function. by @KevinHuSh in #5043
• Feat: Replace next-login-bg.svg #3221 by @cike8899 in #5046
• Fix: Starting the source code on Windows, the 'HTTP API' returns 404 by @hy89 in #5042
• Ignore exceptions when no index ahead. by @KevinHuSh in #5047
• Update agent session API, to support uploading files while create a new session by @flygithub in #5039
• update locale vi by @isthaison in #5035
• Specify img2text model by tag by @hrchu in #5063
• Remove for exeSql component. by @KevinHuSh in #5069
• add option Embed into webpage by @isthaison in #5065
• Added a graphrag guide by @writinwaters in #4978
• Fix: The max tokens defined by the tenant are not used (#4297) (#2817) by @zhxlp in #5066
• Feat: Add LanguageAbbreviation to simplify language resource files. #5065 by @cike8899 in #5072
• Feat: Extract the common parts of groupImage2TextOptions and groupOptionsByModelType #5063 by @cike8899 in #5074
• Fix: Chunk problem tag content cannot be displayed completely. #5076 by @cike8899 in #5077
• Feat: Add ChunkedResultPanel #3221 by @cike8899 in #5085
• Added an FAQ by @writinwaters in https://github.com/i...

v0.16.0

Summary

• Updated model list to support DeepSeek R1 and DeepSeek V3, available on both DeepSeek and SiliconFlow
• GraphRAG enhancements and refactoring: Support KG maintenance over the whole knowledge base dynamically; Support Light and General working mode---entity deduplication and community detection become optional.
• Support for Tagging to improve search quality. You can maintain the tags, and tag the chunks of other knowledge bases, to improve the search relevance.
• Support Iterator operator in Agent.
• Support Research Report Generator in Agent.
• Support for customizing the metadata of chunks, enhancing chunk prompts.
• Support for GPU acceleration on DeepDoc.
• Added support for Portuguese.
• Bump Infinity to 0.6.0.dev3.

What's Changed

• Fix: Q&A chunk modification by @cike8899 in #4227
• Miscellaneous updates by @writinwaters in #4228
• Fix component input error. by @KevinHuSh in #4231
• Removing invisible chars before tokenization. by @KevinHuSh in #4233
• Update version info by @JinHai-CN in #4232
• Fixed invoke component parameters #4236 by @gegef2009 in #4237
• Fix bugs by @JinHai-CN in #4241
• Fix text by @JinHai-CN in #4244
• Replace image2text model check with internal image. by @KevinHuSh in #4250
• Update UI text by @JinHai-CN in #4248
• Feat: Add the iteration Node #4242 by @cike8899 in #4247
• Add iteration for agent. by @KevinHuSh in #4258
• Clean query. by @KevinHuSh in #4259
• Feat: Limit the iteration start node to only be the source node #4242 by @cike8899 in #4260
• Fix Python SDK example error. by @KevinHuSh in #4262
• Fix Python SDK example error. by @KevinHuSh in #4263
• Fix: The edit box for the headers parameter of the invoke operator is always loading. #4265 by @cike8899 in #4266
• Feat: Delete useless code #4242 by @cike8899 in #4267
• Fix chat listing error. by @KevinHuSh in #4270
• Update text2sql agent manual document (#4226) by @TeslaZY in #4271
• Initial draft of the begin component reference by @writinwaters in #4272
• Fix some bugs in text2sql.(#4279)(#4281) by @TeslaZY in #4280
• Fix BaiduFanyi TestRun parameter validation and debug method missing … by @WANGRUI-ZB in #4275
• Feat: Translate the system prompt of the generate operator #3993 by @cike8899 in #4283
• Fix agent session list by user_id. by @KevinHuSh in #4285
• Fix the bug in create_dataset function by @Feiue in #4284
• Feat: The Begin and IterationStart operators cannot be deleted using shortcut keys #4287 by @cike8899 in #4288
• Fix: After executing npm i --force locally, the login page cannot be opened #4290 by @cike8899 in #4292
• Code refactor. by @KevinHuSh in #4291
• Fix bugs in chunk api by @Feiue in #4293
• Add top_k for create_chat and update_chat api by @Feiue in #4294
• Refactor by @KevinHuSh in #4303
• Support OpenAI gpt-4o and gpt-4o-mini for img2text by @hrchu in #4300
• Update error message for agent name conflict by @Feiue in #4299
• Show the errors out. by @KevinHuSh in #4305
• Fix: Fixed the issue that the graph could not display the grouping #4180 by @cike8899 in #4306
• Update displayed_name to display_name by @Feiue in #4311
• Fix parameter name error. by @KevinHuSh in #4312
• Feat: Add DatasetCreatingDialog #3221 by @cike8899 in #4313
• Update exesql component for agent by @Feiue in #4307
• Synchronize with enterprise version by @yingfeng in #4325
• Feat: Add FileUploadDialog #3221 by @cike8899 in #4327
• Fix agent_completion bug by @Feiue in #4329
• Fix t_recognizer.py after model updating. by @KevinHuSh in #4330
• Feat: Add model id to ExeSql operator form. #1739 by @cike8899 in #4333
• Fix potential SSRF attack vulnerability by @Feiue in #4334
• Feat: Add FileUploadDialog #3221 (#4327) by @cike8899 in #4335
• Fix total number error. by @KevinHuSh in #4339
• chrome extensions by @isthaison in #4308
• Refactor model list. by @KevinHuSh in #4346
• Improve storage engine by @KennyDizi in #4341
• Adds a research report generator. by @KevinHuSh in #4354
• Fix param error. by @KevinHuSh in #4355
• Fix gemini embedding error. by @KevinHuSh in #4356
• Updated outdated descriptions and added multi-turn optimization by @writinwaters in #4362
• Use LTS polars to resolve some machines don't support AVX CPU flag by @JinHai-CN in #4364
• Feat: Add TagTable #4367 by @cike8899 in #4368
• Added instructions on embedding agent or assistant into a third-party webpage by @writinwaters in #4369
• Refine DB assistant template. by @KevinHuSh in #4383
• Feat: Add LoadingButton #4368 by @cike8899 in #4384
• Fix t_recognizer issue. by @KevinHuSh in #4387
• Refine variable display name. by @KevinHuSh in #4397
• Feat: Add TagWorkCloud #4368 by @cike8899 in #4393
• fix bug, agent invoke can not get params from begin by @WANGRUI-ZB in #4390
• [Fix] fix duckduck go search 202 ratelimit failed by @gegef2009 in #4398
• Fix page size error. by @KevinHuSh in #4401
• Feat: Add description for tag parsing method #4368 by @cike8899 in #4402
• Added generate component description by @writinwaters in #4399
• fix:t_recognizer TypeError: 'super' object is not callable by @michaelice in #4404
• Fix API retrieval error. by @KevinHuSh in #4408
• Feat: Add tag_kwd parameter to chunk configuration modal #4368 by @cike8899 in #4414
• Update error message by @JinHai-CN in #4417
• Added descriptions of the retrieval agent component by @writinwaters in #4416
• Fix typo in helm charts by @hrchu in #4419
• Remove redundant param of rewrite component. by @KevinHuSh in #4422
• Fixed code error when mssql returns multiple columns by @isthaison in #4420
• Let the agent talk while there's pre-set param. by @KevinHuSh in #4423
• Tagging by @KevinHuSh in #4426
• Added a description of the Categorize agent component by @writinwaters in #4428
• Feat: Add TagFeatureItem #4368 by @cike8899 in #4432
• Fix: Modify the text of the category operator form #4412 by @cike8899 in #4433
• fix duckduckgo search subsection error by @gegef2009 in #4430
• Feat: Display tag word cloud on recall test page #4368 by @cike8899 in #4438
• update res vi by @isthaison in #4437
• Error message: Infinity not support table parsing method by @JinHai-CN in #4439
• Add doc meta data. by @KevinHuSh in #4442
• Bump infinity to v0.6.0-dev1 by @yuzhichang in #4448
• Fix: In order to...

v0.15.1

What's Changed

• Fix release.yml by @yuzhichang in #4100
• Miscellaneous updates to session APIs by @writinwaters in #4097
• add typo locale by @isthaison in #4099
• Fixed infinity exception SCORE() / SCORE_FACTORS() requires Fusion or MATCH TEXT or MATCH TENSOR by @yuzhichang in #4110
• Separated list_agents() from session management by @writinwaters in #4111
• Fix fastembed reloading issue. by @KevinHuSh in #4117
• Add parameters for ask_chat and fix bugs in list_sessions by @Feiue in #4119
• Make fast embed and default embed mutually exclusive. by @KevinHuSh in #4121
• fix chunk method "Table" losing content when the Excel file has multi… by @ly0303521 in #4123
• add gemini 2.0 by @isthaison in #4115
• Refactor ask decorator by @JinHai-CN in #4116
• Corrections. by @KevinHuSh in #4127
• Mask password in log by @yuzhichang in #4129
• Fix example in doc by @JinHai-CN in #4133
• Fix redis get error. by @KevinHuSh in #4140
• Fix position_int on infinity by @yuzhichang in #4144
• Update the component of the agent API with parameters. by @Feiue in #4131
• Validate returned chunk at list_chunks and add_chunk by @yuzhichang in #4153
• Fix Voyage re-rank model. Limit file name length. by @KevinHuSh in #4171
• Use s3 configuration from settings module by @KennyDizi in #4167
• Fix bug over chunks classification by document in the promp by @devMls in #4156
• Update jin10.svg by @isthaison in #4159
• Add Llama3.3 by @KevinHuSh in #4174
• Fetch chunk by batches. by @KevinHuSh in #4177
• Fix 'SCORE' not found bug by @JinHai-CN in #4178
• Feat: If there is no result in the recall test, an empty data image will be displayed. #4182 by @cike8899 in #4183
• Fix error of changing embedding model by @JinHai-CN in #4184
• Fix duplicated communitiy by @KevinHuSh in #4187
• Added time to progress message by @yuzhichang in #4185
• Fix: Fixed the issue that the page crashed when the node ID was the same as the combo ID #4180 by @cike8899 in #4191
• Fix raptor bug. by @KevinHuSh in #4192
• Fix score() issue by @JinHai-CN in #4194
• Update progress time info by @JinHai-CN in #4193
• Catch the exception while parsing pptx. by @KevinHuSh in #4202
• fix: stop rerank by model when search result is empty by @mieco in #4203
• Bump infinity to 0.5.2 by @yuzhichang in #4207
• Add user_id for third-party system to record sessions. by @KevinHuSh in #4206
• Remove session owner check. by @KevinHuSh in #4211
• Fix interface as input variable for component. by @KevinHuSh in #4212
• Fix misspell. by @KevinHuSh in #4219
• Fix: Rename chat name, missing field 'avatar' #4125 by @cike8899 in #4221
• Update pyproject.toml to 0.15.1 by @JinHai-CN in #4222

New Contributors

• @ly0303521 made their first contribution in #4123
• @KennyDizi made their first contribution in #4167
• @mieco made their first contribution in #4203

Full Changelog: v0.15.0...v0.15.1

v0.15.0

Released on December 18, 2024. Cheers!

New features

• Introduces additional Agent-specific APIs.
• Supports using page rank score to improve retrieval performance when searching across multiple knowledge bases.
• Offers an iframe in Chat and Agent to facilitate the integration of RAGFlow into your webpage.
• Adds a Helm chart for deploying RAGFlow on Kubernetes.
• Supports importing or exporting an agent in JSON format.
• Supports step run for Agent components/tools.
• Adds a new UI language: Japanese.
• Supports resuming GraphRAG and RAPTOR from a failure, enhancing task management resilience.
• Adds more Mistral models.
• Adds a dark mode to the UI, allowing users to toggle between light and dark themes.

Improvements

• Upgrades the Document Layout Analysis model in Deepdoc.
• Significantly enhances the retrieval performance when using Infinity as document engine.

What's Changed

• Fix the issue where the agent interface cannot call the context by @kunkeji in #3725
• Fix image_id absence issue by @KevinHuSh in #3735
• Fix GPU docker compose file by @JinHai-CN in #3736
• Fix raptor issue by @KevinHuSh in #3737
• Refactor dockerfile by @KevinHuSh in #3741
• Change Traditional Chinese to Simplified Chinese by @kunkeji in #3742
• Update document by @JinHai-CN in #3746
• Pass top_p to ollama by @yuzhichang in #3744
• Added release notes v0.11.0 by @writinwaters in #3745
• Feat: Add DatasetTable #3221 by @cike8899 in #3743
• Feat: Support for formulas #1954 by @cike8899 in #3747
• Weight up title and keywords for chunks in terms of retrieval by @KevinHuSh in #3750
• Fixed increase_usage for builtin models by @yuzhichang in #3748
• Image compression by @kunkeji in #3749
• Feat: Translate comments of file-util.ts to English #3749 by @cike8899 in #3757
• Optimize the knowledge base card UI by @kunkeji in #3756
• Feat: Add tooltip to delimiter filed #1909 by @cike8899 in #3758
• Fix chunk creation using Infinity by @JinHai-CN in #3763
• Update progress info and start welcome info by @JinHai-CN in #3768
• Update QR code of wechat by @JinHai-CN in #3776
• Update README by @JinHai-CN in #3777
• Update file parsing progress info by @JinHai-CN in #3780
• Refactor parse progress by @JinHai-CN in #3781
• add jina new models in jina connector by @devMls in #3770
• Removed obsolete instructions by @writinwaters in #3785
• Fix out of boundary. by @KevinHuSh in #3786
• Fix the bug that prevented modifying dataset_ids by @Feiue in #3784
• Fix service_conf for oc9 docker compose file. by @KevinHuSh in #3790
• Detect invalid response from api.siliconflow.cn by @yuzhichang in #3792
• Update document: how upload file large than 128MB by @JinHai-CN in #3791
• Feat: Quit from jointed team #3759 by @cike8899 in #3797
• More dataset test cases by @JinHai-CN in #3802
• Set Log level by env by @yuzhichang in #3798
• Improved ollama doc by @yuzhichang in #3787
• [DOC] We have no plan to maintain Docker images for ARM. Please build your … by @writinwaters in #3808
• Feat: Supports page rank score for different knowledge bases. #3794 by @cike8899 in #3800
• Fix the bug that the agent could not find the context by @Feiue in #3795
• Feat: Add TestingForm #3221 by @cike8899 in #3810
• Fix voyage embedding. by @KevinHuSh in #3818
• Web API test cases by @JinHai-CN in #3812
• Fix: page_chars attribute does not exist in some formats of PDF by @cyhasuka in #3796
• Feat: Store the pagerank field at the outermost #3794 by @cike8899 in #3822
• Fix @ in model name issue. by @KevinHuSh in #3821
• Add pagerank to KB. by @KevinHuSh in #3809
• Add Helm chart deployment method by @sd109 in #3815
• Fix the agent reference bug and the session prologue by @Feiue in #3823
• Add more mistral models. by @KevinHuSh in #3826
• Refactor embedding batch_size by @yuzhichang in #3825
• Feat: Modify the style of the home page in bright mode #3221 by @cike8899 in #3832
• Fix parsing JSON file error by @JinHai-CN in #3829
• Add api for list agents and agent seesions by @Feiue in #3835
• Change default error message to English by @JinHai-CN in #3838
• Update QRcode by @JinHai-CN in #3844
• Email sending tool by @kunkeji in #3837
• Web: Fixed the download and preview file not authorized. by @baifachuan in #3652
• Fix preview issue in file manager. by @KevinHuSh in #3846
• Update docs. by @KevinHuSh in #3849
• Feat: Fixed the problem of not finding EmailForm #3837 by @cike8899 in #3847
• Fix: Delete unused code #3651 by @cike8899 in #3852
• Fix: Hide the download button if it is an empty file #3762 by @cike8899 in #3853
• Add sdk for list agents and sessions by @Feiue in #3848
• Refine synonym query. by @KevinHuSh in #3855
• Feat: Bind the route to the navigation bar in the head #3221 by @cike8899 in #3863
• Fix open AI compatible rerank issue. by @KevinHuSh in #3866
• Fix chunk position issue. by @KevinHuSh in #3867
• Fix: The right coordinates of Categorize and Switch operators are misplaced #3868 by @cike8899 in #3869
• Fix HuggingFace model error. by @KevinHuSh in #3870
• Feat: Add question parameter to edit chunk modal #3873 by @cike8899 in #3874
• Feat: Adjust the input box width of EditTag to 100% #3873 by @cike8899 in #3876
• Feat: Add question parameter to edit chunk modal by @KevinHuSh in #3875
• Fix chunk available issue by @KevinHuSh in #3877
• Feat: Add tooltip to question item of ChunkCreatingModal #3873 by @cike8899 in #3878
• Revert "Feat: Add tooltip to question item of ChunkCreatingModal #3873" by @KevinHuSh in #3879
• Feat: Add tooltip to question item of ChunkCreatingModal #3873 by @cike8899 in #3880
• Add a dependency blincker. by @KevinHuSh in #3882
• Fix typos by @JinHai-CN in #3887
• Feat: Import & export the agents. #3851 by @cike8899 in #3894
• release with CI by @yuzhichang in #3891
• Fix: An error occurred when deleting a new conversation #3898 by @cike8899 in #3900
• Remove token check while adding model. by @KevinHuSh in #3903
• Fix: Fixed the issue that the agent list page failed to load #3827 by @cike8899 in #3902
• Remove vector stored in component output. by @KevinHuSh in #3908
• Introduced NEED_MIRROR by @yuzhichang in #3907
• Refactor UI text by @JinHai-CN in #3911
• Update oc9 docker compose file by @JinHai-CN in #3913
• Fix errors detected by Ruff by @yuzhichang in https:...

v0.14.1

Summary

Mainly addressing several serious bugs in 0.14.0 and issues with Infinity configuration, the updates are listed below:

• Infinity configuration can be changed in docker/infinity_conf.toml. After modifying the file, restart docker compose to take effect.
• Solve the problem that the Chunk interface cannot be displayed or modified.
• Solve the problem of garbled Chinese text parsing.
• Solve the Elasticsearch 'Not found error' problem.
• Solve the problem of Polars library compatibility.
• Solve the problem that Infinity can't adapt GraphRAG.

What's Changed

• Updated UI by @writinwaters in #3639
• Feat: Add ModelManagement page #3221 by @cike8899 in #3638
• For security. by @KevinHuSh in #3642
• Fixed es mapping by @yuzhichang in #3643
• Fix the bug causing garbled text by @Feiue in #3640
• Let ThreadPool exit gracefully. by @KevinHuSh in #3653
• Check model id when set dialog. Close #849 by @yuzhichang in #3655
• Feat: add PromptManagement page #3221 by @cike8899 in #3650
• Fix es get NotFoundError by @yuzhichang in #3659
• Added release notes by @writinwaters in #3660
• Fix KB list bugs and add web api test by @JinHai-CN in #3649
• Fix a bug in VolcEngine by @Feiue in #3658
• Feat: Add Datasets page #3221 by @cike8899 in #3661
• Use polars-lts-cpu on arm64 by @yuzhichang in #3667
• Fix enable/disable bug by @Feiue in #3662
• Fix graphrag + infinity bugs by @yuzhichang in #3681
• Added aspose on macosx/arm64 by @yuzhichang in #3686
• Always open text file for write with UTF-8 by @yuzhichang in #3688
• Feat: Add dataset sidebar #3221 by @cike8899 in #3683
• Fix batch size issue. by @KevinHuSh in #3675
• Added release notes for v0.13.0 by @writinwaters in #3691
• Feat: Scrolling knowledge base list #3695 by @cike8899 in #3703
• Revert "Feat: Scrolling knowledge base list #3695" by @KevinHuSh in #3708
• Edit chunk shall update instead of insert it by @yuzhichang in #3709
• Fix RGBA error by @kuschzzp in #3707
• Detect shape error of embedding by @yuzhichang in #3710
• Added release notes v0.12.0 by @writinwaters in #3711
• Feat: Scrolling knowledge base list and set the number of entries per page to 30 #3695 by @cike8899 in #3712
• Add more web test cases by @JinHai-CN in #3702
• Added an infinity configuration file to easily customize the settings of Infinity by @yuzhichang in #3715
• Fix test cases by @JinHai-CN in #3718
• Feat: Add Dataset page #3221 by @cike8899 in #3721
• Fix error response by @KevinHuSh in #3719
• Ensure thumbnail be smaller than 64K by @yuzhichang in #3722
• Updated descriptions for the Agent components by @writinwaters in #3728
• Don't log exception if object doesn't exist by @yuzhichang in #3724
• Fix: Clicking the checkbox of the pop-up window for editing chunk is invalid #3726 by @cike8899 in #3727
• Update version info to v0.14.1 by @JinHai-CN in #3720

Full Changelog: v0.14.0...v0.14.1

RAGFlow-0.14.0

Summary

• Supports Infinity as the alternative doc engine to elasticsearch
• Add Agent support for variables and optimize interaction such as auto-saving
• Added Andrew Ng's 3-step translation Agent template and SEO optimized blog generation Agent template.
• Added API for Agent
• English synonyms are supported during retrieval
• Optimized the calculation of term weight, such that the recall time is reduced by half
• More resilient task executor for document parsing and chunking
• Strengthened the monitoring of task Executor
• Replacing Redis with Valkey
• New supported languages: Indonesian, Spanish, Vietnamese

What's Changed

• Updated screenshots for Starting an AI chat by @writinwaters in #3139
• Changed version to 0.13.0 by @yuzhichang in #3140
• Updated obsolete screenshot. by @writinwaters in #3141
• Update gif for readme and add input param to every components by @KevinHuSh in #3145
• feat: Add DynamicInputVariable to RetrievalForm #1739 by @cike8899 in #3112
• Updated an obsolete response by @writinwaters in #3152
• Updated descriptions for knowledge graph by @writinwaters in #3154
• Add test for API by @Feiue in #3134
• Replaced redis with Valkey by @yuzhichang in #3164
• Added jdk to happify tika by @yuzhichang in #3165
• Added tika jar into image to avoid downloading by @yuzhichang in #3167
• fix es search parameter error by @KevinHuSh in #3169
• feat: Proxy the SDK address to the backend #3166 by @cike8899 in #3171
• Updated instructions on upgrading to RAGFlow dev by @writinwaters in #3175
• set default LLM to new registered user by @KevinHuSh in #3180
• feat: docs for api endpoints to generate openapi specification by @hornikmatej in #3109
• feat: Add tooltip to clean_html item #2908 by @cike8899 in #3183
• feat: Add agent interface document link to agent page #3189 by @cike8899 in #3190
• add agent completion API by @KevinHuSh in #3192
• update poetry.lock by @KevinHuSh in #3197
• Docs update for upgrading DLA models by @KevinHuSh in #3198
• fix bugs in test by @Feiue in #3196
• raise exception if embedding model not found by @KevinHuSh in #3199
• add assistant to canvas chat history by @KevinHuSh in #3201
• Unified API response json schema by @yuzhichang in #3170
• rm unused file by @KevinHuSh in #3205
• accelerate term weight calculation by @KevinHuSh in #3206
• add keyword extraction time elapsed to the little lamp. by @KevinHuSh in #3207
• feat: add qwen 2.5 models for silicon flow by @zhyg in #3203
• Fix bugs in API by @Feiue in #3204
• Remove dead code by @yuzhichang in #3210
• fix: Fixed the issue of api markdown document display being messy #2346 by @cike8899 in #3212
• Added a list of supported models by @writinwaters in #3214
• doc updates by @KevinHuSh in #3216
• Editorial updates to Docker README by @writinwaters in #3223
• feat: Add next login page with shadcn/ui #3221 by @cike8899 in #3231
• fix: TypeError: only length-1 arrays can be converted to Python scalars by @ksztone-huanggonghao in #3211
• Add sdk for Agent API by @Feiue in #3220
• add inputs to display to every components by @KevinHuSh in #3242
• feat: Display input parameters on operator nodes #3240 by @cike8899 in #3241
• accelerate tokenize by @KevinHuSh in #3244
• fix ci issue by @KevinHuSh in #3245
• fix: improve embedding model validation logic for dataset operations by @mktawileh in #3235
• Fixed broken links by @writinwaters in #3256
• New locale for Bahasa Indonesia support by @haddad9 in #3255
• fix: The name of the copy operator is displayed the same as before ##3265 by @cike8899 in #3266
• Update authorization for team by @Feiue in #3262
• Refactored Docker README by @writinwaters in #3269
• Fix:#3230 When parsing a docx file using the Book parsing method, to_page is always -1, resulting in a block count of 0 even if parsing is successful by @kuschzzp in #3249
• Updated Docker README by @writinwaters in #3272
• fix index of range by @KevinHuSh in #3279
• fix switch bug by @KevinHuSh in #3280
• feat: Support shortcut keys to delete nodes #3283 by @cike8899 in #3284
• make language judgement robuster by @KevinHuSh in #3287
• Archivo ts con la traducción para el idioma español by @wjimenez123 in #3274
• feat: Modify the name of the answer operator #1739 by @cike8899 in #3288
• fix: term weight issue by @KevinHuSh in #3294
• feat: Support shortcut keys to copy nodes #3283 by @cike8899 in #3293
• Updated .env and Docker README by @writinwaters in #3295
• Added env. MACOS by @writinwaters in #3297
• feat: Automatically save agent page data #3301 by @cike8899 in #3302
• fix term weight issue by @KevinHuSh in #3306
• feat: Translate autosaved #3301 by @cike8899 in #3304
• Added configuration guideline by @writinwaters in #3309
• feat: Switch the login page to the registration component by changing the routing parameters #3221 by @cike8899 in #3307
• Fix typo by @yuzhichang in #3319
• fix benchmark issue by @KevinHuSh in #3324
• trival by @KevinHuSh in #3325
• fix: Anthropic param error by @KevinHuSh in #3327
• fix: double brace issue by @KevinHuSh in #3328
• Miscellaneous edits to RAGFlow's UI by @writinwaters in #3337
• feat: Add custom background color #3221 by @cike8899 in #3336
• feat: documentation updates to support Bahasa Indonesia by @haddad9 in #3315
• feat: updates all readme to have a link to redirect to new locale by @haddad9 in #3339
• add new models for zhipu-ai by @KevinHuSh in #3348
• feat: Add background colors such as inverse-strong #3221 by @cike8899 in #3346
• feat: Disable automatic saving of agent during running agent #3349 by @cike8899 in #3350
• Integration with Infinity by @yuzhichang in #2894
• add dependencies of chrome by @KevinHuSh in #3352
• fix: Cannot copy and paste text on agent page #3356 by @cike8899 in #3357
• Change launch backend script to handle errors gracefully by @sananbintahir in #3334
• Fix bugs in api and add examples by @Feiue in #3353
• Rework logging by @yuzhichang in #3358
• Updated RAGFlow UI by @writinwaters in #3362
• Dynamically create the service_conf.yaml file by replacing environment variables from .env by @gschmutz in #3341
• Refine english synonym by @KevinHuSh in #3371
• Turn the relative date in question to absolute date by @KevinHuSh in #3372
• exstract model di...

RAGFlow-0.13.0

Summary

• Added team support
• Upgrade UI for Agent
• Added HTTP API for knowledge base, document parsing, dialogs, etc. Python SDK is also provided, which can be installed via pip install ragflow-sdk==0.13.0.
• Added smart chunking for Markdown
• Added context retrieval through entity extraction from LLM
• Added Invoke operator for Agent
• Added support for DIFY external knowledge base API
• Added integration for ChatGPT-on-WeChat
• Added support for GLM4-9B, Yi-Lightning

What's Changed

• added tests.yml by @yuzhichang in #2685
• fix tests.yml by @yuzhichang in #2688
• refine readme by @KevinHuSh in #2689
• format mind_map_extractor code by @yqkcn in #2686
• Simplify the usage of dict by @yqkcn in #2681
• remove unused import by @yqkcn in #2679
• Refactoring entity_resolution by @guoyuhao2330 in #2692
• fix error in exception by @KevinHuSh in #2694
• Updated Dockerfile by @yuzhichang in #2695
• fix: Fixed the issue where no error message was displayed when uploading a file that was too large #2258 by @cike8899 in #2697
• Updated Dockefile to use cache by @yuzhichang in #2703
• Fix Dockerfile for arm64 by @yuzhichang in #2705
• Updated Build Docker Image by @writinwaters in #2706
• Fix Dockerfile.slim by @yuzhichang in #2708
• Fix poetry cache by @yuzhichang in #2709
• docs: Migrate README to Compose V2 syntax by @anud18 in #2711
• build multi-arch image by @yuzhichang in #2710
• Fix/bedrock issues by @Omarlsg98 in #2718
• remove redeclared get_json_result func by @yqkcn in #2675
• fix re.escape problem by @KevinHuSh in #2735
• chore: update operators.py by @eltociear in #2724
• support sequence2txt and tts model in Xinference by @JobSmithManipulation in #2696
• Add query parts to lamp by @KevinHuSh in #2736
• feat: Add component TuShare #1739 by @cike8899 in #2745
• Fix LIGHTEN. Close #2723 by @yuzhichang in #2744
• expand rerank range by @KevinHuSh in #2746
• Modified download_deps.py by @yuzhichang in #2747
• Update azure_sas_conn.py - fixing container_url typo by @jstride in #2740
• solve knowledgegraph issue when calling gemini model by @JobSmithManipulation in #2738
• move import positions by @KevinHuSh in #2753
• feat: The same query conditions on the search page should not request the interface every time the mind map drawer is opened. #2759 by @cike8899 in #2760
• Initial draft of Python APIs by @writinwaters in #2719
• Fix component exesql by @guoyuhao2330 in #2754
• fix xinference add rerank model bug by @wangguo1230 in #2758
• Fix docx images by @guoyuhao2330 in #2756
• Docs:fix user guide links by @Howe829 in #2761
• feat: Add a note node to the agent canvas #2767 by @cike8899 in #2768
• HTTP API documents, part1 by @JinHai-CN in #2713
• Use slim image as the default by @JinHai-CN in #2772
• Fix README description by @JinHai-CN in #2773
• Fix README and some comments by @JinHai-CN in #2774
• fix: Large document thumbnail display failed by @chongchuanbing in #2763
• fix bedrock issue by @KevinHuSh in #2776
• fix: torch dependency start error by @chongchuanbing in #2777
• Fix error commands by @JinHai-CN in #2778
• trival by @KevinHuSh in #2779
• Refactor README on different docker version. by @JinHai-CN in #2775
• refine agent by @KevinHuSh in #2787
• Updated instructions on downloading RAGFlow Slim and RAGFlow all-in-one. by @writinwaters in #2785
• fix: Change document status with @tanstack/react-query #13306 by @cike8899 in #2788
• Refactor Dataset API by @Feiue in #2783
• feat: Arrange the form of generate, categorize, switch, retrieval operators vertically #1739 by @cike8899 in #2800
• support api-version and change default-model in adding azure-openai and openai by @JobSmithManipulation in #2799
• fix: document preview by @chongchuanbing in #2795
• reduce rerank batch size by @KevinHuSh in #2801
• Fixed broken links. by @writinwaters in #2805
• support chat model in huggingface by @JobSmithManipulation in #2802
• fix LIGHTEN issue by @KevinHuSh in #2806
• trival by @KevinHuSh in #2808
• fix chat and thumbnail bug by @chongchuanbing in #2803
• Refactor Chat API by @Feiue in #2804
• refine components retrieval and rewrite by @KevinHuSh in #2818
• Refactor API for document and session by @Feiue in #2819
• Updated dataset APIs by @writinwaters in #2820
• refine token similarity by @KevinHuSh in #2824
• feat: Add message_history_window_size to CategorizeForm #1739 by @cike8899 in #2826
• feat: Fix translation issue of message_history_window_size #1739 by @cike8899 in #2828
• Refactor Document API by @Feiue in #2833
• Updated chat APIs by @writinwaters in #2831
• let presentation do raptor by @KevinHuSh in #2838
• feat: Generate operator names in an auto-incremental manner #1739 by @cike8899 in #2844
• refine API token application by @KevinHuSh in #2847
• refactor api util by @KevinHuSh in #2849
• add rm token by @KevinHuSh in #2850
• Feat:Compatible with Dify's External Knowledge API by @Howe829 in #2848
• Enhance email validation: Allow top-level domains with 5 letters by @mrnicegyu11 in #2856
• refactor by @KevinHuSh in #2858
• Fix keys of Xinference deployed models, especially has the same model name with public hosted models. by @0000sir in #2832
• feat: API access key management #2846 by @cike8899 in #2865
• add API for tenant function by @KevinHuSh in #2866
• Refactor Chunk API by @Feiue in #2855
• Updated session APIs by @writinwaters in #2868
• update dashscope by @KevinHuSh in #2871
• feat: Configure the root directory alias #1739 by @cike8899 in #2875
• feat: Load markdown file with "asset/source" #1739 by @cike8899 in #2880
• Fixed docker build by @yuzhichang in #2881
• Draft: Updated file management-related APIs by @writinwaters in #2882
• Miscellaneous minor updates by @writinwaters in #2885
• feat: Bind data to TenantTable #2846 by @cike8899 in #2883
• add team tag to kb by @KevinHuSh in #2890
• Delete useless files by @Feiue in #2889
• feat: Use Badge.Ribbon to distinguish the teams to which the knowledge base belongs #2846 by @cike8899 in #2891
• add owner check for team wor...

RAGFlow-0.12.0

Summary

• Adds new Docker image of slim version will doesn't including embedding and reranker models.
• Improves the effect of long context conversion.
• Supports OpenTTS and SparkTSS
• Adds new Excel parsing method, user can choose the output data format between HTML and row text.
• User can remove the added model provider.

What's Changed

• Add Multi-Language Descriptions for 'Switch' Component and Update Message Assistant Placeholder by @Defozo in #2450
• fix ppt file from filemanager error by @KevinHuSh in #2470
• update document sdk by @JobSmithManipulation in #2445
• rename create_timestamp_flt to create_timestamp_float by @JobSmithManipulation in #2473
• fix superuser password not base64 encoded by @dadahsueh in #2475
• fix duplicated llm name betweeen different suppliers by @KevinHuSh in #2477
• rename some attributes in document sdk by @JobSmithManipulation in #2481
• fix parser for pptx of which files are from filemanager by @KevinHuSh in #2482
• update document sdk by @JobSmithManipulation in #2485
• fix(Add model api): Add VolcEngine to create api_key format error by @muzilib in #2490
• OpenAITTS by @Feiue in #2493
• refine TTS by @KevinHuSh in #2500
• Storage: Rename all the variables about get file to storage from minio. by @baifachuan in #2497
• Web: Display the icon of the currently used storage. by @baifachuan in #2504
• BugFix: Fixed api_key generation error for VolcEngine by @yungongzi in #2502
• refactor add LLM by @KevinHuSh in #2508
• remove setting-system/index.tsx error import by @muzilib in #2507
• Update README_zh.md by @AlvinCage in #2491
• fix self deployed llm lost by @KevinHuSh in #2510
• rm key set in xinference by @KevinHuSh in #2511
• make excel parsing configurable by @KevinHuSh in #2517
• refine reteival of multi-turn conversation by @KevinHuSh in #2520
• refine xinference by @KevinHuSh in #2521
• Rework Dockerfile.scratch by @yuzhichang in #2525
• fix: Add model by ollama in model provider page, user can't choose the model in chat window. #2479 by @cike8899 in #2529
• Reverted replacing npm with yarn by @yuzhichang in #2531
• fix: Merge models of the same category #2479 by @cike8899 in #2536
• feat: Configurable for excel, html table or row based text #2516 by @cike8899 in #2538
• feat: Refine reteival of multi-turn conversation #2362 by @cike8899 in #2539
• fix: Initial language is English, but the UI is in Chinese #2514 by @cike8899 in #2541
• fix component rewrite bug by @KevinHuSh in #2549
• Updated README on debugging web and python by @yuzhichang in #2544
• refine markdown prompt by @KevinHuSh in #2551
• SparkTTS by @Feiue in #2535
• refine using rerank model by @KevinHuSh in #2553
• Streaming output is supported, dialogue share is not by @writinwaters in #2555
• add an API of delete llm supplier by @KevinHuSh in #2556
• fix: Web code build fails on ARM machines #2554 by @cike8899 in #2557
• refine multi-turn chat in agent by @KevinHuSh in #2560
• feat: Add component YahooFinance #1739 by @cike8899 in #2561
• feat: Add component Jin10 #1739 by @cike8899 in #2563
• feat: Delete Model Provider #2376 by @cike8899 in #2565
• add lighten control by @KevinHuSh in #2567
• Fix tokenizer bug by @guoyuhao2330 in #2573
• multi-arch-build by @yuzhichang in #2571
• feat: If the model is not set, a pop-up window will remind the user #2295 by @cike8899 in #2574
• make it lighten by @KevinHuSh in #2577
• revert error in Dockerfile by @KevinHuSh in #2581
• Add template investment_advisor by @guoyuhao2330 in #2580
• trival by @KevinHuSh in #2582
• remove onnx copy command from dockerfile by @KevinHuSh in #2584
• deprecate init a super user by @KevinHuSh in #2589
• Add component Concentrator by @guoyuhao2330 in #2586
• Update dsl_examples and Fix component concentrator by @guoyuhao2330 in #2597
• Fix soft link. Close #2587 by @yuzhichang in #2602
• feat: Add component Concentrator #1739 by @cike8899 in #2604
• Fix: renrank_model and pdf_parser bugs | Update: session API by @Feiue in #2601
• Added two developer guide and removed from README ' builder docker image' and 'launch service from source' by @writinwaters in #2590
• fix AzureOpenAI issue` by @KevinHuSh in #2608
• Remove WenCai imageurl and update investment_advisor prompt by @guoyuhao2330 in #2606
• Support agent for aibot by @guoyuhao2330 in #2609
• fix generate bug by @KevinHuSh in #2614
• Bug fix - email processing could be run now from API by @adam-kobus in #2613
• force eml file to be parsed by EMAIL by @KevinHuSh in #2615
• Update Yichat base_url by @Feiue in #2620
• remove repeat func by @yqkcn in #2619
• style: fix typo and format code by @yqkcn in #2618
• fix: Fixed an issue where the first message would be displayed when sending the second message #2625 by @cike8899 in #2626
• Added doc on dev-slim by @yuzhichang in #2627
• add huggingface model by @JobSmithManipulation in #2624
• feat: Add top_n to DeepLForm #1739 by @cike8899 in #2629
• refine get_input by @KevinHuSh in #2630
• fix: Fixed the issue where the conversation list was not displayed on the conversation page #2625 by @cike8899 in #2638
• handle nits in task_executor by @yqkcn in #2637
• Fix logger error by @yqkcn in #2643
• change chunk.status to chunk.available by @JobSmithManipulation in #2646
• Fix mutable default argument by @yqkcn in #2635
• Refactoring large integers to improve readability by @yqkcn in #2636
• Add get_txt function by @yqkcn in #2639
• Add doc for dev image by @yuzhichang in #2641
• refine general purpose chat bot by @KevinHuSh in #2648
• rename get_txt to get_text by @KevinHuSh in #2649
• trival by @KevinHuSh in #2650
• fix template error by @KevinHuSh in #2653
• Updated component description by @writinwaters in #2651
• fix: Fixed the issue where the error message was not displayed when uploading a file that was too large #1782 by @cike8899 in #2654
• change url of local llm deploy guide by @JobSmithManipulation in #2659
• fix: Filter the timePeriod options based on the userType parameter #1739 by @cike8899 in #2657
• Add build image and launch from source in README by @JinHai-CN in #2658
• document preparation for release by @KevinHuSh in https://github....