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 distinguish the keys of a pair of messages, add a prefix to the id when rendering the message. #4409 by @cike8899 in #4451
• Fix: Can not select GPT-4o / 4o mini as Chat Model #4421 by @cike8899 in #4453
• Fix csv for TAG. by @KevinHuSh in #4454
• Add meta data while chatting. by @KevinHuSh in #4455
• Feat: Metadata in documents for improve the prompt #3690 by @cike8899 in #4462
• Check meta data format in json map by @KevinHuSh in #4461
• Format: dos2unix by @JinHai-CN in #4467
• Replace poetry with uv by @yuzhichang in #4471
• Recalling the file uploaded while chatting. by @KevinHuSh in #4472
• Fix dify retrieval issue. by @KevinHuSh in #4473
• Feat: Add background to next login page #3221 by @cike8899 in #4474
• Update description by @JinHai-CN in #4468
• Sync prerequisites with Helm Charts by @hrchu in #4483
• Refactor. by @KevinHuSh in #4487
• Feat: add gpustack model provider by @alexcodelf in #4469
• Truncate text for zhipu embedding. by @KevinHuSh in #4490
• Feat: Add FilesTable #3221 by @cike8899 in #4491
• Accelerate titles' embeddings. by @KevinHuSh in #4492
• Bump infinity to v0.6.0-dev2 by @yuzhichang in #4497
• Fix: the Display when the knowledge base empty. by @limengning in #4496
• Feat: Add LinkToDatasetDialog #3221 by @cike8899 in #4500
• Fix xinference rerank issue. by @KevinHuSh in #4499
• Feat: Add the MessageHistoryWindowSizeItem to RewriteQuestionForm #1739 by @cike8899 in #4502
• Fix: Fixed an issue where math formulas could not be displayed correctly #4405 by @cike8899 in #4506
• Feat: Make the category operator form displayed in collapsed mode by default #4505 by @cike8899 in #4510
• Added descriptions of Message and Keyword agent components by @writinwaters in #4512
• Change index url per NEED_MIRROR by @yuzhichang in #4515
• add file README_tzh.md by @luohuanhuan2019 in #4513
• Fix: Translate the operator options of the Switch operator #1739 by @cike8899 in #4519
• Fix doc progress issue. by @KevinHuSh in #4520
• Fix: Rename segmented.tsx #3221 by @cike8899 in #4522
• Remove use of eval() from ocr.py by @panzi in #4481
• Remove use of eval() from recognizer.py by @panzi in #4480
• Bump akshare by @yuzhichang in #4536
• Make Categorize see more chat hisotry. by @KevinHuSh in #4538
• Added descriptions of Rewrite and Switch components. To be continued by @writinwaters in #4526
• Feat: Rename document name #3221 by @cike8899 in #4544
• Added description of the Concentrator component by @writinwaters in #4549
• Added entrypoint for task executor by @yuzhichang in #4551
• Feat: Make the scroll bar of the DatasetSettings page appear inside #3221 by @cike8899 in #4548
• Add language portugese br by @henriquelca in #4550
• Feat: Support for Portuguese language #4557 by @cike8899 in #4558
• Added descriptions of the Note and Template components by @writinwaters in #4560
• minor by @writinwaters in #4568
• Update comments by @JinHai-CN in #4569
• Fix Latest Release button on PT README by @henriquelca in #4572
• Revert the chat history for rewrite. by @KevinHuSh in #4579
• re-fix by @isthaison in #4584
• Renamed entrypoint_task_executor.sh entrypoint-parser.sh by @yuzhichang in #4583
• Remove usage of eval() from postprocess.py by @panzi in #4571
• Light GraphRAG by @KevinHuSh in #4585
• Feat: Display the knowledge graph on the knowledge base page #4543 by @cike8899 in #4587
• Fix: Capture the problem that the knowledge graph interface returns null and causes page errors #4543 by @cike8899 in #4598
• Fix index not found for new user. by @KevinHuSh in #4597
• Fix pdf applying Q&A issue. by @KevinHuSh in #4599
• fix bug KGSearch.search() got an unexpected keyword argument 'rank_feature' by @bulexu in #4601
• Unified user_service.py by @yuzhichang in #4606
• Feat: Add keyword item to AssistantSetting #4543 by @cike8899 in #4603
• Template conversion adds Jinjia2 syntax support by @WANGRUI-ZB in #4545
• Rebuild graph when it's out of time. by @KevinHuSh in #4607
• Feat: Set the style of the header tag #3221 by @cike8899 in #4608
• Code format. by @KevinHuSh in #4611
• Refactor. by @KevinHuSh in #4612
• deepdoc use GPU if possible by @yuzhichang in #4618
• Fix TogetherAIEmbed. by @KevinHuSh in #4623
• Add timestamp to messages by @KevinHuSh in #4624
• Fix t_ocr.py for PNG image. by @KevinHuSh in #4625
• Added document: Accelerate document indexing and retrieval by @writinwaters in #4600
• Fix missplace for vector sim weight and token sim weight. by @KevinHuSh in #4627
• Added onnxruntime-gpu by @yuzhichang in #4631
• Fix csv reader exception. by @KevinHuSh in #4628
• Make infinity adapt by @KevinHuSh in #4635
• Removed onnxruntime by @yuzhichang in #4632
• Fix onnxruntime-gpu marks by @yuzhichang in #4643
• Make infinity able to cal embedding sim only. by @KevinHuSh in #4644
• refactor: better vertical alignment for icon and text in some setting buttons by @vndee in #4615
• Fix param error. by @KevinHuSh in #4645
• Align table heading with 'System Model Settings' by @writinwaters in #4646
• Added GPUStack by @writinwaters in #4649
• Fix potential error. by @KevinHuSh in #4650
• Fix too long integer for Table. by @KevinHuSh in #4651
• Refactor for total_tokens. by @KevinHuSh in #4652
• Update README. by @KevinHuSh in #4654
• Make infinity adapt to condition exist. by @KevinHuSh in #4657
• Added description of the Iteration component by @writinwaters in #4656
• Refresh deepseek models. by @KevinHuSh in #4660
• Refactor the delimiter name by @JinHai-CN in #4659
• Update FAQ by @JinHai-CN in #4661
• Fix typos by @JinHai-CN in #4662
• Infinity adapt to graphrag. by @KevinHuSh in #4663
• Infinity mapping refine. by @KevinHuSh in #4665
• Fix macOS startup by @Mulugruntz in #4658
• fix: err object has no attribute 'iter_lines' by @KyTiXo in #4686
• Reverted build slim image documentation by @safipatel in #4687
• Fixed GPU detection on CPU only environment by @yuzhichang in #4711
• Import akshare lazzily. by @KevinHuSh in #4708
• Update deepseek model provider info. by @KevinHuSh in #4714
• Update readme. by @KevinHuSh in #4715
• Fix exesql re-generate SQL issue. by @KevinHuSh in #4717
• Fitin for infinity. by @KevinHuSh in #4722
• Added cuda_is_available by @yuzhichang in #4725
• Fix: Chat Assistant page goes blank #4566 by @cike8899 in #4727
• Fix: pt_br translation and adding pt to knoledg-add by @henriquelca in #4674
• Fix too long query exception. by @KevinHuSh in #4729
• Avoid misunderstanding LLMs about the numbers value by @isthaison in #4724
• Fix too long context issue. by @KevinHuSh in #4735
• Fix: New user can't accept invite without configuring LLM API #4379 by @cike8899 in #4736
• Resume content flow ExecSQL by @isthaison in #4738
• Feat: Supports docx in the MANUAL chunk method and docx, markdown, and PDF in the Q&A chunk method #3957 by @cike8899 in #4741
• Preparation for release. by @KevinHuSh in #4739
• Updated template description by @writinwaters in #4744
• Robust for abnormal response from LLMs. by @KevinHuSh in #4747

New Contributors

• @gegef2009 made their first contribution in #4237
• @TeslaZY made their first contribution in #4271
• @WANGRUI-ZB made their first contribution in #4275
• @hrchu made their first contribution in #4300
• @michaelice made their first contribution in #4404
• @alexcodelf made their first contribution in #4469
• @limengning made their first contribution in #4496
• @luohuanhuan2019 made their first contribution in #4513
• @panzi made their first contribution in #4481
• @henriquelca made their first contribution in #4550
• @bulexu made their first contribution in #4601
• @vndee made their first contribution in #4615
• @Mulugruntz made their first contribution in #4658
• @KyTiXo made their first contribution in #4686
• @safipatel made their first contribution in #4687

Full Changelog: v0.15.1...v0.16.0