nightly

Release nightly created from 07354f4 at 2025-08-07 21:19:35+08:00

v0.20.0

Released on August 1, 2025.

Features and improvements

• Unified orchestration of both Agents and Workflows.
• A comprehensive refactor of the Agent, greatly enhancing its capabilities and usability, with support for Multi-Agent configurations, planning and reflection, and visual functionalities.
• Fully realized MCP functionality, allowing for MCP Server import, Agents functioning as MCP Clients, and RAGFlow itself operating as an MCP Server.
• Access to runtime logs for Agents.
• Chat histories with Agents available through the management panel.
• Integration of a new, more robust version of Infinity, enabling the auto-tagging functionality with Infinity as the underlying document engine.
• An OpenAI-compatible API that supports file reference information.
• Support for new models, including Kimi K2, Grok 4, and Voyage.

10 new Agent templates are now available:

• Multi-Agent based Deep Research: Collaborative Agent teamwork led by a Lead Agent with multiple Subagents, distinct from traditional workflow orchestration.
• An intelligent Q&A chatbot leveraging internal knowledge bases, designed for customer service and training scenarios.
• A resume analysis template used by the RAGFlow team to screen, analyze, and record candidate information.
• A blog generation workflow that transforms raw ideas into SEO-friendly blog content.
• An intelligent customer service workflow.
• A user feedback analysis template that directs user feedback to appropriate teams through semantic analysis.
• Trip Planner: Uses web search and MCP maps to assist with travel planning.
• Image Lingo: Translates content from uploaded photos.
• An information search assistant that retrieves answers from both internal knowledge bases and the web.

Breaking changes

From v0.20.0 onwards, Agents are no longer compatible with earlier versions, and all existing Agents from previous versions must be rebuilt following the upgrade.

What's Changed

• Feat: Add Tavily operator #3221 by @cike8899 in #8400
• Docs: Added v0.19.1 release notes by @writinwaters in #8398
• Fix: Document parse via API will alot problen by @Woody-Hu in #8407
• Fix: rank feature score should be greater than 0. by @KevinHuSh in #8416
• Feat: Solved the conflict between the Handle click and drag events of the canvas node #3221 by @cike8899 in #8413
• Fix: doc_aggs issue. by @KevinHuSh in #8418
• Fix: Database Query Vulnerable to Injection Attacks in rag/utils/opendal_conn.py by @kira-offgrid in #8408
• Feat: The delete button is displayed only when the cursor is hovered over the connection line #3221 by @cike8899 in #8422
• Feat: Add HTTPS setup instructions and configuration for Nginx by @yesidc in #8401
• Fix: AzureChat model code by @asiroliu in #8426
• Update .env ,Defaults to the v0.19.1-slim edition by @jason-this in #8412
• Refa: upgrade MCP SDK to v1.9.4 by @yongtenglei in #8421
• Docs: Miscellaneous editorial updates by @writinwaters in #8430
• Feat: Scratch MCP tool calling support. by @notsyncing in #8263
• Feat: Use the message_id returned by the interface as the id of the reply message #3221 by @cike8899 in #8434
• fix a bug when using huggingface embedding api by @Rainman5042 in #8432
• Feat: Delete the agent and tool nodes downstream of the agent node #3221 by @cike8899 in #8450
• Refactor:Improve insert file logic by @Woody-Hu in #8445
• Test: Add document app tests by @asiroliu in #8456
• FIX:Saving an RGBA image directly as JPEG will cause an error. If the… by @WuWeiFlow in #8399
• Feat: Add IterationNode component #3221 by @cike8899 in #8461
• Fix the bug of long type value overflow by @HaiyangPeng in #8313
• Docs: exporting created knowledge graphs is not supported by @writinwaters in #8465
• Feat: add MCP dashboard operations by @yongtenglei in #8460
• Fix: some cases Task return but not set progress by @Woody-Hu in #8469
• Feat: add MCP treamable-http transport by @yongtenglei in #8449
• Fix: Solve the OOM issue when passing large PDF files while using QA chunking method. by @liuzhenghua in #8464
• Feat: Insert the node data of the bottom subagent into the tool array of the head agent #3221 by @cike8899 in #8471
• RAGFlow service_conf using .env variable by @ruansheng8 in #8454
• Fixes typo in variable name by @tuankg1028 in #8476
• Refa: improve GraphRAG similarity sensitivity to numeric differences by @yongtenglei in #8479
• Feat: Filter the query variable drop-down box options by type #3221 by @cike8899 in #8485
• fix the error 'Unknown field for GenerationConfig: max_tokens' when u… by @Rainman5042 in #8473
• Fix: Enforce default embedding model in create_dataset / update_dataset by @asiroliu in #8486
• Adds retrieval result fields to Chunk by @tuankg1028 in #8478
• Feat: Add retrieval tool #3221 by @cike8899 in #8491
• Feat: Allow operators inside the loop operator to reference the output parameters of external operators #3221 by @cike8899 in #8498
• Fix parser_config access for layout_recognize in presentation.py by @tuankg1028 in #8492
• Feat: add MCP dashboard functionalities list_tools and test_tool by @yongtenglei in #8505
• Perf: ignore concate between rows. by @KevinHuSh in #8507
• Feat: Add UserFillUpForm component #3221 by @cike8899 in #8508
• Feat: Customize the output variable name of the loop operator #3221 by @cike8899 in #8514
• Fix: Add input validation to chunk creation endpoint by @asiroliu in #8516
• Feat: Displays the output variable type selected by the loop operator #3221 by @cike8899 in #8515
• Fix: chunk number error after re-parsing by @yongtenglei in #8513
• fix(prompt-editor): resolve initial cursor position and auto-newline … by @FatMii in #8511
• Feat: Add StringTransform operator #3221 by @cike8899 in #8520
• fix: list index out of range by @LeiZhang-Hunter in #8518
• Fix: user_default_llm configuration doesn't work for OpenAI API compatible LLM factory by @Woody-Hu in #8502
• Refactor:improve the logic to check cancel by @Woody-Hu in #8524
• Refactor: remove useless initialize logic in list_doc by @Woody-Hu in #8523
• Fix memory leaks in PIL image and BytesIO handling during chunk processing by @tuankg1028 in #8522
• Feat: allow users to choose which MCP tools are enabled by @yongtenglei in #8519
• Fix: chat with tools bug. by @KevinHuSh in #8528
• Feat: Fixed the issue where the prompt menu content was hidden #3221 by @cike8899 in #8530
• Feat: Display sub-agents in agent form #3221 by @cike8899 in #8536
• Feat: Fixed the issue where the begin operator parameters could not be submitted during debugging #3221 by @cike8899 in #8539
• Refa: limit embedding concurrency and fix chat_with_tool by @KevinHuSh in #8543
• Feat: add gitee as LLM provider. by @KevinHuSh in #8545
• Feat: Allow users to enter text in the middle of a chat #3221 by @cike8899 in #8569
• Feat: Support GiteeAI model #1853 by @cike8899 in #8573
• Feat: add GiteeAI as a llm provider. by @KevinHuSh in #8572
• Feat: Fixed the issue that the top toolbar disappears when opening the agent operator form #3221 by @cike8899 in #8579
• Adding semaphore usage on the '/run' endpoint by @RafaelFFAumo in #8526
• Feat: In a dialog message, users can enter different types of data #3221 by @cike8899 in https://github.com/infin...

v0.19.1

v0.19.1

Released on June 23, 2025.

Fixed issues

• A memory leak issue during high-concurrency requests.
• Fixed a freezing issue when parsing large files with GraphRAG entity resolution enabled. #8223
• A context error occurring when using Sandbox in standalone mode. #8340
• An excessive CPU usage issue caused by Ollama. #8216
• A bug in the Code Component. #7949

Improvements

• Added support for Qwen 3 Embedding. #8184
• Added support for Voyage Multimodal 3. #7987
• Enabled role-based authentication for S3 bucket access. #8149
• Added support for models installed via Ollama or VLLM when creating a knowledge base through the API. #8069

What's Changed

• Feat: Migrate the code operator to the new agent. #3221 by @cike8899 in #7731
• Feat: Render the agent list page by page #3221 by @cike8899 in #7736
• Feat: Rename agent #3221 by @cike8899 in #7740
• 0519 pdfparser by @writinwaters in #7747
• Feat: delete useless image blobs when task executor meet edge cases by @Woody-Hu in #7727
• Feat: Fixed the issue where the page would refresh continuously when opening the sheet on the right side of the canvas #3221 by @cike8899 in #7756
• Feat: Switching the programming language of the code operator will switch the corresponding language template #3221 by @cike8899 in #7770
• Feat: Add return value widget to CodeForm #3221 by @cike8899 in #7776
• Fix: improve task cancel lag by @Woody-Hu in #7765
• Fix: resolve regex library warnings by @emmanuel-ferdman in #7782
• fix：When creating a new assistant, an avatar was uploaded, but when selecting the assistant to start a new chat, the default avatar still appears in the chat window instead of the one uploaded during creation by @kunger309 in #7769
• Feat: Refactor BeginForm with shadcn #3221 by @cike8899 in #7792
• Feat: Verify the parameters of the begin operator #3221 by @cike8899 in #7794
• Docs: RAGFlow does not suppport batch metadata setting by @writinwaters in #7795
• Fix baidu request error by @gegef2009 in #7799
• Feat: Synchronize BeginForm's query data to the canvas #3221 by @cike8899 in #7798
• Fix backquotes in text2sql causing execution errors by @Sol-Ghf in #7793
• Feat: Reconstruct the QueryTable of BeginForm using shandcn #3221 by @cike8899 in #7807
• Docs: Added instructions on cross-language search by @writinwaters in #7812
• Feat: Translate the begin operator #3221 by @cike8899 in #7811
• Fix: Improve First Chunk Size by @Woody-Hu in #7806
• Feat: add code_executor_manager by @yongtenglei in #7814
• Update rag/nlp/query.py by @Sol-Ghf in #7816
• Feat: Refactor the MessageForm with shadcn #3221 by @cike8899 in #7820
• Fix: Fixed the issue that the script text of the code operator is not displayed after refreshing the page after saving the script text of the code operator #4977 by @cike8899 in #7825
• Delete Corresponding Minio Bucket When Deleting a Knowledge Base by @Hank-MIA in #7841
• Fix: list out of boundary by @KevinHuSh in #7843
• Fix:Setting the message_history_window_size to 0 does not take effect by @Woody-Hu in #7842
• Fix: restore task limiter. by @KevinHuSh in #7844
• Feat: Upgrade react-hook-form to the latest version to solve the problem that appending a useFieldArray entry cannot trigger the watch callback function #3221 by @cike8899 in #7849
• Optimize Tag Removal Method by @luohuanhuan2019 in #7847
• Feat: Convert the data of the messge operator to a string array #3221 by @cike8899 in #7853
• Fix: Opensearch chunk management by @pyyuhao in #7802
• Docs: Miscellaneous editorial updates by @writinwaters in #7865
• Feat: Add the WaitingDialogue operator. #3221 by @cike8899 in #7862
• update xgboost and dep scripts for local build on MacOS by @whhe in #7857
• Fix: task limiter issue. by @KevinHuSh in #7873
• Feat: Put buildSelectOptions to common-util.ts #3221 by @cike8899 in #7875
• Docs: From v0.13.0 onwards, markdown chunking is added to the General chunking method. by @writinwaters in #7883
• Fix: patch regex vulnerability in filename handling by @asiroliu in #7887
• Removed the "USER:" in the question, reducing the accuracy of the search by @Sol-Ghf in #7852
• Fix: raptor overloading by @KevinHuSh in #7889
• Perf: reduce upload to minio limiter scope by @Woody-Hu in #7878
• Feat: Add the SelectWithSearch component #3221 by @cike8899 in #7892
• Update README.md by @xuzhu007 in #7864
• fix: resolve “has no attribute 'max_length'” error in keyword_extraction by @XiaoCaoAskedForHelp in #7903
• Fix: KeyError: 'method' when build run_graphrag by @Woody-Hu in #7899
• Fix: patch SSTI vulnerability in template rendering by @asiroliu in #7905
• Docs: about latest updates by @KevinHuSh in #7902
• doc related_question path changed by @huang-aoqin in #7918
• Feat: Surpport dynamically add knowledge basees for retrieval while u… by @sinopec in #7915
• Fix: bad escape \P at position 374 (line 18, column 23) when using th… by @TeslaZY in #7909
• Fix: early return when update doc in sdk by @yongtenglei in #7907
• Fix: Display bug in the early stage of conversation chat #7904 by @cike8899 in #7922
• Refa: change citation mark as [ID:n] by @yongtenglei in #7923
• Feat:: Use useWatch to synchronize the form data to canvas zustand #3221 by @cike8899 in #7926
• Truncate long agent descriptions text by @wemod123 in #7924
• Feat: Use memo to wrap canvas nodes to improve fluency #3221 by @cike8899 in #7929
• Fix: add default output method for ComponentParamBase by @Woody-Hu in #7933
• agents openai API add new way to get session_id by @huang-aoqin in #7937
• set PARALLEL_DEVICES default value= 0 by @giiiiiithub in #7935
• Fix: add advanced delimiter detection for naive merge by @yongtenglei in #7941
• Fix: code debug by @yongtenglei in #7949
• Feat: Add InnerBlurInput component to avoid frequent updates of zustand causing the input box to lose focus #3221 by @cike8899 in #7955
• Fix: File selection in Retrieval testing causes other options to disappear by @Woody-Hu in #7759
• Feat: Install why-did-you-render to detect component updates #3221 by @cike8899 in #7969
• fix: resolve residual image files issue after document deletion by @XiaoCaoAskedForHelp in #7964
• Fix Bug: When performing the dify_retrieval, the metadata of the document was empty. by @bravecharge in #7968
• Update docker-compose.yml by @xiaoping378 in #7962
• Fix: Add user_id when create Conversation by @Woody-Hu in #7960
• Fix: Prevent Flask hot reload from hanging due to early thread startup by @KraHsu in #7966
• Update upload filename length limit from 128 ...

v0.19.0

Released on May 26, 2025.

New features

• Cross-language search is supported in the Knowledge and Chat modules, enhancing search accuracy and user experience in multilingual environments, such as in Chinese-English knowledge bases.
• Agent component: A new Code component supports Python and JavaScript scripts, enabling developers to handle more complex tasks like dynamic data processing.
• Enhanced image display: Images in Chat and Search now render directly within responses, rather than as external references. Knowledge retrieval testing can retrieve images directly, instead of texts extracted from images.
• Claude 4 and ChatGPT o3: Developers can now use the newly released, most advanced Claude model alongside OpenAI’s latest ChatGPT o3 inference model.

The following features are contributed by our community contributors:

• Agent component: Enables tool calling within the Generate Component. Kudos to notsyncing.
• Markdown rendering: Image references in a markdown file can be displayed after chunking. Kudos to Woody-Hu.
• Document engine support: OpenSearch can now be used as RAGFlow's document engine. Kudos to pyyuhao.

What's Changed

• Feat: Create a folder #3221 by @cike8899 in #7228
• Feat: Deleting files in batches. #3221 by @cike8899 in #7234
• Fix/mcp doc by @yxkong in #7239
• Fix: improve retrieval API by @Woody-Hu in #6744
• Fix: mcp server start by @treywelsh in #7251
• chore: adds pre-commit by @wanpdsantos in #7242
• tag is missing. by @White-Bear1122 in #7256
• fix: task_executor bug fix by @benni82 in #7253
• Feat: Display document parsing status #3221 by @cike8899 in #7241
• Feat: Delete and rename files in the knowledge base #3221 by @cike8899 in #7268
• Feat: Adds OpenSearch2.19.1 as the vector_database support by @pyyuhao in #7140
• Docs: How to disable user registration by @writinwaters in #7265
• Feat: Replace the logo of novita by @neal-davis in #7287
• Fix: Qwen-vl-plus url error by @yongtenglei in #7281
• Doc: Updated sharing behavior in the open-source editions. by @writinwaters in #7293
• Feat: Display the document configuration dialog with shadcn #3221 by @cike8899 in #7302
• Fix pymysql interface error by @Yue-Lyu123 in #7295
• Fix: LLM generated tag issue. by @KevinHuSh in #7301
• Feat: Save the configuration information of the knowledge base document #3221 by @cike8899 in #7317
• Feat: Markdown add image by @Woody-Hu in #7124
• Feat: Save document metadata #3221 by @cike8899 in #7323
• Fix: Creating Knowledge Base Support Enter Key by @Woody-Hu in #7258
• DOC: Miscellaneous UI and editorial updates by @writinwaters in #7324
• Feat: Filter document by running status and file type. #3221 by @cike8899 in #7340
• Feat: Create empty document. #3221 by @cike8899 in #7343
• [BREAKING CHANGE] GET to POST: enhance document list capability by @yongtenglei in #7349
• Updated RAPTOR-specific UI by @writinwaters in #7348
• Feat: Batch operations on documents in a dataset #3221 by @cike8899 in #7352
• Update Groq AI Model Config by @wemod123 in #7335
• Fix: tenant_id spelling error. by @xiaosl-cell in #7331
• Fix mcp server startup failure by @yiminghub2024 in #7329
• Feat: Preview the file #3221 by @cike8899 in #7355
• perf: Optimize GraphRAG’s LOOP_PROMPT by @liuzhenghua in #7356
• feat: replace models of novita by @neal-davis in #7360
• Fix: Add title_tks for Pictures by @Woody-Hu in #7365
• Feat: Add AsyncTreeSelect component #3221 by @cike8899 in #7377
• Fix:Update chat assistant with an empty dataset by @NintendoLink in #7354
• Knowledge graph no longer exists as a chunking method by @writinwaters in #7382
• Feat: Add support for OAuth2 and OpenID Connect (OIDC) authentication by @wengchaoxi in #7379
• Refa: similarity calculations. by @KevinHuSh in #7381
• Feat: Bind data to the agent module of the home page #3221 by @cike8899 in #7385
• fixed missing list input ref in query by @isthaison in #7375
• Feat: Adjust the style of the home page #3221 by @cike8899 in #7405
• Fix: improve recover_pending_tasks timeout by @Woody-Hu in #7408
• Refa: http API create dataset and test cases by @asiroliu in #7393
• Feat: Modify the segmented component style #3221 by @cike8899 in #7409
• feat: dataset filter by parsing status by @Woody-Hu in #7404
• Feat: Add a language switch drop-down box to the top navigation bar #3221 by @cike8899 in #7416
• Feat: add Qwen3 and OpenAI o series by @yongtenglei in #7415
• Feat: Modify background color of Card #3221 by @cike8899 in #7421
• Fix: whole knowledge graph lost after removing any document in the knowledge base by @alkscr in #7151
• Feat: Using IconFont as an additional icon library #3221 by @cike8899 in #7427
• DOC: Added a UI tip for document parsing by @writinwaters in #7430
• Feat: filler list by user change input by @isthaison in #7389
• Test: Update tests to use new fixture instead of deprecated one by @asiroliu in #7431
• Fix: create dataset remove unnecessary parameter constraints by @asiroliu in #7432
• Fix: Tried to fix the fid mis match under some cases by @Woody-Hu in #7426
• Built-in reranker models have been removed from official deliveries. by @writinwaters in #7439
• Feat: Support passing knowledge base id as variable in retrieval component by @notsyncing in #7088
• Feat: Modify the dataset list page style #3221 by @cike8899 in #7437
• Fix: change create dataset htto api delimiter default value to r'\n' by @asiroliu in #7434
• Feat: Modify the style of the dataset page #3221 by @cike8899 in #7446
• Fix: filed_map was incorrectly persisted by @yongtenglei in #7443
• Fix instructions for Ollama by @raffaem in #7468
• Fix Ollama instructions by @raffaem in #7478
• Fix:Set CUDA_VISIBLE_DEVICES In DefaultEmbedding by @Woody-Hu in #7465
• fix(deps): incorrect nltk download dir by @kowyo in #7447
• fixed errror when vars of cnt begin declare with key contain "begin" by @isthaison in #7457
• perf: optimze figure parser by @liuzhenghua in #7392
• refa: Optimize create dataset validation by @asiroliu in #7451
• Fix: Sometimes VisionFigureParser.figures may is tuple by @Woody-Hu in #7477
• Fix: chat solo issue. by @KevinHuSh in #7479
• Feat: Support knowledge base type input in agent flow debugger by @notsyncing in #7471
• fix: After the file is deleted, it still remains in the bucket. by @liuzhenghua in #7482
• docs: add API key instructions for MCP host mode by @Monster-Beast in #7496
• Feat: Improve 'user_canvan_version' delete and 'document' delete performance by @Woody-Hu in #6553
• Fix:When sharing the knowledge base of multiple tenants with one person, when this person queries the knowledge base of both tenan...

v0.18.0

Release v0.18.0 created from 94181a9 at 2025-04-23 14:11:59+08:00

New features

• MCP server: enables access to RAGFlow's knowledge bases via MCP.
• DeepDoc supports adopting VLM model as a processing pipeline during document layout recognition, enabling in-depth analysis of images in PDFs.
• Agent version control: all updates are continuously logged and can be rolled back to a previous version via export.
• Team collaboration: Agents can be shared with team members.
• OpenAI-compatible APIs: Agents can be called via OpenAI-compatible APIs.
• User registration control: administrators can enable or disable user registration through an environment variable.

Improvements

• Enhanced answer referencing: Citation accuracy in generated responses is improved.
• Enhanced question-answering experience: users can now manually stop streaming output during a conversation.

Compatibility changes

• From this release on wards, built-in re-rank models have been removed because they have minimal impact on retrieval rates but significantly increase retrieval time.

What's Changed

• Test: Added test cases for Download Documents HTTP API by @asiroliu in #6032
• Fix: optimize OCR garbage identification to reduce unnecessary filtering by @yongtenglei in #6027
• Fix: chat_completion answer data incorrect by @alen08266 in #6041
• Improve API Documentation, Standardize Error Handling, and Enhance Comments by @PStarH in #5990
• Fix: Reduce excessive IO operations by loading LLM factory configurations by @utopia2077 in #6047
• Feat: Add deepseek to llm_factories by @c-goosen in #6051
• Fix 6030 by @yuzhichang in #6070
• Fix: empty doc id validation. by @KevinHuSh in #6064
• Feat: Change “Document parser” to "PDF parser" #6072 by @cike8899 in #6073
• Feat: add token comsumption & speed to little lamp. by @KevinHuSh in #6077
• Refa: remove max toekns for image2txt models. by @KevinHuSh in #6078
• Fix: remove NaN output of components. by @KevinHuSh in #6079
• Fix executor name by @yuzhichang in #6080
• Fix: Prevent password boxes other than login passwords from displaying passwords saved in the browser's password manager by default. #6033 by @cike8899 in #6084
• Doc: update launch from source. by @KevinHuSh in #6074
• Fix: check the file name length. by @KevinHuSh in #6083
• Refa: enlarge default max request body size. by @KevinHuSh in #6088
• Fix: none parse_config updating. by @KevinHuSh in #6092
• Fix: Knowledge base page cannot upload folders #6062 by @cike8899 in #6096
• Fix: fix document concurrent upload issue by @yongtenglei in #6095
• Refa: enlarge http body size. by @KevinHuSh in #6100
• Fix: limit the depth of DFS by @KevinHuSh in #6101
• Regards kb_id at ElasticSearch insert, update, delete. by @yuzhichang in #6105
• Fix: empty tag field issue. by @KevinHuSh in #6103
• Fix: Fixed the issue that events cannot be triggered after the shadcn-ui dialog is closed #3221. by @cike8899 in #6108
• Introduced task priority by @yuzhichang in #6118
• Fix: update link of deploy_local_llm.mdx by @jingfelix in #6110
• Test: Added test cases for Update Documents HTTP API by @asiroliu in #6106
• Doc: Update readme document by @zmxccxy in #6052
• Test: update test cases per pr #6095 to fix issue #6039 by @asiroliu in #6143
• Feat: Limit view with more knowledge when list knowledge so many by @isthaison in #6093
• Feat: add OCR's muti-gpus and parallel processing support by @debugdoctor in #5972
• Fix: validation of readonly fields. by @KevinHuSh in #6144
• Fix: retrieval debug mode issue. by @KevinHuSh in #6150
• Refa: refine the error message. by @KevinHuSh in #6151
• Refa: fix re-rank scope. by @KevinHuSh in #6152
• Miscellaneous UI updates by @writinwaters in #6094
• Test: fix expected value validation for list dataset endpoint by @asiroliu in #6160
• Test: Added test cases for List Documents HTTP API by @asiroliu in #6158
• Fix: Correct parameter retrieval in thumbup api by @kuro5989 in #6114
• Test: update test cases per pr #6144 by @asiroliu in #6166
• Refa: PARALLEL_DEVICES is a static parameter. by @KevinHuSh in #6168
• Refa: Improve ppt_parser better handle list by @Woody-Hu in #6162
• Test: Added test cases for Delete Documents HTTP API by @asiroliu in #6175
• Fix: none item while concating df. by @KevinHuSh in #6176
• Feat: Improve Recognizer.py performance by @Woody-Hu in #6185
• Fix: in case response.choices[0].message.content is None. by @KevinHuSh in #6190
• Fix: NaN data error. by @KevinHuSh in #6192
• Fix: doc deletion failure with invalid docid. by @KevinHuSh in #6194
• Docs: remove max tokens. by @KevinHuSh in #6198
• Docs: rm max token by @KevinHuSh in #6202
• Fix: float transfer exception. by @KevinHuSh in #6197
• Fix: enable ollama api-key. by @KevinHuSh in #6205
• Fix: miss url path. by @KevinHuSh in #6211
• Feat: Add TreeView component #3221 by @cike8899 in #6214
• Fix: add support for non-stream response with session.ask_without_stream by @Nalkey in #6207
• Feat: add vision LLM PDF parser by @yongtenglei in #6173
• Fix: rank feat issue. by @KevinHuSh in #6225
• Feat: Alter TransferList props #3221 by @cike8899 in #6226
• Feat: text file support position retaining. by @KevinHuSh in #6231
• Fix: empty retrieval kb ids. by @KevinHuSh in #6236
• Test: Added test cases for Parse Documents HTTP API by @asiroliu in #6235
• Fix: Nan issue. by @KevinHuSh in #6242
• Fix: #5719 Added type check for parser_config by @asiroliu in #6243
• Miscellaneous updates by @writinwaters in #6245
• Fix: read flow blank template strings from i18n file by @Womsxd in #6240
• Fix: tag_feas deletion error. by @KevinHuSh in #6257
• Fix: type violations. by @KevinHuSh in #6262
• Fix: let parsing continue. by @KevinHuSh in #6259
• Feat: add TTS support for SILICONFLOW. by @KevinHuSh in #6264
• Fix: Nan response for retrieval component. by @KevinHuSh in #6265
• Fix: remove dup ids for APIs. by @KevinHuSh in #6263
• Fix: long api key issue. by @KevinHuSh in #6267
• Feat: support agent version history. by @isthaison in #6130
• Feat: Alter TreeView component #3221 by @cike8899 in #6272
• Fix: switch follow interact issue. by @KevinHuSh in #6279
• Fix: Add a basic example when the example of content_tagging is empty by @zhoujy95 in #6276
• Fix get_unacked_iterator by @yuzhichang in #6280
• Docs: Update accelerate_doc_indexing.mdx by @zangqianglei in #6268
• Fix: In the Agent's workflow, the input content cannot be wrapped, and \n will not work, otherwise an error will be reported #6241 by @cike8899 in #6284
• Feat...

v0.17.2

Improvements

• Adds OpenAI-compatible APIs.
• Introduces a German user interface.
• Accelerates knowledge graph extraction.
• Enables Tavily-based web search in the Retrieval agent component.
• Adds Tongyi-Qianwen QwQ models (OpenAI-compatible).
• Supports CSV files in the General chunk method.

Fixed issues

• Unable to add models via Ollama/Xinference, an issue introduced in v0.17.1.

Related APIs

HTTP APIs

Create chat completion

Python APIs

Create chat completion

What's Changed

• Docs: updates issue templates. by @KevinHuSh in #5913
• Reverted some of the version changes by @writinwaters in #5908
• Docs: reformat. by @KevinHuSh in #5914
• Feat: Add german translations by @HashtagAssist in #5866
• Docs: updates. by @KevinHuSh in #5921
• Optimized graphrag again by @yuzhichang in #5927
• TEST: Added test cases for Update Dataset HTTP API by @asiroliu in #5924
• Feat: Add Breadcrumb component #3221 by @cike8899 in #5929
• Fix: When calling the Create chat completion API, the response data… by @alen08266 in #5928
• Feat: apply LLM to optimize citations. by @KevinHuSh in #5935
• Fix:signal.SIGUSR1 and signal.SIGUSR2 can't use in window. so don't bind signal.SIGUSR1 and signal.SIGUSR2 in the windows env by @donblack01 in #5941
• Fix: HTTP API Updates Read-Only Dataset Fields During Modification #5923 by @RaghavPatidar18 in #5937
• Fix: ollama model add error. by @KevinHuSh in #5947
• Fix: empty value updating. by @KevinHuSh in #5949
• Refa: Optimization of the Deep Research Module Code Structure by @liwenju0 in #5959
• Fixed a Docusaurus display issue. by @writinwaters in #5969
• Fix: Add Knowledge Base Document Parsing Status Check by @liwenju0 in #5966
• TEST: Remove unstable assertion introduced in PR #5924 by @asiroliu in #5968
• Feat: Retrieval supports internet search. by @KevinHuSh in #5974
• For an Agent with an Input Begin value, on the first call the return … by @isthaison in #5957
• Feat: Why can't Retrieval component support internet web search. #5973 by @cike8899 in #5978
• Feat: Add qwq model support to Tongyi-Qianwen factory by @kuro5989 in #5981
• Feat: Alter Item to TransferListItemType #3221 by @cike8899 in #5986
• Feat: add use KG to retrieval component. by @KevinHuSh in #5988
• Feat: add CSV file parsing support by @yongtenglei in #5989
• TEST: Added test cases for Upload Documents HTTP API by @asiroliu in #5991
• Refa: refine the context window size warning. by @KevinHuSh in #5993
• Fix: encode detect error. by @KevinHuSh in #6006
• Test: update test cases per issue #5920 #5923 by @asiroliu in #6007
• Optimize graphrag cache get entity by @yuzhichang in #6018
• 0.17.1 release notes by @writinwaters in #6021
• Feat: Set the default value of Chunk token number to 512 #6016 by @cike8899 in #6017
• Fix: empty api-key causes problems. by @KevinHuSh in #6022
• DOCS: for release. by @KevinHuSh in #6023
• Added 0.17.2 release notes by @writinwaters in #6028

New Contributors

• @HashtagAssist made their first contribution in #5866
• @alen08266 made their first contribution in #5928
• @kuro5989 made their first contribution in #5981

Full Changelog: v0.17.1...v0.17.2

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