MaxKB 发行版 - Gitee.com

v2.6.0

2026-02-05 16:29

v2.6.0

## New Features
- **Agent**: Added trigger activation capability;
- **Agent (X-Pack)**: Supported setting validity period for Agent API Keys;
- **Agent**: Added **IP Address** and **Source** attributes to the conversation log list;
- **Agent**: Supported setting independent cleanup policies for uploaded files in conversation logs;
- **Tools**: Added trigger activation capability;
- **Tools**: Added the function to view execution records;
- **Shared Tools (X-Pack)**: Added the function to view execution records;
- **Triggers**: Added trigger management function for the workspace administrator role;
- **Knowledge Base**: General Knowledge Base, Web Site Knowledge Base, and Lark Knowledge Base all support direct conversion to Workflow Knowledge Base;
- **Knowledge Base**: Added support for batch exporting documents in the document list;
- **System Management (X-Pack)**: Supported setting validity period for system API Keys.

## Feature Optimizations
- **Agent**: Adjusted the position of the **Go to Conversation** button to the Agent panel;
- **Agent**: Added a **Current Moment** setting for the default value of date-type parameters entered by users; after setting, the parameter dynamically obtains the current time on the Q&A page;
- **Models**: Added support for entering the **API URL** parameter for video models and speech recognition models of Alibaba Cloud BaiLian;
- **Models**: Vector models of the Volcano Engine provider support docking with multimodal vector models;
- **Models**: Speech recognition models of the Volcano Engine provider support the docking method of speech recognition for audio files;
- **Models**: Added support for setting the **Response Type** parameter (e.g., `response_format=b64_json`) in the model parameters of image generation models of the OpenAI provider; #4538
- **System**: Optimized internationalized copy and partial UI interfaces.

## Bug Fixes
- **Agent**: Fixed the issue where the **Referenced Segment Count** and **Segment Title + Content** fields were missing when exporting conversation logs;
- **Agent**: Fixed the issue where the calling process was not displayed if a tool in skills had no input parameters when the AI model called the tool;
- **Agent**: Fixed the issue of disordered AI reply content when a sub-agent in a loop body also had a loop node (#4654);
- **Agent**: Fixed the issue where AI reply content did not automatically scroll to the bottom during Agent debugging (#4660);
- **Login Authentication (X-Pack)**: Fixed the issue where the number of failed login attempts for displaying captcha could not be set to 0;
- **Models**: Fixed the issue where the slm speech recognition model of iFlytek Spark could not convert speech to text;
- **Models**: Fixed the error when editing the iat model of iFlytek Spark;
- **Folders**: Fixed the issue where users with only folder view permissions could still create subfolders (#4688).

最后提交信息为： fix: [Tool] Trigger triggered execution tool, the execution details...

v2.5.0

f95a619

2026-02-05 16:29

v2.5.0

## New Features
- **Agent**: Upgraded the "Application" module to the "Agent" module;
- **Agent**: Added automatic agent calling function to simple agents, and merged tools, MCP, and agents into the "Skills" function;
- **Agent**: Added automatic agent calling function to AI Conversation nodes in advanced agents, and merged tools, MCP, and agents into the "Skills" function;
- **Agent**: Supported creating agents via templates in the Template Center;
- **Agent**: Added exception branch output to all AI capability nodes in advanced agents to enhance process fault tolerance;
- **Agent**: Supported displaying feedback information filled by users in conversation log details;
- **Agent**: The user input parameter component in the Basic Information node supports multi-line text boxes, single-line tab components, and single-line multi-select tab components;
- **Agent**: Input parameters in custom tool nodes support boolean type;
- **Q&A Page**: Supported users to fill in feedback information when submitting feedback;
- **Knowledge Base**: Supported canceling the document import process in workflow knowledge bases;
- **Knowledge Base**: Added workflow import/export function to workflow knowledge bases;
- **Knowledge Base**: Supported viewing associated resources;
- **Tools**: Supported viewing associated resources;
- **Tools**: Added JSON text box and slider components to the component types in parameter dialogs;
- **Folders**: Supported sorting by name, creation time, and custom drag-and-drop order;
- **Models**: Supported viewing associated resources;
- **Login Authentication (X-Pack)**: Added default role assignment function for third-party users in login settings;
- **Login Authentication (X-Pack)**: Added account lockout function after failed login attempts in login settings;
- **User Management**: Supported setting default resource permissions when creating users;
- **User Management (X-Pack)**: Supported batch role assignment and batch user deletion.

## Feature Optimizations
- **Agent**: Added conversation user group `{{global.chat_user_group}}` to the start node in advanced agents;
- **Knowledge Base**: Optimized the hit test interface to use POST requests;
- **Folders**: Supported authorizing folders by user roles;
- **API Key**: Optimized system API Keys to be isolated by user;
- **Q&A Page**: Removed the limit of only viewing 20 historical chat records;
- **Q&A Page**: Supported editing and re-submitting the last question;
- **Q&A Page (X-Pack)**: Supported logout function for third-party conversation users after logging into the Q&A page;
- **System**: Optimized the system UI interface.

## Bug Fixes
- **Security Vulnerability**: Fixed the XSS vulnerability caused by file uploads;
- **Security Vulnerability**: Fixed the issue where Python code in the tool module loaded dynamic link libraries to bypass security restrictions;
- **Security Vulnerability**: Fixed the potential RCE issue caused by deserializing untrusted objects via pickle in Celery;
- **Tools**: Fixed the false interception of emails sent via the SMTP protocol;
- **Agent**: Fixed the issue where the scroll bar of the tool drop-down box in MCP nodes could not scroll;
- **Agent**: Fixed the style issue where execution details of MCP call and tool nodes exceeded the screen;
- **Agent**: Fixed the issue where child agents could not receive video files from parent agents (#4568);
- **Knowledge Base**: Fixed the style issue where video components in segmentation details exceeded the segmentation detail area (#4542);
- **Knowledge Base**: Fixed the issue where all videos automatically played when opening the segmentation details page.

最后提交信息为： fix: update LayoutContainer to conditionally show left panel based ...

v2.4.2

b943567

2025-12-30 10:33

v2.4.2

Bug Fixes
- Applications: Fixed the incorrect jump path of the Go to Conversation button on the workflow orchestration page when the system's secondary path has been modified;
- Applications: Fixed the issue where the reference variable selection could not be canceled for tool nodes in advanced orchestration applications;
- Applications: Fixed the issue where the workflow did not terminate when a node inside the loop body threw an error;
- Applications: Fixed the inconsistency between the node order in the add component dialog and the node order in the loop body;
- Applications (X-Pack): Fixed the redirection issue on the WeChat Work QR code login page for conversation users;
- Knowledge Base: Fixed the issue where the previous page state was not retained when returning to the document list page from the document segmentation details page;
- Knowledge Base: Fixed the parsing failure issue of global variables entered in the specified reply node of the workflow knowledge base;
- Knowledge Base: Removed the historical chat record function from the Image Understanding, Video Understanding, and AI Conversation nodes in the workflow knowledge base;
- Knowledge Base: Fixed the issue where newly created vector models were not displayed in the vector model list when creating them in the knowledge base creation interface;
- Resource List: Fixed the incorrect display of the resource list when moving resources to folders in the root directory of applications/knowledge bases/tools;
- Tools: Fixed the issue where data source tools lacked parameters set during debugging;
- Tools: Fixed the issue where IPv6-mapped IPv4 addresses were not intercepted;
- API Documentation: Fixed the incorrect parameter type of the document segmentation interface.

最后提交信息为： fix: deny access to local services by IPv6 and IPv6-mapped IPv4 add...

v2.4.1

4ef20a9

2025-12-30 10:32

v2.4.1

最后提交信息为： fix: Component sequence adjustment

v2.4.0

44b1387

2025-12-30 10:32

v2.4.0

Security Vulnerability Fixes
- Fixed the permission bypass issue caused by system file overwriting (CVE-2025-66446);
- Fixed the permission bypass issue caused under specific concurrent conditions (CVE-2025-66419).
Special thanks to GitHub users @yck99, @NikoCat233, and @Threonine for discovering and promptly reporting the above vulnerabilities to the MaxKB open-source community!
New Features
- Knowledge Base: Added workflow knowledge base;
- Tools: Added data source tools;
- Tools: Tools in the Tool Store support two types: "Tool" and "Data Source";
- Models: AWS provider added support for vision models and reranking models;
- Models: Vision models of OpenAI, Ollama, vLLM, Xinference, and Zhipu AI providers support video understanding functionality;
- Models: Added support for large language models, vector models, and reranking models from the Docker AI provider;
- Applications: Added "URL Address" as an upload method in the file upload settings;
- Applications: Added ranking statistics for "User Consumed Tokens" and "User Question Count" to the monitoring statistics on the overview page;
- Resource Authorization: Supported filtering users by role when authorizing applications, knowledge bases, tools, and models to users by resource;
- Login Authentication (X-Pack): Added SAML2 login authentication method.
Feature Optimizations
- Applications: The generated prompts of AI conversation nodes in advanced applications no longer carry application names and description information;
- Applications: Supported outputting request parameters when AI models call MCP tools;
- Applications: Supported using shortcut keys to copy nodes into loop bodies in advanced orchestration;
- Tools: Supported importing three types of resources: tools, MCPs, and data sources;
- Tools: Adjusted the Tool Store entry to the tool list;
- Tools: Removed system built-in tools and moved them to the Tool Store.
Bug Fixes
- Q&A Page: Fixed the issue where retrieval results of knowledge base retrieval nodes in loop bodies were not displayed in knowledge sources;
- Applications: Fixed the incorrect display of execution time for loop nodes in execution details;
- Applications: Fixed the incorrect retrieval results when the variable value was empty in the document tag retrieval node;
- Knowledge Base: Fixed the issue where the original document could not be opened after downloading it following replacement (#4397);
- Models: Fixed the generation error of the qwen-image model from the Alibaba Cloud BaiLian provider (#4376);
- Models: Fixed the error when adding the gpt-5-codex model from the Azure OpenAI provider;
- Models: Fixed the incorrect setting of some parameters for vLLM models (#4403);
- Roles: Fixed the issue where the "About" permission authorized to workspace administrators and ordinary users did not take effect;
- Conversation Users (X-Pack): Fixed the issue where non-essential information was displayed in the conversation user query interface;
- API Documentation (X-Pack): Revised several inaccurate descriptions in the API documentation.

最后提交信息为： style: switch style

v2.3.0

d636d6e

2025-12-30 10:30

v2.3.0

New Features
- Knowledge Base: Added "Tag Management" function;
- Knowledge Base: Added "Tag Setting" function for documents in the knowledge base;
- Knowledge Base: Added "Replace Original Document" function for the general knowledge base;
- Applications: Added "Document Tag Retrieval" node to Advanced Orchestration Applications;
- Applications: Added "Video Understanding" node to Advanced Orchestration Applications;
- Applications: Added "Variable Splitting" node to Advanced Orchestration Applications;
- Applications: Added "Variable Aggregation" node to Advanced Orchestration Applications;
- Applications: Added "Parameter Extraction" node to Advanced Orchestration Applications;
- Applications: Added "Video" file type option to file upload settings;
- Applications: Added "startwith" and "endwith" judgment conditions to the Judge node;
- Applications: Added "Historical Chat Records {history}" parameter to the output parameters of the AI Conversation node;
- Applications: Added two retrieval scope options (manual selection of knowledge base and variable reference) to the Knowledge Base Retrieval node;
- Resource Authorization: Supported authorizing folder resources by user;
- Resource Authorization: Supported folder-based resource authorization for applications, knowledge bases, and tools in the workspace;
- System Management (X-Pack): Added cleaning policies to operation logs to help administrators manage log data efficiently.
Feature Optimizations
- Applications (X-Pack): Supported password-free login for users after the application is connected to WeChat Work, Lark, or DingTalk;
- Applications: Supported video file types for file uploads;
- Applications: Added URL address setting support for the "select file" parameter of Image Understanding, Image-to-Video, and Video Understanding nodes;
- Applications: Allowed Variable Assignment nodes to be used as end nodes;
- Applications: Supported batch selection of nodes on the workflow orchestration page;
- Applications: Added a description field to interface parameters;
- Applications: Adjusted the maximum value of the "Question Limit per Client" option in "Access Restrictions" to 10 million times per day;
- Applications: Added custom input support for multi-select box components in the Form Collection node;
- Applications: Displayed all applications in the current workspace in the root directory and supported global search;
- Tools: Displayed all tools in the current workspace in the root directory and supported global search;
- Tools: Added variable parsing support for custom-type parameters;
- Knowledge Base: Displayed all knowledge bases in the current workspace in the root directory and supported global search;
- Roles: Adjusted the "About" permission to the ordinary user role;
- Models: Added model parameter setting support for vector models.
Bug Fixes
- Applications: Fixed the issue where tool nodes in the loop body were not exported when exporting the application;
- Applications: Fixed the issue where nodes after the Form Collection node in the loop body could not output loop variables;
- Applications: Fixed the issue where the content of the first parameter was cleared when modifying the content of the second parameter in the MCP Call node;
- Applications: Fixed the issue where Tokens showed 0 during conversations when using the Zhipu large language model and enabling the tool function in the AI Conversation node;
- Applications (X-Pack): Fixed the issue where the history record setting option in display settings did not take effect (#4201);
- Q&A Page: Fixed the issue where uploaded files were lost when clicking the "Get Another Answer" button after uploading files and asking questions on the Q&A page (#4180);
- Q&A Page: Fixed the issue where conversation records were lost when adjusting the size of the conversation window while asking questions on the Q&A page (#4202).

最后提交信息为： fix(vector): 修复 source_type 判断类型问题

v2.2.0

f834569

2025-12-30 10:30

v2.2.0

Release Notes for MaxKB v2.2.0 Community Edition
In MaxKB v2.2.0 Community Edition, regarding Applications: Advanced Orchestration Applications have added Loop Nodes, Intent Recognition Nodes, Text-to-Video Nodes, and Image-to-Video Nodes. Simple Applications now support MCP and tool calling functions, and have newly added prompt generation capabilities. For Tools: MaxKB has launched a brand-new Tool Store, allowing users to select required tools directly without self-development. In terms of Models: MaxKB has added support for Text-to-Video and Image-to-Video models from Alibaba Cloud BaiLian and Volcano Engine.
For the X-Pack Enhancement Package: MaxKB supports default login method settings, enabling administrators to customize the system’s default login channels (e.g., account-password login, third-party login, etc.) based on enterprise needs; it also newly supports setting to enable captcha verification after N failed login attempts.
New Features
- Tools: Added Tool Store;
- Applications: Added Loop Node, Break Node, and Continue Node;
- Applications: Added Intent Recognition Node;
- Applications: Added Text-to-Video Node;
- Applications: Added Image-to-Video Node;
- Applications: Simple Applications now support MCP and tool calling functions;
- Applications: Added support for prompt generation;
- Applications: Added "Output MCP/Tool Execution Process" switch setting;
- Applications: Variable Assignment Nodes now support the bool data type when assigning values;
- Applications: MCP configuration information supports variable parsing;
- Applications: Conversation users support the setting to enable captcha verification after a specified number of failed account login attempts (X-Pack);
- Knowledge Base: Supports parameter settings for models that handle question generation tasks;
- Models: Alibaba Cloud BaiLian provider has added support for Text-to-Video and Image-to-Video models;
- Models: Volcano Engine provider has added support for Text-to-Video and Image-to-Video models;
- Models: Speech Recognition Models support model parameter settings;
- Login: Added default login method setting (X-Pack);
- Login: Added setting to enable captcha verification after a specified number of failed user login attempts (X-Pack);
- Login: Upgraded the login captcha to an authentication mechanism with user isolation functionality.
Feature Optimizations
- Q&A Page: Added a "Back to Bottom" shortcut operation;
- Knowledge Base: The question list supports the "Show 1000 Items" option setting;
- Applications: Optimized the display style of "Add Component" for Advanced Orchestration Applications;
- Applications: Optimized the descriptions of system prompts and user prompts;
- Resource Management: Added support for filtering by type in the resource list filter options (X-Pack).
Bug Fixes
- Knowledge Base: Fixed the issue where exporting a knowledge base would time out and report an error when the knowledge base contains a large amount of data (#3995);
- Applications: Fixed the issue where the thinking process was not returned when using the application API interface for conversations (#4084);
- Applications: Fixed the issue where the display order of login methods in Access Restrictions was not sorted by category (#4049);
- Applications: Fixed the issue where the "Question Limit per Client" option setting in Access Restrictions did not take effect (#4042);
- Q&A Page: Fixed the issue where the send button was not displayed on some browsers in the iOS system;
- Q&A Page: Fixed the issue where refreshing the browser on the Q&A page would open the application list page after setting the question interface parameters in the application settings (#4076);
- Q&A Page: Fixed the issue where the font style of the thinking process was incorrect (#2792);
- Models: Fixed the issue where the parameter settings for the speech synthesis model from the Silicon Flow provider did not take effect.

最后提交信息为： feat: raise error

v2.1.0

d94871b

2025-09-04 15:07

v2.1.0

## New Features
- **Tools**: Added the MCP tool management function.
- **Applications**: Added tool settings for AI conversation nodes; after users select a custom tool, the model can independently decide whether to call the configured tool.
- **Applications**: Parameters of form collection nodes now support variable reference.
- **Applications**: Added multi-line text boxes, file upload, and single-line multi-select box components to form collection nodes.
- **Applications (X-Pack)**: Application access now supports connection to WeChat Work intelligent robots, enabling users to achieve efficient linkage between AI capabilities and the WeChat Work office ecosystem.
- **Applications (X-Pack)**: Added the "Show History Records" option in display settings.
- **Q&A Page**: Supported exporting current conversation records as PDF and PNG image formats on the Q&A page.
- **Knowledge Base**: Added the "Allow Download in Knowledge Sources" setting option for documents in the general knowledge base and Lark knowledge base.
- **Resource Authorization**: Added resource-level authorization function, supporting the authorization of core resources such as applications, knowledge bases, tools, and models to specified users.
- **Resource Authorization**: When authorizing resources by user in system management, different permissions can be set for each resource.
- **Models**: Added support for reranking models and speech recognition models to the vLLM provider.
- **Models**: Added support for speech recognition models to the Tencent Hunyuan provider.
- **Models**: Added support for Chinese speech large models to the speech recognition models of the iFlytek Spark provider.
- **Models**: Added support for qwen-omni-turbo, qwen2.5-omni-7b, and ASR models to the speech recognition models of the Alibaba Cloud BaiLian provider.
- **Models**: Added support for the API Version V2 connection method to the Baidu Qianfan Large Model provider.

## Feature Optimizations
- **Applications**: Added the function of querying by user in the conversation log list.
- **Applications (X-Pack)**: After an application is connected to Lark, AI response content is displayed in Markdown format.
- **Q&A Page**: Automatically creates a new conversation by default when entering the Q&A page.
- **Q&A Page**: Optimized the issue where a default question is automatically generated when uploading files or images.
- **Tools**: Added a secondary confirmation prompt when clicking the "Close" or "Cancel" button while creating or editing a tool.
- **Login**: Users must change their default password before continuing to use the system after logging in with it.

## Bug Fixes
- **Applications**: Fixed the issue where MCP nodes in advanced orchestration applications were not internationalized.
- **Applications**: Fixed the issue where session variables could not be read when used after form collection nodes.
- **Q&A Page (X-Pack)**: Fixed the issue where the custom application Logo was not displayed in the browser tab.
- **Q&A Page (X-Pack)**: Fixed the issue where existing authentication information remained valid when switching the application's identity authentication method in the "Access Restriction" function.
- **Q&A Page**: Fixed the issue where the content display style was messed up when clicking the "Collapse" button in the left navigation area.
- **Q&A Page**: Fixed the issue where a "missing parameter" prompt appeared when a conversation user asked a question after re-logging in.
- **Q&A Page**: Fixed the issue where conversation records were not displayed in the conversation record area when loading historical record data.
- **Q&A Page**: Fixed the issue where uploading an empty file caused extraction errors.
- **Q&A Page**: Fixed the issue where tags were displayed abnormally when the content of quick questions was too long.
- **Knowledge Base**: Fixed the issue where the input box on the hit test interface was displayed incompletely when the system had no License authorization.
- **Knowledge Base**: Fixed the issue where there was no secondary confirmation when clicking the "Back" button during document upload to the knowledge base.
- **Knowledge Base**: Fixed the issue where search results were incorrect when searching by segment content in the knowledge base segment details.
- **Knowledge Base**: Fixed the issue where the same segment could be associated with the same question multiple times.
- **Knowledge Base**: Fixed the issue where the "Number of Associated Segments" count was incorrect in the question list.
- **Models**: Fixed the issue where models in the "All Models" list were not displayed in descending order of creation time.
- **Resource Authorization**: Fixed the issue where users with only knowledge base view permission could add segments in conversation logs.
- **Folders**: Fixed the issue where clicking the "Back" button in the resource details of applications and knowledge bases always returned to the root directory.
- **Conversation Users (X-Pack)**: Fixed the issue where user passwords were not synchronized when synchronizing system users.
- **Conversation Users (X-Pack)**: Fixed the issue where a new conversation user could be created successfully even without setting a user group.

最后提交信息为： fix: Model parameter save permission error (#3989)

v1.10.10-lts

4c878b0

2025-08-21 17:36

v1.10.10-lts

## New features

- Knowledge Base: Improved knowledge base search performance for complex scenarios with large amounts of data.
- Q&A Page: Users can directly submit files or images to ask questions.

## Bug Fixes

- Knowledge Base: Fixed an issue where links in web knowledge base documents could not be accessed in some cases;
- Knowledge Base: Fixed an issue where search results were inaccurate when searching by segment content in the segment details of a document;
- Applications: Fixed an issue where parameters in function nodes in advanced orchestration applications were not echoed;
- Applications: Fixed an issue where node connections in advanced orchestration applications were incorrectly connected;
- Applications: Fixed an issue where AI responses were incorrectly included in the MCP execution results;
- Applications: Fixed an issue where dragging parameters multiple times in form collection nodes caused a console error;
- Applications: Fixed an issue where clicking a quick question set in the opening line in the conversation log would call the application's answer;
- Operation Logs: Fixed a vulnerability where user passwords could be seen in the operation log; (X-Pack)
- Installation and Deployment: Upgraded the PostgreSQL database version to v15.14;
- API Documentation: Fixed several known issues.

最后提交信息为： feat: Add connection pool connection check parameters (#3905)

v2.0.2

2367b87

2025-08-21 15:39

v2.0.2

## Important Upgrades

■ Comprehensive Upgrade of Multi-Tenant Permission Management System (X-Pack)

In MaxKB V2, the multi-tenant permission management system has been fully upgraded. Through the collaboration of four modules: user management, role management, workspace, and resource authorization, an extensible multi - tenant permission management system has been built. It effectively supports the permission and resource management needs of multiple organizations, departments, and user groups, achieving precise control of permissions and resources by the system.

Role management is the core of the RBAC permission system. MaxKB V2 comes with three preset roles: system administrator, workspace administrator, and ordinary user. The system administrator has system - level management permissions, the workspace administrator is responsible for managing members and resource authorization, and ordinary users can maintain self - created and authorized resources.

In addition, MaxKB V2 supports the function of custom roles based on the system - preset roles. It allows for personalized permission configuration on the basis of inheriting the permissions of system administrators, workspace administrators, or ordinary users.

■ New Shared Resource Management Function (X-Pack)

MaxKB V2 has added a shared resource function, supporting cross - workspace resource reuse and collaboration. System administrators can uniformly manage core resources such as knowledge bases, tools, and models, and authorize them to designated workspaces. While ensuring the secure sharing of resources, it achieves a balance between sharing and control through permission control.

■ New Conversation User Management Function (X-Pack)

MaxKB V2 has also added the "conversation user management" function, supporting identity authentication on the question - asking end. Through the linkage of modules such as conversation users, user groups, application - conversation users, and knowledge base - conversation user authorization, this function realizes the management and control of users' question - asking scope and knowledge retrieval permissions. Thus, it achieves precise management of "one person, one permission" and "one group, one permission", further enhancing the security and controllability of the system. The new version of MaxKB also supports third - party authentication methods such as LDAP, OIDC, CAS, and OAuth2 to meet enterprise data security requirements.

■ Support for Managing Applications, Knowledge Bases, and Tools by Folder Directories

MaxKB V2 has upgraded its resource management capabilities. After logging in, users can enter the workspace to manage resources. Workspace resources include four core types: applications, knowledge bases, tools, and models. Among them, applications, knowledge bases, and tools can be managed by folder directories. This improvement facilitates users to classify and organize resources, conduct hierarchical management, and perform quick retrieval, greatly improving the efficiency of resource management and the convenience of use.

## Enhancements

- Resource Management: System administrators are supported to view the list of applications, knowledge bases, tools, and model resources of all workspaces;
- Knowledge Base: After uploading offline documents to the general knowledge base, the original documents will be stored, and downloading of the original documents is supported;
- Knowledge Base: The segment detail page is optimized to support the adjustment of segment order;
- Application: The knowledge base retrieval node and multi - path recall node of advanced orchestration applications have added a switch setting of "results displayed in knowledge sources";
- Application: In the "display settings" function, setting the chat background of the question - and - answer page is supported; (X - Pack)
- Application: When having a conversation in the debugging preview, the saved application configuration is used;
- Application: An entry of "go to conversation" is added to the "settings" page of the application, facilitating users to go to the question - and - answer page for conversation after adjusting the configuration;
- Question - and - Answer Page: Advanced orchestration applications support the display of knowledge sources;
- Question - and - Answer Page: The interaction and style of the question - and - answer page are optimized;
- Security: Fixed a remote command execution vulnerability in the tool module ([CVE-2025-53927](https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-5xhm-4j3v-87m4));
- Security: Fixed a potential remote command execution vulnerability during MCP calls ([CVE-2025-53928](https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-38q2-4mm7-qf5h)).

P.S.  MaxKB does not currently support direct upgrade from version v1.10.x to v2.0.x. The MaxKB team plans to release a related migration tool in September 2025.

最后提交信息为： fix: There is a tool node in the application - the tool node has st...

v1.10.8-lts

9d7a383

2025-05-22 16:53

v1.10.8-lts

## New features
- Application: MCP settings in MCP call nodes and AI dialogue nodes support Streamable HTTP protocol; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/3088
- System: Added verification code verification function when users log in. by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3117

## Enhancements  
- Login authentication (X-Pack): Support multi-level attribute mapping when connecting to OAuth2 login authentication platform.

## Bug Fixes
- Security: Fix the vulnerability of exporting knowledge base as unsafe documents (CVE-2025-4546); by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3105
- Security: Fix the vulnerability of function execution to obtain system sensitive information; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3127
- Application: Fix the problem of dialogue log export failure; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3100
- Application: Fix the problem that the document extraction node cannot extract complex table files; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3116
- Application: Fix the problem that the value of the variable will become the initial value after the form collection node is executed in the workflow; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3108
- Application: Fixed the problem that when the workflow contains a form collection node, after the AI reply is completed, the refresh page displays incorrect content; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3081
- Application: Fixed the problem that when the workflow contains a sub-application node, the number of users in the sub-application overview is incorrect;
- Application (X-Pack): Fixed the problem that in the user number statistics of the overview "Monitoring Statistics", the number of users who asked questions on corporate WeChat, public accounts, DingTalk, and Feishu were not counted;
- Knowledge Base (X-Pack): Fixed the problem that the document segmentation of Feishu Knowledge Base was incorrect;
- Function Library: Fixed the problem that when the function parameter is a non-character type and the value is empty, the function is run with an error; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3107
- Function Library: Fixed the problem that some enabled parameters of the function will be changed to "X" after disabling and then enabling the function
- Q&A page: Fixed the problem that in some cases, the question will always be displayed as the question being answered; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/3094
- Q&A page: Fixed the problem that the English words at the end of the line in the AI reply content will be split into two lines; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/3109
- Q&A page: Fixed the problem that after uploading a document on the Q&A page, the hover document will keep flashing. by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/3110

最后提交信息为： fix: The dropdown data of subsequent nodes in the form cannot be di...

v1.10.3-lts

6bc00eb

2025-04-03 17:25

v1.10.3-lts

## New features
- Application: Added MCP call node, which has the ability to act as a remote function library service. Users can select tools from the tool set provided by the MCP service for calling; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2665
- Application: Added tool calling function to AI dialogue node. After users enable and complete the configuration of MCP tool in tool settings, the large language model will autonomously call the most appropriate MCP tool to handle tasks based on the questions raised by users; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2665
- Application: Embed third-party functions to support mobile mode; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2615
- Application (X-Pack): In the display settings, support setting whether to display user question avatars and AI reply avatars;
- Function Library: Added built-in function library, including Google search, Bocha search, LangSearch, MySQL query and PostgreSQL query; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2611, @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2725
- Function Library: Added startup parameter configuration for functions; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2596
- Function Library: Support setting the function logo; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2573
- Knowledge Base (X-Pack): Support docking with Feishu Knowledge Base;
- System Settings (X-Pack): Added operation log function;
- System Settings (X-Pack): Enterprise WeChat, Feishu, and DingTalk support password-free login.

## Enhancements
- Knowledge base: Added a new operation of generating questions in the knowledge base panel operation to facilitate batch operation; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2760
- Knowledge base: When uploading files in the knowledge base, the segment preview is optimized to lazy loading mode to reduce user waiting time;
- Knowledge base: Optimize the search logic of full-text search and improve the segment recall rate; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2767
- Q&A page: The voice input in the embedded mode of the mobile terminal supports pressing and speaking, and supports releasing and sending after setting automatic sending; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2651
- Q&A page: Optimize the voice playback logic, and support streaming playback during automatic playback; @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2661
- Q&A page: Optimize the interaction of user input parameters. You need to fill in the user input parameters before entering the dialogue. After entering the dialogue page, the user input parameter settings are adjusted to the upper right corner of the question input box; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2680
- Q&A page: Optimize the problem that the user feedback operation button displays a line break after the mobile AI reply is completed; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2772
- Q&A page: After the AI reply is completed, the form data is filtered out when the user copies the answer; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2778
- Function library: Optimize the location of function permission settings and adjust them to the drop-down list of function panel operations; by @wangdan-fit2cloud in https://github.com/1Panel-
- Application: In the parameter configuration of the form collection node, support adjusting the parameter order; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2533
- Application: When a user is having a conversation, if the asker parameter is carried in the URL address, the parameter will be displayed as the questioning user in the conversation log; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2667
- Application (X-Pack): After a user asks a question in WeChat Enterprise, Feishu, or DingTalk, if no reply is received for more than 10 seconds, the system automatically replies: "Thinking, please wait";
- API Documentation (X-Pack): Accessing the Swagger document requires user identity authentication.

## Bug Fixes
- Knowledge base: Fixed the problem that the knowledge base name is not fully displayed when selecting the knowledge base page when migrating documents; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2718
- Knowledge base: Fixed the problem that the knowledge base name is not fully displayed when switching knowledge bases in the navigation bar inside the knowledge base; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2718
- Knowledge base: Fixed the problem that when the uploaded document contains an image with a title set, the image cannot be recognized; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2683
- Knowledge base: Fixed the problem that the document name after uploading a ZIP file to the knowledge base is displayed in garbled characters after decompression; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2747
- Knowledge base: Fixed the issue that when the document name is very long, the document name will be changed to "Sheet" when exporting the knowledge base; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2740
- Application: Fixed the issue that after the child application embedded in the workflow is deleted, the parent application will report an error when opening; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2743
- Application: Fixed the issue that the knowledge base search results are not output in descending order according to the similarity; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2791
- Application: Fixed the issue that the node name suffix is repeated in the workflow, causing parsing errors; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2513
- Application: Fixed the issue that when adding functions with different names in the workflow, the suffix number will be automatically added to the node name; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2513
- Application: Fix the error in setting integer value in form collection slider component; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2601
- Application: Fix the problem that the application avatar is successfully modified, but the prompt information is incorrect; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2749
- Application: Fix the problem that when multiple applications are embedded in the same page, users will be prompted that the dialogue does not exist when asking questions in different applications;
- Model settings: Fix the problem of verification error when adding Alibaba Cloud Bailian QWQ type model;
- Login authentication (X-Pack): Fix the problem that after connecting to the OAuth2 platform, the user will return the "500" error code when logging in;
- Login authentication (X-Pack): Fix the problem that multiple OUs (Organization Units) will report errors when connecting to LDAP;
- API Documentation (X-Pack): Fixed an issue where incorrect parameters were output in the OpenAI dialogue interface of the API documentation.

最后提交信息为： fix: During the debugging process, the browser voice will automatic...

v1.10.2-lts

bc3dcda

2025-03-06 15:09

v1.10.2-lts

## New features
- Application (X-Pack): Application access now supports Slack;
- Application: Add variable assignment node; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2346
- Function library: Support import/export functions; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2294
- Model settings: Add support for Ollama supplier reordering model;

## Enhancements
- Application (X-Pack): After starting the thinking process, optimize the reply process in WeChat for Business, Feishu, DingTalk, and public accounts;
- Application (X-Pack): Support uploading pictures during WeChat for Business conversations;
- Application (X-Pack): Support configuring scope parameters for login authentication OIDC settings;
- Application: Support creating blank applications; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2377
- Application: Add support for password box and switch components for user input parameters; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2307
- Application: User input supports custom titles; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2313
- Application: Add support for password box components for parameters of form collection nodes; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2307
- Application: Add m4a format to the uploaded audio file type; by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/2277
- Application: Support uploading file parameters when conducting a conversation by calling the application API Key; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2300
- Application: By calling the application API Key mode, support output of thinking process parameters; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2392
- Application: The parameters in the user input table in the basic information node support drag-and-drop adjustment of the order;
- Application: The conditional value in the judgement supports variable parsing; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2311
- Application: In the "Execution Details" dialog box of the multi-way recall node, optimize the segment display content (including segment title, document and knowledge base); by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2309
- Application: When the user exits the workflow editing, prompt the user to save the data; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2312
- Application: The maximum number of reference segments of the associated knowledge base is adjusted to 10,000; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2487
- Application: The operation of modifying the node name in the advanced arrangement is changed to "..." → "Rename"; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2432
- Application: When a single image generation node generates multiple images, the images are arranged horizontally; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2423
- Q&A page: Optimize the Q&A page layout to a left-right layout, with AI answers displayed on the left and user questions displayed on the right; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2258
- Q&A page: Optimize the display of historical conversation records when users open the Q&A page; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2301
- Q&A page: Optimize voice playback to play only the last content; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2431
- Q&A page: Support modifying the session title; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2348
- Knowledge base: Support the continued generation of questions for the segment that failed to generate questions; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2299
- Knowledge base: Support sorting the document list; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2284
- Knowledge base: Support using the {title} variable to obtain the segment title in the generated question; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2310
- Function library: ignore case when querying functions; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2279
- Model settings: ignore case when querying models; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2279
- Team members: ignore case when querying members; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2279
- System: optimize the problem of long time consumption when logging in for the first time. by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2414

## Bug Fixes
- Application: Fixed the problem that the image in the AI reply content cannot be enlarged; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2327
- Application: Fixed the problem that the prompt word window in the advanced arrangement is not saved after editing the content after enlarging the prompt word window and pressing the ESC key to close the window; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2312
- Application: Fixed the problem that the answer cannot be ended in some cases when using the vLLM supplier's large language model for dialogue; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2375
- Application: Fixed the problem that the tokens calculation is inaccurate when using the Kimi supplier's large language model for dialogue; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2326
- Application: Fix the problem that the parameter setting is not updated after the image generation node switches the model;
- Application: Fix the problem that when the Excel table contains data from merged cells, the data is missing when reading; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2265
- Application: Fix the problem that the OpenAI call format does not have the thinking process parameter; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2392
- Application: Fix the problem that if there is a non-mandatory parameter in the application child node, if the parameter is not set in the parent application, an error will be reported during the dialogue; by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/2278
- Application: Fix the problem that the Ollama supplier's large language model uses the num_ctx parameter, and an error will be reported during the dialogue. by @itaa in https://github.com/1Panel-dev/MaxKB/pull/2444
- Q&A page: fix the problem that the browser cannot play voice in the historical conversation record; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2378
- Q&A page: fix the problem that refreshing the page will delete the current conversation when asking the first question after creating a new conversation; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2428
- Q&A page: fix the problem that line breaks cannot be inserted in the middle of the content in the question box; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2258
- Q&A page: fix the problem that "/" is automatically added after the URL address of the document in some cases, resulting in inaccessibility;
- Q&A page (X-Pack): Fix the problem that the new dialogue on the Q&A page is not displayed after turning off the history in the display settings;
- Function library: fix the problem that the output result during debugging is displayed incorrectly when the function return value is 0; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2413
- Model Settings: Fix the error when adding Alibaba Cloud Bailian's large language model, if it is a full-modal model submission; by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/2302
- Model Settings: Fix the error when adding the DeepSeek -R1 model to the Azure OpenAI provider; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2483
- System Settings (X-Pack): Fix the problem that the interface parameters in the Swagger document are not fully displayed;
- System Settings (X-Pack): Fix the problem that the Q&A page does not display the application name after setting the website name in the appearance settings;
- System Settings (X-Pack): Fix the problem that the default logo flashes when the login page is loaded.

最后提交信息为： fix: Team management remove button nationalization (#2504)

v1.10.1-lts

0640d4c

2025-03-04 16:23

v1.10.1-lts

## New features
- Model settings: Added a large language model for the atomic capability provider of Tencent Cloud Knowledge Engine. by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/2158

## Enhancements
- Application: Optimize the problem of slow opening of the workflow orchestration page when there are too many nodes in the advanced orchestration application; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2250
- Application: Optimize the filtering of form data in the historical chat records sent to the AI model to avoid affecting the AI answer; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2256
- Application: Optimize the description of output thinking settings;
- Application: Optimize the advanced orchestration application, the debug preview dialog window will only be closed when the "Close" button is clicked. by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2248

## Bug Fixes
- Knowledge base: Fixed the problem that when setting the title to the association problem when uploading files, the actual association is not successful; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2255
- Knowledge base: Fixed the problem that the upload error occurs when the uploaded folder contains subfolders; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2259
- Knowledge base: Fixed the problem that the upload error occurs when the uploaded folder contains hidden files; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2259
- Application: Fixed the problem that the document content extraction node in the execution details displays the wrong text; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2223
- Application: Fixed the issue that the document content extraction node reports an error when the uploaded Excel document has a blank sheet; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2259
- Application: Fixed the issue that the occasional reply "Sorry, no relevant content was found. Please re-describe your question or provide more information."; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2256
- Application: After the application reaches the upper limit of the number of questions, the English prompt information is incorrect; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2223
- Application: Fixed the issue that the column name in the exported conversation log file is not displayed accurately; by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/2246
- Application (X-Pack): Fixed the issue that the theme color and header font color cannot be set after clicking "Restore Default" in the display settings;
- Application (X-Pack): Fixed the issue that after clicking "Restore Default" in the display settings, the language will display null or undefined;
- System Settings (X-Pack): Fixed the issue that DingTalk users who are not in the organization can also scan the code to log in successfully;
- System Settings (X-Pack): Fixed the issue that the user's email information is not fully obtained after the DingTalk user scans the code to log in;
- System Settings (X-Pack): Fixed the issue that there should be no language setting operation in the platform settings preview.

最后提交信息为： build: update build-and-push.yml.

v1.10.0-lts

50f2c96

2025-03-04 16:22

v1.10.0-lts

## New features
- Application: Support output thinking process settings; by @shaohuzhang1,@liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2158
- Application: Support setting thinking process labels; by @shaohuzhang1,@liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2158
- Application: Support automatic sending of voice input; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1971
- Application: Support automatic voice playback; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1971
- Application: Add language settings for the Q&A page in the display settings; by @shaohuzhang1,@liuruibin,@wangdan-fit2cloud,@wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/2011
- Model settings: Support large language models, vector models, rearrangement models, speech recognition and image generation models from SILICONFLOW; by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/2127
- Model settings: Support large language models and visual models from Anthropic; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1974
- Model settings: Support vector models and image understanding models from vLLM; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2038
- Model settings: support vector models of Doubao suppliers; by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2006
- System management: support system language switching, the first batch supports simplified Chinese, traditional Chinese and English. by @shaohuzhang1,@liuruibin,@wangdan-fit2cloud,@wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/2011

## Enhancements
- Application: optimize the style display problem of uploaded files when users ask questions; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/2061
- Application: you can right-click to quote or copy the AI reply content. by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/2005

## Bug Fixes
- Knowledge base: Fixed the problem of error when uploading offline files when the file name exceeds 128 characters; by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1962
- Application (X-Pack): Fixed the problem of incomplete reply content in WeChat for Business;
- Application: Fixed the problem of error when the opening remarks exceed 4096 characters; by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/2075
- Application: Fixed the problem that the uploaded document cannot read the document content after creating a new conversation on the Q&A page;
- Application: Fixed the problem that the parameters in the added application subnode are not updated in real time. by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1962

最后提交信息为： docs: Update README.md (#2207)

v1.9.0

9d96ed3

2025-03-04 16:19

v1.9.0

## 新增功能
- 知识库：知识库和文档支持导出Excel文件与离线图片的ZIP包；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1869
- 知识库：上传文档选择文本文件类型时，新增XLS、XLSX、CSV、ZIP文件格式；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1869
- 知识库：上传文档选择QA问答对类型时，新增ZIP文件格式；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1869
- 应用：新增图片生成节点；by @liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1812
- 应用：支持上传音频文件；by @liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1787
- 应用：新增语音转文本节点；by @wxg0103,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1827
- 应用：新增文本转语音节点；by @wxg0103,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1827
- 应用：支持导出和导入应用；by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1836
- 应用：工作流节点支持设置执行条件；by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1888
- 应用（X-Pack）：支持接入企业微信的微信客服；
- 应用（X-Pack）：公众号、企业微信、微信客服支持语音提问和语音回答；
- 模型设置：创建模型时，支持设置模型参数；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1911
- 模型设置：图片理解模型新增支持Gemini供应商； by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1857
- 模型设置：图片理解模型新增支持Azure OpenAI 供应商；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1857
- 模型设置：图片理解模型新增支持阿里云百炼 供应商 by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1844
- 模型设置：图片理解模型新增支持Xinference、Ollama、豆包供应商； by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1812
- 模型设置：图片生成模型新增支持Xinference、OpenAI、腾讯混元、通义千问、智谱AI、豆包、阿里云百炼、Azure OpenAI供应商；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1812
- 模型设置：向量模型新增支持Azure OpenAI供应商；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1868
- 模型设置：语音识别模型新增支持Azure OpenAI供应商；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1872
- 模型设置：语音合成模型新增支持Azure OpenAI供应商；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1872
## 功能优化
- 知识库：文档列表支持批量取消向量化和批量取消生成问题；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1896
- 应用：基本信息节点中的“用户输入“参数，添加参数时支持设置“显示默认值”选项；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1890 
- 应用：表单收集节点的参数支持设置“显示默认值”选项；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1890
- 应用：对话URL支持携带“question=问题”参数，打开对话页面时自动发送问题；
- 应用：上传图片时自动生成“请解析图片内容”的问题；
- 应用：优化工作流节点的执行效率；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1913
- 模型设置：Amazon Bedrock供应商添加大语言模型时，支持ProxyURL参数。by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1901
## 问题修复
- 安全：修复函数库模块中远程命令执行的安全漏洞（[CVE-2024-56137](https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-76w2-2g72-cg85)）；by @liqiang-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1856
- 应用：修复浮窗对话框中不显示“新建对话”按钮的问题；
- 应用：修复浮窗对话框右上角的icon颜色不一致的问题；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1941
- 应用：修复历史应用进行对话时会提示“缺少上下文类型”错误的问题； by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1926
- 应用：修复使用低版本浏览器进行对话时报错的问题；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1870
- 应用：修复执行复杂工作流时，在部分情况下会漏执行节点的问题。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1913

最后提交信息为： fix: Generate a problem with continuous clicking without response (...

v1.8.0

a3e7fcb

2025-03-04 16:19

v1.8.0

## 新增功能

- 应用：用户提问时支持上传文档和图片；by @liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1602
- 应用：工作流新增文档内容提取节点；by @liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1602
- 应用：工作流新增图片理解节点；by @liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1602
- 应用：工作流新增表单收集节点；by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1608
- 应用：工作流支持嵌入应用节点；by @wxg0103,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1598
- 应用：工作流画布支持收起或展开全部节点以及一键美化布局；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1644
- 应用：基础节点的用户输入参数中，支持多选框和选项卡组件；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1651
- 应用：开场白支持HTML渲染； by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1608
- 应用：支持批量将对话日志添加到知识库；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1606
- 应用：支持按创建者显示应用； by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1546
- 知识库：支持按创建者显示知识库；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1546
- 函数库：支持按创建者显示函数；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1546
- 模型设置：支持通义千问供应商的图片理解模型；by @liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1602
- 模型设置：支持OpenAI供应商的图片理解模型；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1545
- 模型设置：支持腾讯混元供应商的图片理解模型；by @liuruibin,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1602
- 模型设置：支持阿里云百炼供应商的大语言模型；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1642
- 系统管理（X-Pack）：支持OAuth2单点登录方式；by @wxg0103

## 功能优化

- 知识库：优化文档状态，显示向量化和生成问题的进度详情；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1674
- 应用：基础节点的用户输入参数中，单选框组件支持标签、选项值的设置方式；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1719
- 应用：对话详情页面对AI回复内容进行标注时，保留上一次所选的知识库文档；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1606
- 应用：优化对话日志列表的显示顺序，按最近对话时间降序排序； by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1645
- 应用：优化打开对话详情时，默认显示最新对话记录。by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1645

## 问题修复

- 知识库：修复PDF文档中若包含不能识别的特殊字符时，上传文档会报错的问题； by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1640
- 知识库：修复部分情况下为“成功”状态的文档生成问题时，无法下发任务的问题；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1727
- 知识库：修复由于网站编码问题，导致web站点知识库无法获取文本内容的问题； by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1743
- 系统管理：修复拥有知识库管理权限的成员，无法查看知识库的问题；by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1740
- 系统管理（X-Pack）：修复拥有应用查看权限的成员，能够修改应用接入配置的问题。by @wxg0103

最后提交信息为： fix: 修复执行详情图片理解样式

v1.7.0

44b3aed

2024-10-31 18:08

v1.7.0

## 新增功能

- 知识库：支持知识库文档自动生成关联问题；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1339
- 应用：工作流节点支持多进多出；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1362
- 应用：支持设置语音播放的声音和语速；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1402
- 应用：支持查看和恢复历史版本；by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1386
- 应用：支持设置对话日志的清除策略；by @wxg0103  in https://github.com/1Panel-dev/MaxKB/pull/1486
- 应用：高级编排应用支持自动保存设置，默认不开启，开启后默认5分钟保存一次；by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1517
- 应用：工作流编排界面在添加组件时支持按名称查询组件；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1358
- 模型设置：支持自定义大语言模型和语音合成模型的参数；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1458
- 模型设置：支持按模型类型、创建人、权限查询模型；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1358
- 模型设置：模型面板中增加创建人信息；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1358
- 模型设置：支持阿里云百炼的向量模型；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1392
- 模型设置：支持 Amazon Bedrock 的向量模型；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1399
- 模型设置：支持腾讯混元的向量模型；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1400
- 模型设置：支持讯飞星火的向量模型；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1393
- 模型设置：支持百度千帆的向量模型；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1394
- 模型设置：支持阿里云百炼的语音识别和语音合成模型； by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1340
- 模型设置：支持 Xinference 的语音识别和语音合成模型；  by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1349
- 问答页面：支持个性化显示设置；（X-Pack）by @wxg0103,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1428
- 问答页面：支持身份验证；（X-Pack）by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1370
- 系统设置：支持企业微信、钉钉、飞书扫码登录。（X-Pack）by @wxg0103

## 功能优化

- 应用：基础节点的全局变量优化为用户输入和接口传参两个参数表单；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1410
- 应用：关联知识库时支持按名称查询知识库；by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1338
- 应用：关联知识库的名称过长时增加悬浮显示；by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1338
- 应用：`知识库检索结果` 和 `满足直接回答的分段内容`中包含分段标题；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1377
- 应用：导出高级编排应用时包含知识库检索节点的引用分段数据；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1377
- 应用：在语音输入时，控制台不再输出调试信息；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1346
- 函数库：优化函数中 Python 编辑器组件，使得编写函数体验更友好；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1328
- 团队管理：设置资源权限时增加全选按钮；by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1335
- 模型设置：创建模型时，支持按模型类型筛选供应商；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1384
- 模型设置：优化供应商列表的显示顺序和分类，将供应商划分为公有模型供应商和私有模型供应商；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1359
- 系统设置：优化修改密码的逻辑，先验证两次密码是否一致，再发邮件验证码。by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1459

## 问题修复

- 知识库：修复导入 License 文件后，会显示一次 License 过期的提示的问题；（X-Pack）by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1429
- 知识库：修复当导出空知识库时，打开导出文件报错的问题；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1501
- 知识库：修复当知识库文档中图片不存在时，AI 回复内容显示异常的问题；by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1483
- 知识库：修复在知识库上传 DOCX 文件后，部分情况下图片未正常导入的问题；by Henry-Shaw in https://github.com/1Panel-dev/MaxKB/pull/1482
- 知识库：修复在知识库上传 PDF 文件，选择高级分段时，设置分段长度不生效的问题；by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1488
- 知识库：修复在知识库分段中插入 MarkDown 流程图，不显示文本内容的问题；
- 应用：修复当应用使用的模型为豆包智能体模型时，接入企业微信提问不回复的问题；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1425
- 应用：修复知识来源引用分段的文件名过长时，界面显示错乱的问题；
- 应用：修复在接入的公众号中提问时，若回复内容在图片后面有文本内容, 无法返回图片的问题；（X-Pack）
- 模型管理：修复添加 Xinference 模型时，如果模型名称和 ID 不一致，无法添加模型的问题；by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1390
- 模型管理：修复添加 Xinference 模型时，没有传认证参数导致提示 API 域名无效的问题。by @dolphinlife in https://github.com/1Panel-dev/MaxKB/pull/1334

最后提交信息为： fix: 修复模型参数修改后,未清除旧数据

v1.6.1

9aeb68c

2024-09-29 20:12

v1.6.1

最后提交信息为： fix: 修复段落过长导出知识库报错

v1.6.0

c78f216

2024-09-27 11:55

v1.6.0

## 新增功能
- 【应用】支持语音方式问答。by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1120
- 【应用】支持使用重排模型进行多路召回。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1121
- 【应用】支持自定义全局变量。by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1146
- 【应用】支持标准OpenAI格式对话。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1128
- 【应用】支持渲染ECharts图表和HTML页面。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1173,https://github.com/1Panel-dev/MaxKB/pull/1175
- 【知识库】支持上传Excel和CSV表格文档。by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1083
- 【知识库】支持对多个文档进行批量重新向量化操作。
- 【知识库】支持问题批量关联分段。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1235
- 【函数库】支持自定义设置函数权限与状态。by @shaohuzhang1,@wangdan-fit2cloud  in https://github.com/1Panel-dev/MaxKB/pull/1189
- 【模型管理】支持对接豆包、讯飞星火、OpenAI供应商的语音识别、语音合成模型。by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1102
- 【模型管理】支持对接阿里云百炼、Xinference以及本地模型的重排模型。by @shaohu    zhang1 in https://github.com/1Panel-dev/MaxKB/pull/1121
- 【应用】支持一键接入企业微信、钉钉、飞书和微信公众号。（X-Pack）
- 【外观设置】支持自定义主题色、项目信息等设置。（X-Pack）

## 功能优化
- 【知识库】优化PDF文档支持按目录章节进行分段。by @liuruibin in https://github.com/1Panel-dev/MaxKB/pull/1124
- 【应用】AI模型的参数设置中最大输出token数最大值调整为10w,由用户自行控制大小。by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1192
- 【应用】显示设置中浮窗入口图标按用户上传的图片大小显示，最大支持500*500。(X-Pack)
- 【应用】优化简易应用的设置，提示词分为无引用知识库提示词和引用知识库提示词。 by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1182
- 【应用】简易应用的问题优化调整至 关联知识库的参数设置中，且支持设置提示词。by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1182
- 【应用】简易应用的多轮对话调整为历史聊天记录，可自定义设置历史记录数。by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1182
- 【应用】简易应用调试预览的应用logo上可自定义上传应用头像。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1195
- 【应用】高级编排应用的节点支持展开和收起，节省画布空间。
- 【应用】高级编排应用点击节点右侧+ 可直接添加节点。by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1276
- 【应用】新增系统变量历史聊天记录和对话ID。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1203
- 【应用】对话日志详情中修改标注内容时支持Markdown样式编辑。
- 【问答页面】优化换个答案的图标。by @shaohuzhang1,@wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1223
- 【用户管理】优化创建用户的用户名规则。by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1193
- 【系统】优化弹窗只能点保存或者关闭退出，避免编辑过程中误退出。

## 问题修复
- 【知识库】修复语雀导出的word，导入知识库是空白的问题。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1249
- 【知识库】修复上传空白PDF文件报错的问题。
- 【应用】修复开启多轮对话，提问30秒以上不携带历史对话记录的问题。 by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1122
- 【应用】修复AI模型的参数设置中最大输出Tokens的提示描述错误的问题。 by @wxg0103 in https://github.com/1Panel-dev/MaxKB/pull/1192
- 【应用】修复通过应用的API Key进行对话时，若stream设置为false会报错的问题。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1289
- 【应用】AI对话节点，修复混元模型设置角色设定后，对话报错的问题。by @shaohuzhang1 in https://github.com/1Panel-dev/MaxKB/pull/1236
- 【团队成员】修复团队成员过多时会出现超出边界的问题。by @wangdan-fit2cloud in https://github.com/1Panel-dev/MaxKB/pull/1276

最后提交信息为： fix: 添加组件函数库滚动条无法滚动

GVP飞致云/MaxKB

搜索帮助

GVP 飞致云/MaxKB