Releases: dataelement/bisheng
v2.4.0-beta1
🚀 BISHENG 2.4 beta1
🧩 1. Enhanced Workflow Core Capabilities
🔀 1.1 Input Node Logic Refactor & Enhancements
- Strategy decoupling: The file-handling strategy for input nodes has been split out, allowing you to choose among:
- Parse content (extract text)
- Do not parse (keep the original file for multimodal/code nodes)
- Save to a temporary knowledge base
This better supports a wide range of business scenarios.
- Smart recommended questions: Supports configuration to automatically generate and display three recommended questions based on historical conversation context.
🖼️ 1.2 Report Node Rendering Optimization
Now supports recognizing Markdown headings and bold styling, and automatically converting them into corresponding Word document styles to improve the visual quality of exported documents.
🖥️ 2. Multimodal Support in Workbench Daily Mode
A new backend vision capability toggle has been added. When enabled, uploaded images can be semantically understood via a multimodal model, instead of relying on OCR text recognition.
🧠 3. Deep Integration with DeepSeek-V3.2
DeepSeek-V3.2 is the first model to incorporate “thinking” into tool usage (historically, DeepSeek’s official model APIs—including R1-0528—could not call tools in thinking mode). In this iteration, we deeply adapted DeepSeek-V3.2 and resolved tool-calling errors encountered when assistants use DeepSeek-V3.2.
🔧 4. Other Improvements & Bug Fixes
Includes multiple optimizations such as:
- Support for high-availability deployments
- Drag-and-drop file upload in the chat input box
- Ability to configure whether “灵思模式” is displayed
- Audit logs now cover daily-mode sessions
Also fixes an issue where switching the embedding model for the knowledge base did not take effect.
💡 5. Notes
This upgrade changes certain fields returned by the workflow API. Specifically: in the Input Node → Form Input Mode → File-type form, the form key is now automatically generated by the backend.
📢 6. Skill Module Deprecation Notice
As an early application-building approach in BISHENG, the skills (langflow) module has become difficult to use due to an excessive number of components and unintuitive orchestration logic, and its capabilities have been superseded by workflows and assistants. Therefore, starting from 2.4 release, we will deprecate and remove the skills module.
v2.3.0-release
🚀 BISHENG 2.3-Release
📊 1. Prebuilt Dashboards & Data Insights
- Open-source edition: Comes with standard prebuilt dashboards covering four core metrics: number of users, number of apps, number of knowledge bases, and user feedback.
- Commercial edition (Business Expansion Suite): Provides full dashboard coverage out of the box, supports customizing component dimensions and metrics based on 11 intermediate tables, and enables multi-dashboard management.
🎨 2. Dashboard Management & Personalization (Commercial Feature)
🔄 2.1 Full Lifecycle Management: Supports the full lifecycle of dashboards, including creating, duplicating, renaming, deleting, publishing, sharing, and taking offline. The admin console supports role-based permissions for dashboard management and usage.
✨ 2.2 Drag-and-Drop Layout & Interactions: Allows dashboard components to be freely dragged, resized, and duplicated, and supports full-screen presentation mode.
📈 2.3 Rich Dashboard Components: Built-in components include bar charts (basic/stacked/grouped), horizontal bar charts (basic/stacked/grouped), line charts (basic/stacked/area), pie charts, donut charts, KPI cards, plus a global time filter component, meeting diverse data visualization needs.
🔧 2.4 Advanced Chart Configuration: Supports drag-and-drop configuration of dimensions/metrics, custom number formatting, advanced filtering and sorting, and personalized styling.
🌍 3. Other Improvements
📚 3.1 Knowledge Base File Parsing Improvements: Improved processing logic for docx and ppt files, addressing parsing failures in certain edge cases.
👥 3.2 System Management Improvements: Supports role-based access control for “Workspace” and “Admin Console” spaces, and adds audit logs for dashboard-related actions.
v2.3.0-beta4
🚀 BISHENG 2.3-beta4 Version
🌐 1. Start node supports “Custom Global Variables”: Declare variables (e.g., city, role) in the start node and flexibly reuse them in other nodes to avoid rewriting prompts.
⚡ 2. Workflow API supports runtime parameter overrides: On the first call to the /api/v2/workflow/invoke endpoint, you can temporarily modify a specified node’s configuration via the override parameter (e.g., prompts, knowledge base ID), addressing the need for “one template, personalized for each user.” See details >> https://dataelem.feishu.cn/wiki/ZjIywYGZliClIgkg2jFcP4xunjh#YgH2dpyiWoK1VwxjyQgc0fm6nZe
v2.3.0-beta3
📖 1. Workspace Optimization: Added support for selecting backend organization knowledge bases in daily mode conversations within the workspace, enabling a more convenient RAG Q&A experience.
🌍 2. Enhanced Internationalization for Built-in Tools: Tianyancha and stock market tools now support proxy configuration, resolving accessibility issues outside mainland China.
🛠 3. Bug Fixes: Resolved several issues including doc file parsing failures and workflow report node deletion errors.
v2.3.0-beta2
🌍 1. Internationalization Enhancements: Added comprehensive multi-language support to improve the experience for overseas enterprise users
📊 2. Data Dashboard Capability Build-out: Completed the design and implementation of underlying database table structures for data dashboard features
✨ 3. Documentation Knowledge Base Experience Optimization: Added support for native Excel / CSV file preview
🛠 4. Bug Fixes:
- Fixed an error that occurred when the assistant accessed the knowledge base
- Fixed a runtime issue in workflow conditional branch nodes when using the “contains” condition
v2.3.0-beta1
🚀 BISHENG 2.3-beta1
📋 1. Metadata support for the Document Knowledge Base
Provides fine-grained document organization and retrieval for the knowledge base, enabling precise document recall in workflows.
1.1 🏷️ Knowledge base–level metadata definitions: supports three data types—String, Number, and Time; provides six built-in metadata fields (document_id, document_name, upload_time, update_time, uploader, updater).
1.2 📝 Document-level metadata assignment: flexibly add, edit, and delete metadata tags for individual documents.
1.3 🔍 Workflow metadata filtering: retrieval/Q&A nodes for the document knowledge base support metadata filtering; supports multi-condition combinations (AND/OR) and rich filter operators.
1.4 🔌 API support: provides APIs for metadata create, read, update, and delete (CRUD).
🛠️ 2. Feature optimizations & experience improvements
2.1 🎨 Model management optimizations: "通义千问" renamed to "阿里云百炼"; the Model Hub adds quick links to obtain API keys and documentation for 10 major vendors.
2.2 ⚡ Better usability: real-time sync updates for preset questions/variable references in workflows, optimized permissions for model fine-tuning, and other improvements.
v2.2.0
🚀 BISHENG 2.2-release Version
🎙️ 1. Workspace supports voice interaction (ASR+TTS):
1.1 Speech input (ASR): Click the “microphone” icon in the input box to dictate text directly.
1.2 Voice playback (TTS): A new “speaker” icon appears next to AI replies; click it to listen to the audio readout.
1.3 Model support: In the admin system’s model settings, you can configure ASR and TTS models. Provider formats from OpenAI, Azure, and 通义千问 are supported.
✨ 2. Conversation experience upgrades:
2.1 Enhanced Markdown rendering: Conversation content now supports rendering Echarts charts and Mermaid flowcharts.
2.2 Conversation sharing: A new “Share” button lets you generate a public, read-only link to safely share conversation results with others.
💡 3. Workflow RAG capability upgrades
3.1 New “Knowledge Base Retrieval” node: A standalone document knowledge base retrieval node for use within workflows, allowing developers to perform retrieval operations more flexibly and obtain structured results (including metadata and text).
3.2 Advanced retrieval settings: “Advanced retrieval settings” are now available in both the “Knowledge Base Retrieval” node and the existing “Document Knowledge Base Q&A” node. You can adjust hybrid retrieval weights (keyword vs. vector), result length, and enable a Rerank (re-ranking) model for secondary ranking.
🎛️ 4. Model management optimizations
4.1 Advanced model parameters: Model management (LLM/Embedding) supports advanced parameter configuration. You can pass vendor-specific parameters (e.g., for 阿里云, 火山引擎) in JSON—such as temperature, enable_thinking—to support configuring hybrid “thinking” model modes and related needs.
4.2 Baidu Qianfan Cloud Platform authentication logic update: Qianfan has switched to an OpenAI-compatible mode (using Base URL and API Key). Users of Baidu models, please update your configuration.
🔐 5. App/Tool admin permissions: Apps (workflows, assistants, skills) and tools now support assigning “admin permissions” to facilitate team collaboration and management.
📚 6. Knowledge base management optimizations: The QA knowledge base now supports “Duplicate” and “Settings” (including changing the embedding model).
🛠️ 7. Historical knowledge base defect fix
7.1 Defect description: When the Document Knowledge Base and the QA Knowledge Base use the same embedding model, modifying content in either may affect the other’s data in Milvus, leading to unexpected retrieval results.
7.2 Root cause: In Milvus’s partition mode, multiple knowledge bases using the same embedding model share one collection. The files in the Document Knowledge Base and QA pairs in the QA Knowledge Base may have conflicting file_id values (different tables with auto-increment IDs). Therefore, operations on items with the same file_id—files or QA pairs—will affect the counterpart’s data in Milvus.
7.3 Fix: ① Upgrade to the 2.2 release; ② Use the script (https://dataelem.feishu.cn/wiki/WNqbwm8zyiPo9ukIw5ecCWcfnPe#share-MTpPdLnTXo0hl3xN7PqcXp6NnBe) to scan for problematic knowledge bases; ③ Run the script as needed to repair all knowledge bases.
V2.2.0-beta3
BISHENG 2.2-beta3
🚀 1. Linsight Result File Export (Word / PDF):
Markdown documents can now be exported to Word (.docx) or PDF format with a single click.
⚙️ 2. Enhanced File Display for Code Executor:
Files generated by the Code Executor (including both E2B mode and Local mode) are now directly displayed within task results.
🧑 3. Upgraded Human-in-the-Loop Capabilities:
When Linsight proactively requests user assistance, the popup now supports file upload and drag-and-drop.
✨ 4. Experience Optimizations:
4.1 A new “Feedback Only” button is added to task results, allowing users to submit feedback without rerunning the task. Submitted feedback is viewable in the backend.
4.2 Tool invocations now display timestamps.
4.3 The task description area now shows uploaded file information from users.
v2.2.0-beta2
BISHENG 2.2.0-beta2
🚀 1. Linsight Featured Cases — “make similar” is now live
1.1 🏠 Workbench home now showcases Linsight Featured Cases: pulled from the backend Featured Case library. Each case card supports “make similar” and “View Case.”
1.2 🧾 Generation logic for “make similar”: in this mode, the SOP is generated directly from the specified featured case, without retrieving from the SOP library.
🗂️ 2. Backend Featured Case Management
2.1 🧑💻 Guidance Manual Library schema extended: added Creator and Featured fields.
2.2 ⭐ Mark as Featured Case: when importing from execution history into the Guidance Manual Library, a new Guidance Manual / Run Results tab is available; you can preview historical run results and mark manuals that include run results as Featured Cases.
📚 3. Linsight task flow now supports viewing knowledge-base & web search results: during task execution, a drawer modal lets you view the returned content from the knowledge-base search tool and the web search tool.
🔌 4. Web search tool: added two search engines — cloudsway and searXNG.