Skip to content

Releases: aingdesk/AingDesk

v1.2.4

27 May 08:00
Compare
Choose a tag to compare
  • Add support for the Qwen3 model
  • Optimize result parsing for certain search engines
  • Add OCR support for pure image PDFs (macOS requires manual installation of Poppler)
  • Improve the effect of using search engines in agent scenarios
  • Optimize parsing of MCP tool invocation results
  • Fix various identified bugs

v1.2.3

18 Apr 03:37
Compare
Choose a tag to compare
  • Fix compatibility with OpenAI GPT-O3
  • Resolve issue where using a third-party embedding model to create a knowledge base resulted in a "model not found" error
  • Optimize the model selector

v1.2.2

16 Apr 06:41
Compare
Choose a tag to compare
  • Add automatic update mechanism (Windows version only)
  • Fix issues with combined invocation of knowledge base, agent, and tools
  • Resolve other known issues

v1.2.1

14 Apr 10:40
Compare
Choose a tag to compare
  • Add MCP client functionality (configure the MCP server in settings, then select the tool in the conversation)
  • Optimize model selector
  • Miscellaneous adjustments

After selecting a tool in Ollama, content will only display after the model fully responds; online models support real-time output

v.1.2.0

08 Apr 03:31
Compare
Choose a tag to compare
  • Optimized the default document chunking effect.
  • Improved the accuracy of full-text search in the knowledge base.
  • Fixed the issue of incomplete chunking with multiple delimiters.
  • Resolved some UI interaction issues.

v1.1.9

03 Apr 06:01
Compare
Choose a tag to compare
  • Change knowledge base precision configuration to automatic
  • Fix issue where knowledge base recall configuration was not taking effect
  • Resolve problems caused by modifying the data directory
  • Fix errors in invoking certain online models
  • Add support for x64 version of macOS

v1.1.8

02 Apr 11:58
Compare
Choose a tag to compare
  1. Improved accuracy and performance of the knowledge base
  2. Configuration of document chunking and recall settings for the knowledge base
  3. Added functionality to modify data storage directories
  4. Fixed the issue where .doc files could not be parsed
  5. Optimized the context embedding process to reduce hallucinations
  6. Other known bug fixes

v1.1.7

21 Mar 10:45
Compare
Choose a tag to compare

feat: add and optimize several features

  • Add support for parsing Mermaid standard syntax output format
  • Introduce configuration option for custom Ollama service interface address to enhance flexibility
  • Synchronize and maintain the latest Ollama model library list

fix: resolve issues

  • Display error messages when model invocation fails to facilitate troubleshooting
  • Fix issue where the Ollama model storage directory configuration did not take effect immediately

v1.1.6

20 Mar 03:04
Compare
Choose a tag to compare
  1. Fixed the issue where knowledge base document embedding would infinitely wait in certain scenarios.
  2. Added a mechanism to detect the availability of embedding models.
  3. Improved the PDF parser to enhance usability and better preserve formatting.
  4. Added support for selecting the model installation location.

v1.1.5

15 Mar 04:03
Compare
Choose a tag to compare

feat: add new features and fix related issues

  • Add intelligent agent functionality module

fix: resolve errors with non-VL models when attachments are images

  • Fix issue where non-VL models throw errors when processing image attachments