8000 Tags · offsoc/AingDesk · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
8000

Tags: offsoc/AingDesk

Tags

v1.2.3

Toggle v1.2.3's commit message 
fix: resolve several known issues

- 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

Toggle v1.2.2's commit message 
docs: add example screenshots for MCP

v1.2.1

Toggle v1.2.1's commit message 
feat: add support for MCP

- Add MCP client functionality (configure the MCP server in settings, then select the tool in the conversation)
- Optimize model selector
- Miscellaneous adjustments

v1.2.0

Toggle v1.2.0's commit message 
chore: optimize certain aspects of the knowledge base

- Improve default document chunking effect
- Enhance full-text search accuracy of the knowledge base
- Fix issues with incomplete chunking caused by multiple delimiters
- Resolve some UI interaction problems

v1.1.9

Toggle v1.1.9's commit message 
chore: optimize several features and resolve issues

- 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

Toggle v1.1.8's commit message 
chore: update and optimize several features

chore: update and optimize several features
- Improve accuracy and performance of the knowledge base
- Add configuration for knowledge base document chunking and recall
- Introduce functionality to modify data storage directory

fix: resolve known issues
- Fix inability to parse .doc files
- Optimize context embedding process to reduce hallucinations
- Address other known bugs

v1.1.7

Toggle v1.1.7's commit message 
feat: add and optimize several features

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

Toggle v1.1.6's commit message 
feat: add new features and fix related issues

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

v1.1.5

Toggle v1.1.5's commit message 
feat: add new features and fix related issues

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

v1.1.4

Toggle v1.1.4's commit message 
feat: add new features and fix related issues

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
0