| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2025-10-13 | 1.3 kB | |
| v4.5.0_ AI Agent Examples and Improved Tool Calling source code.tar.gz | 2025-10-13 | 36.0 MB | |
| v4.5.0_ AI Agent Examples and Improved Tool Calling source code.zip | 2025-10-13 | 36.1 MB | |
| Totals: 3 Items | 72.1 MB | 1 | |
Tool Calling: Enforce tool calls when generating text
You can now force models to use one or more tool calls during output generation by setting the ToolChoice name-value argument of the generate function to "required".
This option is supported for these chat completion APIs:
openAIChatobjectsazureChatobjects
Tool Calling: Temporarily override Tools parameter when generating text
You can now set the Tools parameter for a single API call by using the corresponding name-value argument of the generate function.
AI Agent Workflows: New examples
Use these new examples to learn about agentic workflows:
- Solve Simple Math Problem Using AI Agent
- Fit Polynomial to Data Using AI Agent (requires Curve Fitting Toolbox™)
Minor Updates
This release includes:
- improved error handling
- bug fixes
- documentation updates
Full Changelog: https://github.com/matlab-deep-learning/llms-with-matlab/compare/v4.4.0...v4.5.0