Ollama Now Supports Tool Calling to Access External Functions and Data

Ollama introduces tool calling support for advanced AI models: Ollama, an AI development platform, has expanded its capabilities by adding tool calling support for popular language models like Llama 3.1, enabling more complex interactions and real-world applications.

Key features and functionality: The new tool calling feature allows AI models to utilize external tools to enhance their problem-solving abilities and interact with the outside world.

• Models can now access functions, APIs, web browsing capabilities, and code interpreters to perform more sophisticated tasks.
• This functionality significantly expands the potential applications of AI models, allowing them to gather real-time information and execute complex operations.

Implementation and usage: Ollama has provided a straightforward method for developers to integrate tool calling into their AI applications.

• Developers can enable tool calling by providing a list of available tools through the ‘tools’ field in Ollama’s API.
• The platform offers code examples in Python, demonstrating how to implement weather checking functionality using the new tool calling feature.
• Supported models will respond with a ‘tool_calls’ output, and developers can provide tool responses via messages with the ‘tool’ role.

Supported models and compatibility: Ollama has ensured broad support for tool calling across various AI models and platforms.

• The feature is available for several popular models, including Llama 3.1, Mistral Nemo, Firefunction v2, and Command-R +.
• Users are advised to update their models to the latest versions using the ‘ollama pull ‘ command to ensure compatibility.
• Ollama’s OpenAI-compatible endpoint now supports tools, allowing developers to switch to using Llama 3.1 and other models seamlessly.

Future developments and community engagement: Ollama has outlined plans for further improvements to the tool calling feature and is actively seeking user feedback.

• Upcoming enhancements include streaming tool calls for faster action when multiple tools are returned and the ability to force a model to use a specific tool.
• The company encourages developers to provide feedback through their Discord channel or via email at [email protected].

Broader implications: The introduction of tool calling support in Ollama’s platform represents a significant step forward in AI capabilities and applications.

• This feature has the potential to bridge the gap between AI language models and real-world interactions, enabling more practical and diverse use cases.
• As AI continues to evolve, the ability to integrate external tools and data sources will likely become increasingly important, potentially leading to more sophisticated and capable AI systems in various industries and applications.