Hello Groq Team,
I hope you're doing well. I'm currently integrating tool calling with your API and have encountered an issue: sometimes, even when all the necessary context and parameters are provided in the conversation, the model does not trigger the tool call as expected.
Could you please help me understand why this might be happening? Are there any known limitations, recommended prompt structures, or best practices that could improve the reliability of tool calling?
Any insights or documentation you can share would be greatly appreciated.
You can see a screen record of this on: https://drive.google.com/file/d/13CoJdEI5OT-9xN9F-Ey9ywQUfw0Qp5nK/view?usp=sharing
Best regards,
Sergio Eloy Espadas & The Beserva Team