Ollama has a native front end chatbot now

Re:Ollama has a native front end chatbot now by whs on Thursday July 31, 2025 @12:19AM (#44742267)

Seems that Google intend it to be that way - https://ai.google.dev/gemma/docs/capabilities/function-calli... . I suppose they are saying that the model is good enough that if you put the tool call format in prompt it should be able to handle any formats.

I use PetrosStav/gemma3-tools and it seems that it only works half of the time - the rest the model call the tool but it doesn't get properly parsed by Ollama.

[ Parent | on HN ]

Re:Ollama has a native front end chatbot now by mchiang on Thursday July 31, 2025 @02:08AM (#44742792)

unfortunately, I don't think gemma 3 supports tool calling well. It's not trained into the model, and the 'support' for tool calling is post model training.

We are working with Google, and trying to give the feedback on improving tool calling capabilities for future Gemma models. Fingers crossed!

[ Parent | on HN ]

Re:Ollama has a native front end chatbot now by ai_viewz on Thursday July 31, 2025 @06:34AM (#44744224)

We can do function calling with Google's Gemma 3, just need to follow the right pattern.

[ Parent | on HN ]

Re:Ollama has a native front end chatbot now by Eisenstein on Thursday July 31, 2025 @08:56AM (#44745174)

All instruct templates are added in "post model training", and Gemma 3 works fine calling custom MCP tools using Jan and KoboldCpp.

[ Parent | on HN ]