Splitting LLM call blocks into model and provider

Significant-Gravitas / AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

https://agpt.co

Other

168.85k stars 44.48k forks source link

Splitting LLM call blocks into model and provider #8330

Open Fried-Squid opened 1 month ago

Fried-Squid commented 1 month ago

Duplicates

[X] I have searched the existing issues

Summary 💡

The LLM call blocks should have a dropdown for model and provider, in order to enable users to use specific providers for models available on multiple providers, such as choosing between Ollama and Grok for llama models.

@ntindle @Bentlybro continued from convo in the PR

Examples 🌈

No response

Motivation 🔦

This allows us to implement more customization for LLM providers and models.

Fried-Squid commented 1 month ago

As I said in the PR, I'm happy to look at this myself but I'm not sure how to proceed with implementing this on the frontend, as I assume this would require changes to the JSON schema for blocks as rather than just having an Enum which the dropdown selects on, the Model dropdown now depends on the Provider dropdown. If someone could advise on how would be best to approach this, I'd be happy to try and get a PR out soon