local only agent

[Aaronminer1]

Duplicates

• [X] I have searched the existing issues

Summary 💡

add option to use locally hosted gpt models to interact with the agent but still have the agent contact gpt-4 for task that are beyond the local gpt's capability's this will cut down on api cost maybe incorporate alpaca electron or similar projects

Examples 🌈

No response

Motivation 🔦

reduce api calls to openai thus reduce cost to run an agent

[mothermetabot]

Using alpaca would add several GBs of artifacts to the project (i.e. ggml-alpaca .bin). Not sure if there is any way around this though. Certainly a nice addition.

[Aaronminer1]

I have been working with gpt4all trying to see if it might work but the model so far is not impressing me

[PurrsianMilkman]

guys we just need to add a way to make it so it can tap into the textgen api. ive got the api working and i dont know much python but trying to get it so it accepts text gen api as an option at least.

[Boostrix]

related to #2158

[github-actions[bot]]

This issue was closed automatically because it has been stale for 10 days with no activity.