Add support for Auto-GPT

[keldenl]

Get Auto-GPT working. It's blocked on the following 2 items

• Adding local embedding: Add back local embeddings Significant-Gravitas/AutoGPT#2473
• Adding support for different BASE_URL for OpenAi
  • update: @DGdev91 made a PR for this: Add settings for custom base url Significant-Gravitas/AutoGPT#2594

Embeddings aren't working quite right / very inconsistent between models, so having a built-in local embedding option is good.

For the second bullet point, we can technically work around and set the BASE_URL by modifying the code, but it would be nice to have it as an option / env variable so it's easier to get started.

I'll likely open a new PR against Auto-GPT for the second point and push to get that PR i linked above in

[keldenl]

Just got AutoGPT working consistently from this embeddings fix b3db39f

Still need to manually update the vector size in autogpt to 5120 or 4096 depending on the llama model (see https://huggingface.co/shalomma/llama-7b-embeddings#quantitative-analysis), but it works!

vicuna 13b, the best model i've tested so far, isn't doing a GREAT job generating actions that it can follow continuously (gets stuck in a loop)

[keldenl]

I'll put up a fork of AutoGPT tmr with all the changes I made (openai BASE_URL and configurable vector dimensions) to make it easier for folks to replicate and test as well.

[DGdev91]

Thanks for your work!

i was exited to try it out and made those changes myself. i also made a pull request Significant-Gravitas/AutoGPT#2594

Feel free to add your changes if i missed something

[keldenl]

wow @DGdev91 that was EXACTLY what i was going to do.. thanks!! nothing to add for me

[keldenl]

Re-opening this until we get the PR Significant-Gravitas/AutoGPT#2594 fully merged

[keldenl]

🚀 🚀 AUTOGPT + GPT-LLAMA.CPP GUIDE IS NOW AVAILABLE: https://github.com/keldenl/gpt-llama.cpp/blob/master/docs/Auto-GPT-setup-guide.md

HUGE shoutout to @DGdev91 for putting up the PR to make this possible – hopefully the PR gets merged to master soon.

Here's a (very short) demo of it running on my M1 Mac: https://github.com/keldenl/gpt-llama.cpp/blob/master/docs/demos.md#Auto-GPT