search

yoheinakajima / babyagi

https://babyagi.org/
20.4k stars 2.68k forks source link

Is it possible to run without an OpenAi API key #124

Closed harborwater closed 1 year ago

harborwater commented 1 year ago

I'm wondering if there's alternative to the OpenAI API, such as a self-hosted model that can do the same?

Jawad1347 commented 1 year ago

I'm wondering if there's alternative to the OpenAI API, such as a self-hosted model that can do the same?

Good question, I was about to ask the same. Vicuna should be fine replacement, but how.

LJH4 commented 1 year ago

Imagine there is a way to use the huggingface api

alexdzm commented 1 year ago

Hey, you can use llama. See this from the README:

Llama

Download the latest version of Llama.cpp and follow instructions to make it. You will also need the Llama model weights.

Under no circumstances share IPFS, magnet links, or any other links to model downloads anywhere in this repository, including in issues, discussions or pull requests. They will be immediately deleted. After that link llama/main to llama.cpp/main and models to the folder where you have the Llama model weights. Then run the script with OPENAI_API_MODEL=llama or -l argument.

alexdzm commented 1 year ago

See also #130 for some helpful tips on getting this to work!

francip commented 1 year ago

Theoretically, you can run BabyAGI with any models supported by llama.cpp. We haven't done extensive testing, and it's possible the prompts need to be changed, but the infra to enable this is there.