Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Integration of Together.ai with babyagi-ui #186

Open
JM2197 opened this issue Aug 29, 2023 · 2 comments
Open

Integration of Together.ai with babyagi-ui #186

JM2197 opened this issue Aug 29, 2023 · 2 comments

Comments

@JM2197
Copy link

JM2197 commented Aug 29, 2023

I propose the integration of Together.ai with babyagi-ui to enhance capabilities and provide more affordable options for utilizing llm. Together.ai offers a variety of base models, including Llama2 (70B), at a significantly lower cost compared to OpenAI, making it a valuable resource for project.

Key Features of Together.ai:

  1. Affordable Access to llm: Together.ai provides access to a variety of base models, including Llama2 (70B), at a significantly lower cost compared to OpenAI. This cost-effective solution can help us to leverage llm more efficiently.

  2. Robust API Support: Together.ai offers robust API support, which can facilitate seamless integration with Babyagi-ui and ensure smooth operation.

  3. Fine-tuning Model Deployment: Together.ai allows for the deployment of fine-tuned models. This feature can be beneficial for project as it can enable us to customize the models according to specific requirements.

Considering the ongoing project of Llama-2 support in Babyagi-ui, integrating Together.ai can be seen as a logical extension of current efforts. This integration can potentially enhance the functionality of Babyagi-ui and provide us with more flexibility in terms of utilizing llm.

link: https://together.ai/

@miurla
Copy link
Owner

miurla commented Aug 29, 2023

Together.ai looks good.

The call to LLM in BabyAGI-UI is done using LangChain.
I checked for support and it seems to be in progress.
langchain-ai/langchainjs#2284

If it gets merged soon, I'd like to add it to Llama-2 support.

@JM2197
Copy link
Author

JM2197 commented Aug 29, 2023

That sounds great! I hope it works out.

It would be more efficient if we could use a model like LLaMA-2 Chat (70B) as the main one and selectively utilize the LLaMA-2-32K (7B) model for like web crawling.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants