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

Vector DB: local model (privateGPT) #8

Closed
slobentanzer opened this issue Jul 19, 2023 · 3 comments
Closed

Vector DB: local model (privateGPT) #8

slobentanzer opened this issue Jul 19, 2023 · 3 comments

Comments

@slobentanzer
Copy link
Contributor

slobentanzer commented Jul 19, 2023

https://github.com/imartinez/privateGPT is an example for local hosting of models for increased privacy. Could also be less expensive than relying on commercial services for the embeddings of large datasets.

LLaMA2 is open source now, could be a good alternative. Has an API on replicate: https://replicate.com/a16z-infra/llama13b-v2-chat

@slobentanzer
Copy link
Contributor Author

Of note, the replicate API is not the same as the naive model. It seems to have some additional layer that changes responses (sensitive content etc.).

@slobentanzer
Copy link
Contributor Author

Building a solution based on Xorbits Inference and Docker

@slobentanzer slobentanzer moved this to In Progress in BioCypher Development Nov 9, 2023
@slobentanzer
Copy link
Contributor Author

Using open-source embedding models is now possible via PR #24

@slobentanzer slobentanzer moved this from In Progress to Done in BioCypher Development Nov 23, 2023
slobentanzer pushed a commit that referenced this issue Dec 7, 2023
Mock dependencies on OpenAI and Milvus server in llm_connect test, prompts tests and benchmark tests
slobentanzer pushed a commit that referenced this issue Jun 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Done
Development

No branches or pull requests

1 participant