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

Would it be possible for Ollama to support re-rank models? #4510

Open
lyfuci opened this issue May 18, 2024 · 3 comments
Open

Would it be possible for Ollama to support re-rank models? #4510

lyfuci opened this issue May 18, 2024 · 3 comments
Labels
feature request New feature or request

Comments

@lyfuci
Copy link

lyfuci commented May 18, 2024

I am using Ollama for my projects and it's been great. However, when using some AI app platform, like dify, build RAG app, rerank is nessesary. It's possible for Ollama to support rerank models.

@lyfuci lyfuci added the feature request New feature or request label May 18, 2024
@igorschlum
Copy link

@lyfuci Ollama only support OpenSource models. Before adding a model to Ollama, it is often available on Hunging Face.

@lyfuci
Copy link
Author

lyfuci commented May 18, 2024

@igorschlum sorry, just set a typo, reranker->rerank. reranker model means a model input some sentences and a query, output a list of similarity.
There is some reranker model on Hugging Face, like bge-reranker-v2-m3,jina-reranker-v1-base-en etc.

@ah3243
Copy link

ah3243 commented Jun 1, 2024

just to bump this, i agree, I had to switch from ollama to transformers library when doing rag to use a reranker. Also maybe a wider range of embedding models in general or some whay to search for or filter them. I found that bge embeddings like m3 or large outperformed the largest embedding model currently on ollama: mxbai-embed-large.

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

No branches or pull requests

3 participants