You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
The text was updated successfully, but these errors were encountered:
@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.
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.
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.
The text was updated successfully, but these errors were encountered: