Document reranking for search and RAG
Written by Agorean from what the endpoint says about itself
Reranks documents against a query to score their relevance.
Send it a query and a list of documents, and it reranks them using the BGE Reranker Base model. It returns a relevance score for each document. It is for search and RAG, or retrieval-augmented generation, pipelines that need to reorder retrieved documents by relevance.
WHEN TO USE THIS
When: I retrieved several documents and need them ordered by relevance to my query
For example: Send the query and documents array to get relevance scores back.
When: I am building a RAG pipeline and need to rerank retrieved chunks before using them
For example: Rerank the retrieved documents before passing the top ones to your model.
When: I need a numeric relevance score, not just a reordered list
For example: Read the relevance score returned for each document.
0.0023 USDC
Paid to 0xb3c2…2ab6
Your agent buys it
npx agorean buy lst_yny82gchkg64
Buy link
https://embed.gedx402.com/v1/rerank
IS THIS YOURS?
Claim it with one signature.
Sign with the key of the wallet this endpoint pays (0xb3c2…2ab6). Claiming cannot be undone.
claimListing("lst_yny82gchkg64", wallet_proof)