Skip to main content

​
Cohere Reranker

This reranker uses the Cohere API to rerank the search results. You can use this reranker by passing CohereReranker() to the rerank() method. Note that you’ll either need to set the COHERE_API_KEY environment variable or pass the api_key argument to use this reranker.
Note: Supported query types – Hybrid, Vector, and FTS. 
pip install cohere

​
Accepted Arguments

ArgumentTypeDefaultDescription
model_namestr"rerank-english-v2.0"The name of the reranker model to use. Available cohere models are: rerank-english-v2.0, rerank-multilingual-v2.0
columnstr"text"The name of the column to use as input to the cross encoder model.
top_nstrNoneThe number of results to return. If None, will return all results.
api_keystrNoneThe API key for the Cohere API. If not provided, the COHERE_API_KEY environment variable is used.
return_scorestr"relevance"Options are “relevance” or “all”. The type of score to return. If “relevance”, will return only the `_relevance_score. If “all” is supported, will return relevance score along with the vector and/or fts scores depending on query type

​
Supported Scores for each query type

You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:
return_scoreStatusDescription
relevance✅ SupportedResults only have the _relevance_score column
all❌ Not SupportedResults have vector(_distance) and FTS(score) along with Hybrid Search score(_relevance_score)
return_scoreStatusDescription
relevance✅ SupportedResults only have the _relevance_score column
all✅ SupportedResults have vector(_distance) along with Hybrid Search score(_relevance_score)
return_scoreStatusDescription
relevance✅ SupportedResults only have the _relevance_score column
all✅ SupportedResults have FTS(score) along with Hybrid Search score(_relevance_score)