Skip to content
BAAI logo

bge-reranker-base

Text ClassificationBAAIHosted

Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.

Model Info
Unit Pricing$0.0031 per M input tokens

Usage

export interface Env {
AI: Ai;
}
export default {
async fetch(request, env): Promise<Response> {
const query = 'Which one is cooler?'
const contexts = [
{
text: 'a cyberpunk lizzard'
},
{
text: 'a cyberpunk cat'
}
];
const response = await env.AI.run('@cf/baai/bge-reranker-base', { query, contexts });
return Response.json(response);
},
} satisfies ExportedHandler<Env>;

Parameters

query
stringrequiredminLength: 1A query you wish to perform against the provided contexts.
top_k
integerminimum: 1Number of returned results starting with the best score.

API Schemas

{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"description": "A query you wish to perform against the provided contexts."
},
"top_k": {
"type": "integer",
"minimum": 1,
"description": "Number of returned results starting with the best score."
},
"contexts": {
"type": "array",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"description": "One of the provided context content"
}
}
},
"description": "List of provided contexts. Note that the index in this array is important, as the response will refer to it."
}
},
"required": [
"query",
"contexts"
]
}