Skip to content
Cloudflare Docs
b

bge-reranker-base

Text Classification • baai
@cf/baai/bge-reranker-base

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.

Usage

Workers - TypeScript

 
export interface Env {
  AI: Ai;
}


export default {
  async fetch(request, env): Promise<Response> {


    const response = await env.AI.run(
      "@cf/baai/bge-reranker-base",
      {
        text: "This pizza is great!",
      }
    );


    return Response.json(response);
  },
} satisfies ExportedHandler<Env>;

Python

 
API_BASE_URL = "https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/"
headers = {"Authorization": "Bearer {API_KEY}"}


def run(model, input):
    response = requests.post(f"{API_BASE_URL}{model}", headers=headers, json=input)
    return response.json()


output = run("@cf/baai/bge-reranker-base", { "text": "This pizza is great!" })
print(output)

curl
Terminal window
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/baai/bge-reranker-base  \
  -X POST  \
  -H "Authorization: Bearer $CLOUDFLARE_API_TOKEN"  \
  -d '{ "text": "This pizza is great!" }'

Parameters

* indicates a required field

Input

  • query * string min 1

    A query you wish to perform against the provided contexts.

  • top_k integer min 1

    Number of returned results starting with the best score.

  • contexts * array

    List of provided contexts. Note that the index in this array is important, as the response will refer to it.

    • items object

      • text string min 1

        One of the provided context content

Output

  • response array

    • items object

      • id integer

        Index of the context in the request

      • score number

        Score of the context under the index.

API Schemas

The following schemas are based on JSON Schema

{
    "type": "object",
    "properties": {
        "query": {
            "type": "string",
            "minLength": 1,
            "description": "A query you wish to perform against the provided contexts."
        },
        "top_k": {
            "type": "integer",
            "default": null,
            "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"
    ]
}