Rerank documents by relevance
Rerank documents by relevance. Order up to 50 documents by how well each answers a query, with a relevance score from 0 to 1 (BAAI bge-reranker-base, a cross-encoder). Send documents as a JSON array or one per line; each is read up to 2,000 characters, 40,000 in all. Returns the original index, score and text, best first; top_n keeps only the best. Also available in the Cohere-style shape at /v1/rerank. Use to pick what a model reads after search or vector retrieval.
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
GET https://agent-data-tools.revmesh2074.workers.dev/ai/rerank
| Category | Search and research |
|---|---|
| Provider host | agent-data-tools.revmesh2074.workers.dev |
| Networks | eip155:137, eip155:42161, eip155:8453, solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp |
| Payment schemes | exact |
| Self-reported calls, 30 days | 0 from 0 payers (the provider's figure, not ours) |
Our checks, last 30 days
We never call tools that send, buy, move money or file anything, not even without paying.
Example input (from the provider)
{
"method": "GET",
"queryParams": {
"documents": "[\"France has hundreds of cheeses.\",\"Berlin is the capital of Germany.\",\"Paris is the capital and largest city of France.\"]",
"query": "What is the capital of France?"
},
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"method": {
"enum": [
"GET"
],
"type": "string"
},
"queryParams": {
"properties": {
"documents": {
"description": "Up to 50 documents: a JSON array of strings, or one per line",
"examples": [
"[\"France has hundreds of cheeses.\",\"Berlin is the capital of Germany.\",\"Paris is the capital and largest city of France.\"]"
],
"type": "string"
},
"query": {
"description": "What the documents should answer (up to 2,000 characters)",
"examples": [
"What is the capital of France?"
],
"type": "string"
},
"top_n": {
"description": "Keep only the best N results (default all)",
"examples": [
"2"
],
"type": "string"
}
},
"required": [
"query",
"documents"
],
"type": "object"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"properties": {
"clippedDocuments": {
"type": "number"
},
"documents": {
"type": "number"
},
"model": {
"type": "string"
},
"query": {
"type": "string"
},
"results": {
"items": {
"properties": {
"document": {
"type": "string"
},
"index": {
"type": "number"
},
"relevance_score": {
"type": "number"
}
},
"type": "object"
},
"type": "array"
}
},
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}