Jump to

• Request
• Response

Rerank documents by query relevance

post

/vecdb/rerank

Score and order documents by relevance to a query using an ONNX reranker hosted in the database.

Request

There are no request parameters for this operation.

Supported Media Types

• application/json

Request Body - application/json ()

Root Schema : schema

Type: object

Show Source

• debugFlags: object VectorDebugFlags
  Debug flags to be used to trace vector modules
• documents(required): array documents
  Minimum Number of Items: 1

  Array of raw document strings to score.
• modelName(required): string
  The name of the ONNX reranking model hosted in the database.
• modelParams: object modelParams
  Additional Properties Allowed: true

  Model-specific parameters.
• query(required): string
  Natural language query to use for reranking.

{
    "type":"object",
    "required":[
        "query",
        "documents",
        "modelName"
    ],
    "properties":{
        "query":{
            "type":"string",
            "description":"Natural language query to use for reranking."
        },
        "documents":{
            "type":"array",
            "description":"Array of raw document strings to score.",
            "minItems":1,
            "items":{
                "type":"string"
            }
        },
        "modelName":{
            "type":"string",
            "description":"The name of the ONNX reranking model hosted in the database."
        },
        "modelParams":{
            "type":"object",
            "description":"Model-specific parameters.",
            "additionalProperties":true,
            "properties":{
                "provider":{
                    "type":"string",
                    "description":"Optional model provider (e.g., 'database')."
                }
            }
        },
        "debugFlags":{
            "$ref":"#/components/schemas/VectorDebugFlags"
        }
    }
}

Nested Schema : VectorDebugFlags

Type: object

Debug flags to be used to trace vector modules

Show Source

• VEC_INDEX_CALIBRATION: string
  Allowed Values: [ "low", "medium", "high" ]
• VECIDX_TRANS: string
  Allowed Values: [ "low", "medium", "high" ]
• VECIDX_TRANS_COM: string
  Allowed Values: [ "low", "medium", "high" ]
• VECIDX_TRANS_PJ: string
  Allowed Values: [ "low", "medium", "high" ]
• VECIDX_TRANS_PJ_DWNGRD: string
  Allowed Values: [ "low", "medium", "high" ]
• VECIDX_TRANS_PJ_GROW: string
  Allowed Values: [ "low", "medium", "high" ]
• VECIDX_TRANS_SJ: string
  Allowed Values: [ "low", "medium", "high" ]
• VECIDX_TRANS_SJ_BG: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX_FIXED_VIEW: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX_NEIGHBOR_GRAPH: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX_NEIGHBOR_GRAPH_APPCHNG: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX_NEIGHBOR_GRAPH_BUILD: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX_NEIGHBOR_GRAPH_MEM: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX_NEIGHBOR_GRAPH_SEARCH: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX_NEIGHBOR_GRAPH_STATS: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_INDEX_NEIGHBOR_PARTITIONS: string
  Allowed Values: [ "low", "medium", "high" ]
• VECTOR_TRACE: string
  Allowed Values: [ "low", "medium", "high" ]

{
    "type":"object",
    "description":"Debug flags to be used to trace vector modules",
    "properties":{
        "VECTOR_INDEX":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_INDEX_NEIGHBOR_GRAPH":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_INDEX_NEIGHBOR_GRAPH_BUILD":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_INDEX_NEIGHBOR_GRAPH_MEM":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_INDEX_NEIGHBOR_GRAPH_SEARCH":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_INDEX_NEIGHBOR_GRAPH_APPCHNG":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_INDEX_NEIGHBOR_GRAPH_STATS":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_INDEX_NEIGHBOR_PARTITIONS":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_INDEX_FIXED_VIEW":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECIDX_TRANS":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECIDX_TRANS_COM":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECIDX_TRANS_PJ":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECIDX_TRANS_PJ_DWNGRD":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECIDX_TRANS_PJ_GROW":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECIDX_TRANS_SJ":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECIDX_TRANS_SJ_BG":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VEC_INDEX_CALIBRATION":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        },
        "VECTOR_TRACE":{
            "type":"string",
            "enum":[
                "low",
                "medium",
                "high"
            ]
        }
    }
}

Nested Schema : documents

Type: array

Minimum Number of Items: 1

Array of raw document strings to score.

Show Source

• Array of: string

{
    "type":"array",
    "description":"Array of raw document strings to score.",
    "minItems":1,
    "items":{
        "type":"string"
    }
}

Nested Schema : modelParams

Type: object

Additional Properties Allowed: true

Model-specific parameters.

Show Source

• provider: string
  Optional model provider (e.g., 'database').

{
    "type":"object",
    "description":"Model-specific parameters.",
    "additionalProperties":true,
    "properties":{
        "provider":{
            "type":"string",
            "description":"Optional model provider (e.g., 'database')."
        }
    }
}

Security

• BasicAuth: http
  Type: http
• BearerAuth: http
  Type: http
• OAuth2: oauth2
  Type: oauth2

Back to Top

Response

Supported Media Types

• application/json
• application/problem+json

200 Response

Rerank scores for each input document in descending relevance.

Body ()

Root Schema : VectorRerankResponse

Type: array

List of rerank results sorted by descending relevance.

Show Source

• Array of: object VectorRerankItem

{
    "type":"array",
    "description":"List of rerank results sorted by descending relevance.",
    "items":{
        "$ref":"#/components/schemas/VectorRerankItem"
    }
}

Nested Schema : VectorRerankItem

Type: object

Show Source

• index(required): integer (int32)
  Zero-based index of the input document in the request payload.
• score(required): number (double)
  Relevance score for the document (higher is more relevant).

{
    "type":"object",
    "required":[
        "index",
        "score"
    ],
    "properties":{
        "index":{
            "type":"integer",
            "format":"int32",
            "description":"Zero-based index of the input document in the request payload."
        },
        "score":{
            "type":"number",
            "format":"double",
            "description":"Relevance score for the document (higher is more relevant)."
        }
    }
}

400 Response

The request body included invalid parameters.

Body ()

Root Schema : ORDSErrorResponse

Type: object

Show Source

• code(required): string
• diagnosticTrace: string
• instance(required): string
• message(required): string
• stackTrace: string
• type(required): string

{
    "type":"object",
    "required":[
        "code",
        "message",
        "type",
        "instance"
    ],
    "properties":{
        "code":{
            "type":"string"
        },
        "message":{
            "type":"string"
        },
        "type":{
            "type":"string"
        },
        "instance":{
            "type":"string"
        },
        "diagnosticTrace":{
            "type":"string"
        },
        "stackTrace":{
            "type":"string"
        }
    }
}

Back to Top