pinecone

Pinecone Vector Database

Server path: /pinecone | Type: Application | PCID required: Yes

Tools

Tool	Description
pinecone_configure_index	Configure an index
pinecone_create_backup	Create a backup of an index
pinecone_create_collection	Create a collection
pinecone_create_index	Create an index
pinecone_create_index_for_model	Create an index with integrated embedding
pinecone_create_index_from_backup_operation	Create an index from a backup
pinecone_delete_backup	Delete a backup
pinecone_delete_collection	Delete a collection
pinecone_delete_index	Delete an index
pinecone_describe_backup	Describe a backup
pinecone_describe_collection	Describe a collection
pinecone_describe_index	Describe an index
pinecone_describe_restore_job	Describe a restore job
pinecone_embed	Generate vectors
pinecone_get_model	Describe a model
pinecone_list_collections	List collections
pinecone_list_index_backups	List backups for an index
pinecone_list_indexes	List indexes
pinecone_list_models	List available models
pinecone_list_project_backups	List backups for all indexes in a project
pinecone_list_restore_jobs	List restore jobs
pinecone_rerank	Rerank results

---

pinecone_configure_index

Configure an index

Parameters:

Parameter	Type	Required	Default	Description
index_name	string	Yes	—	The name of the index to configure.
deletion_protection	string	No	—	Whether deletion protection is enabled/disabled for the index. Possible values: disabled or enabled.
embed	object	No	—	Configure the integrated inference embedding settings for this index. You can convert an existing index to an integrated index by specifying the embedding model and field_map. The index vector type and dimension must match the model vector type and dimension, and the index similarity metric must be supported by the model. Refer to the model guide for available models and model details. You can later change the embedding configuration to update the field map, read parameters, or write parameters. Once set, the model cannot be changed.
spec	object	No	—	The spec object defines how the index should be deployed. Only some attributes of an index’s spec may be updated. In general, you can modify settings related to scaling and configuration but you cannot change the cloud or region where the index is hosted.
tags	object	No	—	Custom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '', or ’-’. Values must be alphanumeric, ’;’, ’@’, '', ’-’, ’.’, ’+’, or ’ ’. To unset a key, set the value to be an empty string.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "index_name": {
      "type": "string",
      "description": "The name of the index to configure."
    },
    "deletion_protection": {
      "type": "string",
      "description": "Whether [deletion protection](http://docs.pinecone.io/guides/manage-data/manage-indexes#configure-deletion-protection) is enabled/disabled for the index. Possible values: `disabled` or `enabled`."
    },
    "embed": {
      "type": "object",
      "description": "Configure the integrated inference embedding settings for this index.  You can convert an existing index to an integrated index by specifying the embedding model and field_map. The index vector type and dimension must match the model vector type and dimension, and the index similarity metric must be supported by the model. Refer to the [model guide](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) for available models and model details.  You can later change the embedding configuration to update the field map, read parameters, or write parameters. Once set, the model cannot be changed.",
      "properties": {
        "model": {
          "type": "string",
          "description": "The name of the embedding model to use with the index. The index dimension and model dimension must match, and the index similarity metric must be supported by the model. The index embedding model cannot be changed once set."
        },
        "field_map": {
          "type": "object",
          "description": "Identifies the name of the text field from your document model that will be embedded."
        },
        "read_parameters": {
          "type": "object",
          "description": "The read parameters for the embedding model."
        },
        "write_parameters": {
          "type": "object",
          "description": "The write parameters for the embedding model."
        }
      }
    },
    "spec": {
      "description": "The spec object defines how the index should be deployed.  Only some attributes of an index's spec may be updated.  In general, you can modify settings related to scaling and  configuration but you cannot change the cloud or region  where the index is hosted."
    },
    "tags": {
      "type": "object",
      "description": "Custom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '_', or '-'.  Values must be alphanumeric, ';', '@', '_', '-', '.', '+', or ' '. To unset a key, set the value to be an empty string."
    }
  },
  "required": [
    "PCID",
    "index_name"
  ]
}

---

pinecone_create_backup

Create a backup of an index

Parameters:

Parameter	Type	Required	Default	Description
index_name	string	Yes	—	Name of the index to backup
description	string	No	—	A description of the backup.
name	string	No	—	The name of the backup.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "index_name": {
      "type": "string",
      "description": "Name of the index to backup"
    },
    "description": {
      "type": "string",
      "description": "A description of the backup."
    },
    "name": {
      "type": "string",
      "description": "The name of the backup."
    }
  },
  "required": [
    "PCID",
    "index_name"
  ]
}

---

pinecone_create_collection

Create a collection

Parameters:

Parameter	Type	Required	Default	Description
name	string	Yes	—	The name of the collection to be created. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or ’-’.
source	string	Yes	—	The name of the index to be used as the source for the collection.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "name": {
      "type": "string",
      "description": "The name of the collection to be created. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or '-'."
    },
    "source": {
      "type": "string",
      "description": "The name of the index to be used as the source for the collection."
    }
  },
  "required": [
    "PCID",
    "name",
    "source"
  ]
}

---

pinecone_create_index

Create an index

Parameters:

Parameter	Type	Required	Default	Description
deletion_protection	string	No	—	Whether deletion protection is enabled/disabled for the index. Possible values: disabled or enabled.
dimension	integer	No	—	The dimensions of the vectors to be inserted in the index.
metric	string	No	—	The distance metric to be used for similarity search. You can use ‘euclidean’, ‘cosine’, or ‘dotproduct’. If the ‘vector_type’ is ‘sparse’, the metric must be ‘dotproduct’. If the vector_type is dense, the metric defaults to ‘cosine’. Possible values: cosine, euclidean, or dotproduct.
name	string	Yes	—	The name of the index. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or ’-’.
spec	object	Yes	—	The spec object defines how the index should be deployed. For serverless indexes, you define only the cloud and region where the index should be hosted. For pod-based indexes, you define the environment where the index should be hosted, the pod type and size to use, and other index characteristics.
tags	object	No	—	Custom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '', or ’-’. Values must be alphanumeric, ’;’, ’@’, '', ’-’, ’.’, ’+’, or ’ ’. To unset a key, set the value to be an empty string.
vector_type	string	No	—	The index vector type. You can use ‘dense’ or ‘sparse’. If ‘dense’, the vector dimension must be specified. If ‘sparse’, the vector dimension should not be specified.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "deletion_protection": {
      "type": "string",
      "description": "Whether [deletion protection](http://docs.pinecone.io/guides/manage-data/manage-indexes#configure-deletion-protection) is enabled/disabled for the index. Possible values: `disabled` or `enabled`."
    },
    "dimension": {
      "type": "integer",
      "description": "The dimensions of the vectors to be inserted in the index."
    },
    "metric": {
      "type": "string",
      "description": "The distance metric to be used for similarity search. You can use 'euclidean', 'cosine', or 'dotproduct'. If the 'vector_type' is 'sparse', the metric must be 'dotproduct'. If the `vector_type` is `dense`, the metric defaults to 'cosine'. Possible values: `cosine`, `euclidean`, or `dotproduct`."
    },
    "name": {
      "type": "string",
      "description": "The name of the index. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or '-'."
    },
    "spec": {
      "type": "object",
      "description": "The spec object defines how the index should be deployed.  For serverless indexes, you define only the [cloud and region](http://docs.pinecone.io/guides/index-data/create-an-index#cloud-regions) where the index should be hosted. For pod-based indexes, you define the [environment](http://docs.pinecone.io/guides/indexes/pods/understanding-pod-based-indexes#pod-environments) where the index should be hosted, the [pod type and size](http://docs.pinecone.io/guides/indexes/pods/understanding-pod-based-indexes#pod-types) to use, and other index characteristics."
    },
    "tags": {
      "type": "object",
      "description": "Custom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '_', or '-'.  Values must be alphanumeric, ';', '@', '_', '-', '.', '+', or ' '. To unset a key, set the value to be an empty string."
    },
    "vector_type": {
      "type": "string",
      "description": "The index vector type. You can use 'dense' or 'sparse'. If 'dense', the vector dimension must be specified.  If 'sparse', the vector dimension should not be specified."
    }
  },
  "required": [
    "PCID",
    "name",
    "spec"
  ]
}

---

pinecone_create_index_for_model

Create an index with integrated embedding

Parameters:

Parameter	Type	Required	Default	Description
cloud	string	Yes	—	The public cloud where you would like your index hosted. Possible values: gcp, aws, or azure.
deletion_protection	string	No	—	Whether deletion protection is enabled/disabled for the index. Possible values: disabled or enabled.
embed	object	Yes	—	Specify the integrated inference embedding configuration for the index. Once set the model cannot be changed, but you can later update the embedding configuration for an integrated inference index including field map, read parameters, or write parameters. Refer to the model guide for available models and model details.
name	string	Yes	—	The name of the index. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or ’-’.
read_capacity	object	No	—	By default the index will be created with read capacity mode OnDemand. If you prefer to allocate dedicated read nodes for your workload, you must specify mode Dedicated and additional configurations for node_type and scaling.
region	string	Yes	—	The region where you would like your index to be created.
schema	object	No	—	Schema for the behavior of Pinecone’s internal metadata index. By default, all metadata is indexed; when schema is present, only fields which are present in the fields object with a filterable: true are indexed. Note that filterable: false is not currently supported.
tags	object	No	—	Custom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '', or ’-’. Values must be alphanumeric, ’;’, ’@’, '', ’-’, ’.’, ’+’, or ’ ’. To unset a key, set the value to be an empty string.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "cloud": {
      "type": "string",
      "description": "The public cloud where you would like your index hosted. Possible values: `gcp`, `aws`, or `azure`."
    },
    "deletion_protection": {
      "type": "string",
      "description": "Whether [deletion protection](http://docs.pinecone.io/guides/manage-data/manage-indexes#configure-deletion-protection) is enabled/disabled for the index. Possible values: `disabled` or `enabled`."
    },
    "embed": {
      "type": "object",
      "description": "Specify the integrated inference embedding configuration for the index.  Once set the model cannot be changed, but you can later update the embedding configuration for an integrated inference index including field map, read parameters, or write parameters.  Refer to the [model guide](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) for available models and model details.",
      "properties": {
        "model": {
          "type": "string",
          "description": "The name of the embedding model to use for the index."
        },
        "metric": {
          "type": "string",
          "description": "The distance metric to be used for similarity search. You can use 'euclidean', 'cosine', or 'dotproduct'. If not specified, the metric will be defaulted according to the model. Cannot be updated once set. Possible values: `cosine`, `euclidean`, or `dotproduct`."
        },
        "field_map": {
          "type": "object",
          "description": "Identifies the name of the text field from your document model that will be embedded."
        },
        "dimension": {
          "type": "integer",
          "description": "The dimension of embedding vectors produced for the index."
        },
        "read_parameters": {
          "type": "object",
          "description": "The read parameters for the embedding model."
        },
        "write_parameters": {
          "type": "object",
          "description": "The write parameters for the embedding model."
        }
      },
      "required": [
        "model",
        "field_map"
      ]
    },
    "name": {
      "type": "string",
      "description": "The name of the index. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or '-'."
    },
    "read_capacity": {
      "description": "By default the index will be created with read capacity  mode `OnDemand`. If you prefer to allocate dedicated read  nodes for your workload, you must specify mode `Dedicated` and additional configurations for `node_type` and `scaling`."
    },
    "region": {
      "type": "string",
      "description": "The region where you would like your index to be created."
    },
    "schema": {
      "type": "object",
      "description": "Schema for the behavior of Pinecone's internal metadata index. By default, all metadata is indexed; when `schema` is present, only fields which are present in the `fields` object with a `filterable: true` are indexed. Note that `filterable: false` is not currently supported.",
      "properties": {
        "fields": {
          "type": "object",
          "description": "A map of metadata field names to their configuration. The field name must be a valid metadata field name. The field name must be unique."
        }
      },
      "required": [
        "fields"
      ]
    },
    "tags": {
      "type": "object",
      "description": "Custom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '_', or '-'.  Values must be alphanumeric, ';', '@', '_', '-', '.', '+', or ' '. To unset a key, set the value to be an empty string."
    }
  },
  "required": [
    "PCID",
    "cloud",
    "embed",
    "name",
    "region"
  ]
}

---

pinecone_create_index_from_backup_operation

Create an index from a backup

Parameters:

Parameter	Type	Required	Default	Description
backup_id	string	Yes	—	The ID of the backup to create an index from.
deletion_protection	string	No	—	Whether deletion protection is enabled/disabled for the index. Possible values: disabled or enabled.
name	string	Yes	—	The name of the index. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or ’-’.
tags	object	No	—	Custom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '', or ’-’. Values must be alphanumeric, ’;’, ’@’, '', ’-’, ’.’, ’+’, or ’ ’. To unset a key, set the value to be an empty string.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "backup_id": {
      "type": "string",
      "description": "The ID of the backup to create an index from."
    },
    "deletion_protection": {
      "type": "string",
      "description": "Whether [deletion protection](http://docs.pinecone.io/guides/manage-data/manage-indexes#configure-deletion-protection) is enabled/disabled for the index. Possible values: `disabled` or `enabled`."
    },
    "name": {
      "type": "string",
      "description": "The name of the index. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or '-'."
    },
    "tags": {
      "type": "object",
      "description": "Custom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '_', or '-'.  Values must be alphanumeric, ';', '@', '_', '-', '.', '+', or ' '. To unset a key, set the value to be an empty string."
    }
  },
  "required": [
    "PCID",
    "backup_id",
    "name"
  ]
}

---

pinecone_delete_backup

Delete a backup

Parameters:

Parameter	Type	Required	Default	Description
backup_id	string	Yes	—	The ID of the backup to delete.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "backup_id": {
      "type": "string",
      "description": "The ID of the backup to delete."
    }
  },
  "required": [
    "PCID",
    "backup_id"
  ]
}

---

pinecone_delete_collection

Delete a collection

Parameters:

Parameter	Type	Required	Default	Description
collection_name	string	Yes	—	The name of the collection.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "collection_name": {
      "type": "string",
      "description": "The name of the collection."
    }
  },
  "required": [
    "PCID",
    "collection_name"
  ]
}

---

pinecone_delete_index

Delete an index

Parameters:

Parameter	Type	Required	Default	Description
index_name	string	Yes	—	The name of the index to delete.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "index_name": {
      "type": "string",
      "description": "The name of the index to delete."
    }
  },
  "required": [
    "PCID",
    "index_name"
  ]
}

---

pinecone_describe_backup

Describe a backup

Parameters:

Parameter	Type	Required	Default	Description
backup_id	string	Yes	—	The ID of the backup to describe.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "backup_id": {
      "type": "string",
      "description": "The ID of the backup to describe."
    }
  },
  "required": [
    "PCID",
    "backup_id"
  ]
}

---

pinecone_describe_collection

Describe a collection

Parameters:

Parameter	Type	Required	Default	Description
collection_name	string	Yes	—	The name of the collection to be described.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "collection_name": {
      "type": "string",
      "description": "The name of the collection to be described."
    }
  },
  "required": [
    "PCID",
    "collection_name"
  ]
}

---

pinecone_describe_index

Describe an index

Parameters:

Parameter	Type	Required	Default	Description
index_name	string	Yes	—	The name of the index to be described.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "index_name": {
      "type": "string",
      "description": "The name of the index to be described."
    }
  },
  "required": [
    "PCID",
    "index_name"
  ]
}

---

pinecone_describe_restore_job

Describe a restore job

Parameters:

Parameter	Type	Required	Default	Description
job_id	string	Yes	—	The ID of the restore job to describe.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "job_id": {
      "type": "string",
      "description": "The ID of the restore job to describe."
    }
  },
  "required": [
    "PCID",
    "job_id"
  ]
}

---

pinecone_embed

Generate vectors

Parameters:

Parameter	Type	Required	Default	Description
inputs	object[]	Yes	—	List of inputs to generate embeddings for.
model	string	Yes	—	The model to use for embedding generation.
parameters	object	No	—	Additional model-specific parameters. Refer to the model guide for available model parameters.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "inputs": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "text": {
            "type": "string",
            "description": "The text input to generate embeddings for."
          }
        }
      },
      "description": "List of inputs to generate embeddings for."
    },
    "model": {
      "type": "string",
      "description": "The [model](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) to use for embedding generation."
    },
    "parameters": {
      "type": "object",
      "description": "Additional model-specific parameters. Refer to the [model guide](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) for available model parameters."
    }
  },
  "required": [
    "PCID",
    "inputs",
    "model"
  ]
}

---

pinecone_get_model

Describe a model

Parameters:

Parameter	Type	Required	Default	Description
model_name	string	Yes	—	The name of the model to look up.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "model_name": {
      "type": "string",
      "description": "The name of the model to look up."
    }
  },
  "required": [
    "PCID",
    "model_name"
  ]
}

---

pinecone_list_collections

List collections

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    }
  },
  "required": [
    "PCID"
  ]
}

---

pinecone_list_index_backups

List backups for an index

Parameters:

Parameter	Type	Required	Default	Description
index_name	string	Yes	—	Name of the backed up index
limit	integer	No	—	The number of results to return per page.
paginationToken	string	No	—	The token to use to retrieve the next page of results.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "index_name": {
      "type": "string",
      "description": "Name of the backed up index"
    },
    "limit": {
      "type": "integer",
      "description": "The number of results to return per page."
    },
    "paginationToken": {
      "type": "string",
      "description": "The token to use to retrieve the next page of results."
    }
  },
  "required": [
    "PCID",
    "index_name"
  ]
}

---

pinecone_list_indexes

List indexes

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    }
  },
  "required": [
    "PCID"
  ]
}

---

pinecone_list_models

List available models

Parameters:

Parameter	Type	Required	Default	Description
type	string	No	—	Filter models by type (‘embed’ or ‘rerank’).
vector_type	string	No	—	Filter embedding models by vector type (‘dense’ or ‘sparse’). Only relevant when type=embed.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "type": {
      "type": "string",
      "description": "Filter models by type ('embed' or 'rerank')."
    },
    "vector_type": {
      "type": "string",
      "description": "Filter embedding models by vector type ('dense' or 'sparse'). Only relevant when `type=embed`."
    }
  },
  "required": [
    "PCID"
  ]
}

---

pinecone_list_project_backups

List backups for all indexes in a project

Parameters:

Parameter	Type	Required	Default	Description
limit	integer	No	—	The number of results to return per page.
paginationToken	string	No	—	The token to use to retrieve the next page of results.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "limit": {
      "type": "integer",
      "description": "The number of results to return per page."
    },
    "paginationToken": {
      "type": "string",
      "description": "The token to use to retrieve the next page of results."
    }
  },
  "required": [
    "PCID"
  ]
}

---

pinecone_list_restore_jobs

List restore jobs

Parameters:

Parameter	Type	Required	Default	Description
limit	integer	No	—	The number of results to return per page.
paginationToken	string	No	—	The token to use to retrieve the next page of results.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "limit": {
      "type": "integer",
      "description": "The number of results to return per page."
    },
    "paginationToken": {
      "type": "string",
      "description": "The token to use to retrieve the next page of results."
    }
  },
  "required": [
    "PCID"
  ]
}

---

pinecone_rerank

Rerank results

Parameters:

Parameter	Type	Required	Default	Description
documents	object[]	Yes	—	The documents to rerank.
model	string	Yes	—	The model to use for reranking.
parameters	object	No	—	Additional model-specific parameters. Refer to the model guide for available model parameters.
query	string	Yes	—	The query to rerank documents against.
rank_fields	string[]	No	—	The field(s) to consider for reranking. If not provided, the default is ["text"]. The number of fields supported is model-specific.
return_documents	boolean	No	—	Whether to return the documents in the response.
top_n	integer	No	—	The number of results to return sorted by relevance. Defaults to the number of inputs.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "documents": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "The documents to rerank."
    },
    "model": {
      "type": "string",
      "description": "The [model](https://docs.pinecone.io/guides/search/rerank-results#reranking-models) to use for reranking."
    },
    "parameters": {
      "type": "object",
      "description": "Additional model-specific parameters. Refer to the [model guide](https://docs.pinecone.io/guides/search/rerank-results#reranking-models) for available model parameters."
    },
    "query": {
      "type": "string",
      "description": "The query to rerank documents against."
    },
    "rank_fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The field(s) to consider for reranking. If not provided, the default is `[\"text\"]`.  The number of fields supported is [model-specific](https://docs.pinecone.io/guides/search/rerank-results#reranking-models)."
    },
    "return_documents": {
      "type": "boolean",
      "description": "Whether to return the documents in the response."
    },
    "top_n": {
      "type": "integer",
      "description": "The number of results to return sorted by relevance. Defaults to the number of inputs."
    }
  },
  "required": [
    "PCID",
    "documents",
    "model",
    "query"
  ]
}