Pinecone
pineconeLong-term Memory for AI. The Pinecone vector database makes it easy to build high-performance vector search applications. Developer-friendly, fully managed, and easily scalable without infrastructure hassles.
Acciones disponibles (30)
Cada acción es una operación que el agente puede ejecutar contra este conector. Haz clic en una acción para ver sus parámetros.
Cancel Bulk ImportPINECONE_CANCEL_BULK_IMPORTAcciónTool to cancel a bulk import operation in Pinecone. Use when you need to stop an ongoing import operation that is not yet finished.
PINECONE_CANCEL_BULK_IMPORTAcciónTool to cancel a bulk import operation in Pinecone. Use when you need to stop an ongoing import operation that is not yet finished.
Parámetros de entrada
idstringObligatorioUnique identifier of the import operation to cancel
index_hoststringObligatorioThe host URL of the index where the bulk import is running. Get this from the list indexes API or Pinecone console (e.g., 'your-index-epf46k1.svc.aped-4627-b74a.pinecone.io')
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Configure IndexPINECONE_CONFIGURE_INDEXAcciónTool to configure an existing Pinecone index, including pod type, replicas, deletion protection, and tags. Use when you need to scale an index vertically or horizontally, enable/disable deletion protection, or update tags. The change is asynchronous; check index status for completion.
PINECONE_CONFIGURE_INDEXAcciónTool to configure an existing Pinecone index, including pod type, replicas, deletion protection, and tags. Use when you need to scale an index vertically or horizontally, enable/disable deletion protection, or update tags. The change is asynchronous; check index status for completion.
Parámetros de entrada
specanyThe desired pod size and replica configuration for the index. For serverless indexes, configure read capacity mode.
tagsanyUpdates custom tags as key-value pairs. Set value to empty string to delete a tag. Keys max 80 chars, values max 120 chars.
index_namestringObligatorioThe name of the index to configure.
api_versionstringRequired date-based version header for the Pinecone API.
deletion_protectionanySets deletion protection for the index. Use 'enabled' to prevent accidental deletion or 'disabled' to allow deletion.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Create BackupPINECONE_CREATE_BACKUPAcciónTool to create a backup of a Pinecone index for disaster recovery and version control. Use when you need to preserve the current state of an index including vectors, metadata, and configuration.
PINECONE_CREATE_BACKUPAcciónTool to create a backup of a Pinecone index for disaster recovery and version control. Use when you need to preserve the current state of an index including vectors, metadata, and configuration.
Parámetros de entrada
nameanyUser-defined identifier for the backup.
index_namestringObligatorioName of the index to backup.
descriptionanyContextual information about the backup purpose.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Create IndexPINECONE_CREATE_INDEXAcciónTool to create a Pinecone index with specified configuration. Use when you need to initialize a new vector database index for storing and querying embeddings.
PINECONE_CREATE_INDEXAcciónTool to create a Pinecone index with specified configuration. Use when you need to initialize a new vector database index for storing and querying embeddings.
Parámetros de entrada
namestringObligatorioIndex identifier (1-45 chars, lowercase alphanumeric or hyphens, must start/end with alphanumeric).
specobjectObligatorioDeployment configuration. Must provide either serverless or pod specification.
metricstringObligatorioenumSimilarity measure. Must be 'dotproduct' for sparse vectors.
cosineeuclideandotproductdimensionanyVector dimensions (1-20,000). Required for dense vectors; omit for sparse vectors.
vector_typeanyVector type: 'dense' (default) or 'sparse'.
deletion_protectionanySet to 'enabled' to prevent accidental deletion.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Create Index with Embedding ModelPINECONE_CREATE_INDEX_FOR_MODELAcciónTool to create a Pinecone index with integrated embedding model for automatic vectorization. Use when you need to set up a new index that automatically converts text to vectors using a pre-configured embedding model.
PINECONE_CREATE_INDEX_FOR_MODELAcciónTool to create a Pinecone index with integrated embedding model for automatic vectorization. Use when you need to set up a new index that automatically converts text to vectors using a pre-configured embedding model.
Parámetros de entrada
namestringObligatorioIndex identifier. Must be 1-45 characters, alphanumeric and hyphens only, must start and end with alphanumeric character.
tagsanyCustom metadata labels. Keys max 80 characters, values max 120 characters.
cloudstringObligatorioenumCloud provider for hosting the index.
gcpawsazureembedobjectObligatorioEmbedding model configuration for automatic vectorization.
regionstringObligatorioDeployment region. Must be valid for the chosen cloud provider (e.g., 'us-east-1' for AWS).
deletion_protectionanyProtection against accidental deletion. Defaults to 'disabled' if not specified.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Create Index from BackupPINECONE_CREATE_INDEX_FROM_BACKUPAcciónTool to create an index from a backup. Use when you need to restore or duplicate index data from a previously saved backup.
PINECONE_CREATE_INDEX_FROM_BACKUPAcciónTool to create an index from a backup. Use when you need to restore or duplicate index data from a previously saved backup.
Parámetros de entrada
namestringObligatorioIndex name, 1-45 characters, alphanumeric lowercase or hyphens only.
tagsanyCustom key-value pairs for organization.
backup_idstringObligatorioThe ID of the backup to create an index from.
deletion_protectionanyEnable or disable deletion safeguards.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Create NamespacePINECONE_CREATE_NAMESPACEAcciónTool to create a namespace within a serverless Pinecone index. Use when you need to organize vectors into isolated partitions.
PINECONE_CREATE_NAMESPACEAcciónTool to create a namespace within a serverless Pinecone index. Use when you need to organize vectors into isolated partitions.
Parámetros de entrada
namestringObligatorioThe name of the namespace to create.
schemaanyOptional schema configuration for metadata indexing behavior. Defines which fields are filterable.
index_hoststringObligatorioThe host URL of the serverless index (e.g., 'index-name-xxxxx.svc.aped-xxxx-xxxx.pinecone.io').
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Delete IndexPINECONE_DELETE_INDEXAcciónTool to permanently delete a Pinecone index. Use when you need to remove an index from your project. Note: Deletion protection and pending collections can prevent deletion.
PINECONE_DELETE_INDEXAcciónTool to permanently delete a Pinecone index. Use when you need to remove an index from your project. Note: Deletion protection and pending collections can prevent deletion.
Parámetros de entrada
index_namestringObligatorioThe name of the index to delete. Example: 'test-index'
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Delete NamespacePINECONE_DELETE_NAMESPACEAcciónTool to permanently delete a namespace from a serverless index. Use when you need to remove an entire namespace and all its data. This operation is irreversible and only supported on serverless indexes.
PINECONE_DELETE_NAMESPACEAcciónTool to permanently delete a namespace from a serverless index. Use when you need to remove an entire namespace and all its data. This operation is irreversible and only supported on serverless indexes.
Parámetros de entrada
namespacestringObligatorioThe namespace identifier to be deleted. This operation is irreversible and will destroy all vectors in the namespace.
index_hoststringObligatorioThe host URL of the serverless index containing the namespace. Can be obtained from the list indexes operation.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Describe BackupPINECONE_DESCRIBE_BACKUPAcciónTool to retrieve detailed information about a specific backup. Use when you need to check backup status, configuration, or metadata.
PINECONE_DESCRIBE_BACKUPAcciónTool to retrieve detailed information about a specific backup. Use when you need to check backup status, configuration, or metadata.
Parámetros de entrada
backup_idstringObligatorioThe unique identifier of the backup to retrieve
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Describe Bulk ImportPINECONE_DESCRIBE_BULK_IMPORTAcciónTool to describe a specific bulk import operation in Pinecone. Use when you need to retrieve detailed information about an import's status, progress, timing, and any errors.
PINECONE_DESCRIBE_BULK_IMPORTAcciónTool to describe a specific bulk import operation in Pinecone. Use when you need to retrieve detailed information about an import's status, progress, timing, and any errors.
Parámetros de entrada
idstringObligatorioUnique identifier for the import operation to describe.
index_hoststringObligatorioThe host URL of the Pinecone index where the bulk import is being performed. This is the data plane URL (e.g., 'my-index-abc123.svc.us-east1-gcp.pinecone.io').
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Describe Index StatsPINECONE_DESCRIBE_INDEX_STATSAcciónTool to get index statistics including vector count per namespace, dimensions, and fullness. Use when you need to understand the contents and status of an index.
PINECONE_DESCRIBE_INDEX_STATSAcciónTool to get index statistics including vector count per namespace, dimensions, and fullness. Use when you need to understand the contents and status of an index.
Parámetros de entrada
filteranyMetadata filter to return statistics only for vectors matching the filter. Note: Not supported on serverless indexes.
index_hoststringObligatorioThe host URL of the index to get stats for (e.g., 'index-name-xxx.svc.region.pinecone.io'). Get this from the list_indexes response.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Describe Restore JobPINECONE_DESCRIBE_RESTORE_JOBAcciónTool to get detailed information about a specific restore job in Pinecone. Use when you need to check the status, progress, or metadata of a restore operation.
PINECONE_DESCRIBE_RESTORE_JOBAcciónTool to get detailed information about a specific restore job in Pinecone. Use when you need to check the status, progress, or metadata of a restore operation.
Parámetros de entrada
job_idstringObligatorioThe ID of the restore job to describe.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Generate EmbeddingsPINECONE_EMBEDAcciónTool to generate vector embeddings for input text using Pinecone's hosted embedding models. Use when you need to convert text into vector representations for semantic search or similarity matching.
PINECONE_EMBEDAcciónTool to generate vector embeddings for input text using Pinecone's hosted embedding models. Use when you need to convert text into vector representations for semantic search or similarity matching.
Parámetros de entrada
modelstringObligatorioThe embedding model to use (e.g., 'multilingual-e5-large').
inputsobject[]ObligatorioList of input objects to generate embeddings for. Each item contains a text field.
parametersanyAdditional model-specific parameters like input_type and truncate.
Parámetros de salida
dataarrayObligatorioArray of embedding objects (dense or sparse).
erroranyError if any occurred during the execution of the action
modelstringObligatorioThe model used to generate embeddings.
usageobjectObligatorioUsage statistics including total tokens processed.
successfulbooleanObligatorioWhether or not the action execution was successful or not
Get Model InformationPINECONE_GET_MODELAcciónTool to retrieve detailed information about a specific model hosted by Pinecone. Use when you need to understand model capabilities for embedding and reranking operations.
PINECONE_GET_MODELAcciónTool to retrieve detailed information about a specific model hosted by Pinecone. Use when you need to understand model capabilities for embedding and reranking operations.
Parámetros de entrada
model_namestringObligatorioThe name of the model to look up.
api_versionstringRequired date-based version header for the Pinecone API.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
List Bulk ImportsPINECONE_LIST_BULK_IMPORTSAcciónTool to list all recent and ongoing bulk import operations in Pinecone. Use when you need to monitor or track the status of data import jobs. Supports pagination with a default limit of 100 imports per page.
PINECONE_LIST_BULK_IMPORTSAcciónTool to list all recent and ongoing bulk import operations in Pinecone. Use when you need to monitor or track the status of data import jobs. Supports pagination with a default limit of 100 imports per page.
Parámetros de entrada
limitanyMax number of operations to return per page. Range: 1-100, default: 100
index_hoststringObligatorioThe host URL of the index to list bulk imports for (e.g., 'index-name-abc123.svc.region.pinecone.io'). Get the host using the List Indexes action.
paginationTokenanyPagination token to continue a previous listing operation
Parámetros de salida
dataobject[]ObligatorioCollection of import operation objects
erroranyError if any occurred during the execution of the action
paginationanyPagination information
successfulbooleanObligatorioWhether or not the action execution was successful or not
List CollectionsPINECONE_LIST_COLLECTIONSAcciónTool to list all collections in a Pinecone project (pod-based indexes only). Use when you need to view available collections.
PINECONE_LIST_COLLECTIONSAcciónTool to list all collections in a Pinecone project (pod-based indexes only). Use when you need to view available collections.
Parámetros de entrada
Sin parámetros.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
List Index BackupsPINECONE_LIST_INDEX_BACKUPSAcciónTool to list all backups for a specific Pinecone index. Use when you need to view available backups for an index. Supports pagination via limit and paginationToken parameters.
PINECONE_LIST_INDEX_BACKUPSAcciónTool to list all backups for a specific Pinecone index. Use when you need to view available backups for an index. Supports pagination via limit and paginationToken parameters.
Parámetros de entrada
limitanyThe number of results to return per page. Must be between 1 and 100.
index_namestringObligatorioName of the backed up index.
paginationTokenanyThe token to use to retrieve the next page of results.
Parámetros de salida
dataobject[]ObligatorioList of backup objects for the specified index.
erroranyError if any occurred during the execution of the action
paginationanyPagination information for navigating results.
successfulbooleanObligatorioWhether or not the action execution was successful or not
List IndexesPINECONE_LIST_INDEXESAcciónTool to list all indexes in a Pinecone project. Use when you need to retrieve all indexes with their configurations and status information.
PINECONE_LIST_INDEXESAcciónTool to list all indexes in a Pinecone project. Use when you need to retrieve all indexes with their configurations and status information.
Parámetros de entrada
Sin parámetros.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
List Available ModelsPINECONE_LIST_MODELSAcciónTool to list all available embedding and reranking models hosted by Pinecone. Use when you need to discover available models or filter by model type (embed/rerank) or vector type (dense/sparse).
PINECONE_LIST_MODELSAcciónTool to list all available embedding and reranking models hosted by Pinecone. Use when you need to discover available models or filter by model type (embed/rerank) or vector type (dense/sparse).
Parámetros de entrada
typeanyFilter models by type. Use 'embed' for embedding models or 'rerank' for reranking models.
vector_typeanyFilter embedding models by vector type. Only relevant when type='embed'. Use 'dense' for dense vectors or 'sparse' for sparse vectors.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
List NamespacesPINECONE_LIST_NAMESPACES_OPERATIONAcciónTool to list all namespaces in a serverless Pinecone index. Use when you need to discover available namespaces for data organization. Returns up to 100 namespaces by default with pagination support.
PINECONE_LIST_NAMESPACES_OPERATIONAcciónTool to list all namespaces in a serverless Pinecone index. Use when you need to discover available namespaces for data organization. Returns up to 100 namespaces by default with pagination support.
Parámetros de entrada
limitanyMaximum number of namespaces to return per page.
prefixanyPrefix filter to return only namespaces that start with this prefix.
index_hoststringObligatorioThe host URL of the index to list namespaces from. You can get this from the list indexes API.
api_versionstringRequired date-based version header for the Pinecone API.
pagination_tokenanyToken for continuing a previous listing operation.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
List Project BackupsPINECONE_LIST_PROJECT_BACKUPSAcciónTool to list all backups for indexes in a Pinecone project. Use when you need to retrieve backup information across all project indexes. Supports pagination with limit and paginationToken parameters.
PINECONE_LIST_PROJECT_BACKUPSAcciónTool to list all backups for indexes in a Pinecone project. Use when you need to retrieve backup information across all project indexes. Supports pagination with limit and paginationToken parameters.
Parámetros de entrada
limitanyNumber of results per page. Must be between 1 and 100. Default: 10.
paginationTokenanyToken for retrieving subsequent result pages. Obtained from the previous response.
Parámetros de salida
dataobject[]ObligatorioList of backup objects.
erroranyError if any occurred during the execution of the action
paginationanyPagination information.
successfulbooleanObligatorioWhether or not the action execution was successful or not
List Restore JobsPINECONE_LIST_RESTORE_JOBSAcciónTool to list all restore jobs for a project with pagination support. Use when you need to view the status of restore operations or track restore progress.
PINECONE_LIST_RESTORE_JOBSAcciónTool to list all restore jobs for a project with pagination support. Use when you need to view the status of restore operations or track restore progress.
Parámetros de entrada
limitanyNumber of results to return per page. Range: 1-100, Default: 10.
paginationTokenanyToken for retrieving the next page of results.
Parámetros de salida
dataobject[]ObligatorioArray of RestoreJobModel objects.
erroranyError if any occurred during the execution of the action
paginationanyPagination information for the result set.
successfulbooleanObligatorioWhether or not the action execution was successful or not
List VectorsPINECONE_LIST_VECTORSAcciónTool to list vector IDs in a Pinecone serverless index. Use when you need to browse or retrieve vector identifiers from a namespace. Supports filtering by prefix and pagination for large result sets.
PINECONE_LIST_VECTORSAcciónTool to list vector IDs in a Pinecone serverless index. Use when you need to browse or retrieve vector identifiers from a namespace. Supports filtering by prefix and pagination for large result sets.
Parámetros de entrada
limitanyMaximum number of vector IDs to return per page. Default is 100.
prefixanyFilter vector IDs by prefix. Does not accept values containing spaces.
namespaceanyThe namespace to list vectors from. If not provided, the default namespace is used.
index_hoststringObligatorioThe host URL of the Pinecone index to list vectors from. Get this from ListIndexes action.
paginationTokenanyPagination token to continue a previous listing operation.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Query VectorsPINECONE_QUERY_VECTORSAcciónTool to perform semantic search within a Pinecone index using a query vector. Retrieves IDs and similarity scores of the most similar items, ordered from most to least similar. Either vector or id parameter must be provided.
PINECONE_QUERY_VECTORSAcciónTool to perform semantic search within a Pinecone index using a query vector. Retrieves IDs and similarity scores of the most similar items, ordered from most to least similar. Either vector or id parameter must be provided.
Parámetros de entrada
idanyVector ID to use as query. Maximum length is 512 characters. Required if vector is not provided.
topKintegerObligatorioNumber of results to return per query. Must be between 1 and 10,000.
filteranyMetadata filtering criteria to constrain results. Example: {"genre": {"$in": ["comedy", "documentary"]}, "year": {"$eq": 2019}}
vectoranyQuery vector values matching index dimensionality. Length must be between 1 and 20,000. Required if id is not provided.
indexHoststringObligatorioThe host URL of the Pinecone index to query. Get this from the list indexes operation.
namespaceanyThe namespace to search. If omitted, searches the default namespace.
sparseVectoranySparse vector representation for hybrid search.
includeValuesanyWhether to include vector data in the response. Default is false.
includeMetadataanyWhether to include metadata in the response. Default is false.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Rerank DocumentsPINECONE_RERANKAcciónTool to rerank documents by semantic relevance to a query. Use when you need to order retrieved documents by their semantic relevance to a user's search query using Pinecone's hosted reranking models.
PINECONE_RERANKAcciónTool to rerank documents by semantic relevance to a query. Use when you need to order retrieved documents by their semantic relevance to a user's search query using Pinecone's hosted reranking models.
Parámetros de entrada
modelstringObligatorioThe reranking model to apply (e.g., 'bge-reranker-v2-m3').
querystringObligatorioThe search query against which documents are ranked.
top_nanyNumber of ranked results to return. Defaults to the total number of input documents if not specified.
documentsobject[]ObligatorioArray of document objects requiring reranking.
parametersanyAdditional model-specific options. Refer to model documentation for supported parameters.
rank_fieldsanyFields to consider for reranking. Defaults to ['text']. Model-specific limits may apply.
return_documentsanyInclude documents in response. Defaults to true.
Parámetros de salida
dataobject[]ObligatorioArray of reranked documents ordered by relevance score.
erroranyError if any occurred during the execution of the action
modelstringObligatorioThe reranking model used.
usageobjectObligatorioUsage information for the rerank operation.
successfulbooleanObligatorioWhether or not the action execution was successful or not
Search Records in NamespacePINECONE_SEARCH_RECORDS_NAMESPACEAcciónTool to search records within a Pinecone namespace using text, vector, or ID query. Use when you need to find similar records based on embeddings or record IDs. Results can optionally be reranked for relevance.
PINECONE_SEARCH_RECORDS_NAMESPACEAcciónTool to search records within a Pinecone namespace using text, vector, or ID query. Use when you need to find similar records based on embeddings or record IDs. Results can optionally be reranked for relevance.
Parámetros de entrada
queryobjectObligatorioQuery configuration including top_k and optional filters, vector, or ID
fieldsanyFields to include in results
rerankanyOptional reranking configuration
namespacestringObligatorioThe namespace to search within
index_hoststringObligatorioThe host URL for the Pinecone index (e.g., 'my-index-abc123.svc.pinecone.io'). Get this from listing indexes.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Start Bulk ImportPINECONE_START_BULK_IMPORTAcciónTool to start an asynchronous bulk import of vectors from object storage (S3, GCS, or Azure Blob Storage) into a Pinecone index. Use when you need to import large volumes of vectors from external storage. Returns an import ID to track the operation status.
PINECONE_START_BULK_IMPORTAcciónTool to start an asynchronous bulk import of vectors from object storage (S3, GCS, or Azure Blob Storage) into a Pinecone index. Use when you need to import large volumes of vectors from external storage. Returns an import ID to track the operation status.
Parámetros de entrada
uristringObligatorioThe URI of the bucket/container and import directory containing data. Format: s3://BUCKET_NAME/IMPORT_DIR, gs://BUCKET_NAME/IMPORT_DIR, or Azure Blob Storage path.
errorModeanyError handling configuration for the import operation.
index_hoststringObligatorioThe host URL of the Pinecone index to import into. Get this from the index details (e.g., 'my-index-abc123.svc.aped-4627-b74a.pinecone.io'). Use List Indexes to find available index hosts.
integrationIdanyThe identifier of the storage integration used to access the data.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Update VectorPINECONE_UPDATE_VECTORAcciónTool to update a vector in Pinecone by ID. Use to overwrite vector values and/or metadata. Supports bulk updates via metadata filters.
PINECONE_UPDATE_VECTORAcciónTool to update a vector in Pinecone by ID. Use to overwrite vector values and/or metadata. Supports bulk updates via metadata filters.
Parámetros de entrada
idstringObligatorioVector's unique identifier. Length: 1-512 characters.
dryRunanyIf true, return the number of records matching the filter without executing the update. Default: false.
filteranyMetadata filter expression for bulk updates. Example: {"genre": {"$in": ["comedy", "documentary"]}, "year": {"$eq": 2019}}
valuesanyVector data to update. Length: 1-20,000 elements. If provided, overwrites previous values.
namespaceanyThe namespace containing the vector to update. If not specified, uses the default namespace.
index_hoststringObligatorioThe host URL of the index to update vectors in. Get this from the list_indexes response (e.g., 'my-index-abc123.svc.region.pinecone.io').
setMetadataanyMetadata to set for the vector. Key-value pairs that will be added or overwrite previous metadata.
sparseValuesanySparse vector representation to update.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Upsert Records to NamespacePINECONE_UPSERT_RECORDS_NAMESPACEAcciónTool to upsert text records into a Pinecone namespace. Use when you need to add or update records with automatic text-to-vector conversion.
PINECONE_UPSERT_RECORDS_NAMESPACEAcciónTool to upsert text records into a Pinecone namespace. Use when you need to add or update records with automatic text-to-vector conversion.
Parámetros de entrada
recordsobject[]ObligatorioList of records to upsert. Each record must have an '_id' field and can contain arbitrary additional fields like 'chunk_text' for text to be converted to vectors.
namespacestringObligatorioThe namespace to upsert records into.
index_hoststringObligatorioThe host URL of the index to upsert records into. Get this from ListIndexes action (e.g., 'test-embed-idx-99999-epf46k1.svc.aped-4627-b74a.pinecone.io').
api_versionstringPinecone API version header.
Parámetros de salida
dataobjectObligatorioData from the action execution
erroranyError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not