Pinecone

Use Pinecone in Sim to generate embeddings, store and update text records or vectors, search by text or vector, retrieve vectors, and manage indexes. Use the returned matches as input to later workflow steps.

Use the block

Generate embeddings, upsert and update text records, delete vectors, search with text or vectors, fetch and list vectors, inspect index statistics, and manage indexes.

Actions

Pinecone Generate Embeddings

Generate embeddings from text using Pinecone's hosted models

Inputs and outputs

Input

Parameter	Type	Required	Description
`model`	string	Yes	Model to use for generating embeddings
`inputs`	array	Yes	Array of text inputs to generate embeddings for
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`data`	array	Generated embeddings data with values and vector type
`model`	string	Model used for generating embeddings
`vector_type`	string	Type of vector generated (dense/sparse)
`usage`	object	Usage statistics for embeddings generation

Pinecone Upsert Text

Insert or update text records in a Pinecone index

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexHost`	string	Yes	Full Pinecone index host URL (e.g., "https://my-index-abc123.svc.pinecone.io")
`namespace`	string	Yes	Namespace to upsert records into (e.g., "documents", "embeddings")
`records`	array	Yes	Record or array of records to upsert, each containing _id, text, and optional metadata
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`statusText`	string	Status of the upsert operation

Pinecone Update Vector

Update the values, sparse values, or metadata of a vector in a Pinecone namespace

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexHost`	string	Yes	Full Pinecone index host URL (e.g., "https://my-index-abc123.svc.pinecone.io")
`id`	string	Yes	Unique ID of the vector to update
`namespace`	string	No	Namespace containing the vector (e.g., "documents", "embeddings")
`values`	array	No	New dense vector values to overwrite the existing values
`sparseValues`	object	No	New sparse vector values with indices and values arrays
`setMetadata`	object	No	Metadata key-value pairs to add or overwrite on the vector
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`statusText`	string	Status of the update operation

Pinecone Delete Vectors

Delete vectors from a Pinecone namespace by IDs, by metadata filter, or delete all

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexHost`	string	Yes	Full Pinecone index host URL (e.g., "https://my-index-abc123.svc.pinecone.io")
`namespace`	string	No	Namespace to delete vectors from (e.g., "documents", "embeddings")
`ids`	array	No	Vector IDs to delete (1-1000 items). Mutually exclusive with deleteAll and filter
`deleteAll`	boolean	No	Delete all vectors in the namespace. Mutually exclusive with ids and filter
`filter`	object	No	Metadata filter selecting vectors to delete (e.g., {"category": {"$eq": "product"}}). Mutually exclusive with ids and deleteAll
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`statusText`	string	Status of the delete operation

Pinecone Search Text

Search for similar text in a Pinecone index

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexHost`	string	Yes	Full Pinecone index host URL (e.g., "https://my-index-abc123.svc.pinecone.io")
`namespace`	string	No	Namespace to search in (e.g., "documents", "embeddings")
`searchQuery`	string	Yes	Text to search for
`topK`	string	No	Number of results to return (e.g., "10", "25")
`fields`	array	No	Fields to return in the results
`filter`	object	No	Filter to apply to the search (e.g., {"category": "tech", "year": {"$gte": 2020}})
`rerank`	object	No	Reranking parameters
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`matches`	array	Search results with ID, score, and metadata
↳ `id`	string	Vector ID
↳ `score`	number	Similarity score
↳ `metadata`	object	Associated metadata
`usage`	object	Usage statistics including tokens, read units, and rerank units
↳ `total_tokens`	number	Total tokens used for embedding
↳ `read_units`	number	Read units consumed
↳ `rerank_units`	number	Rerank units used

Pinecone Search Vector

Search for similar vectors in a Pinecone index

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexHost`	string	Yes	Full Pinecone index host URL (e.g., "https://my-index-abc123.svc.pinecone.io")
`namespace`	string	No	Namespace to search in (e.g., "documents", "embeddings")
`vector`	array	Yes	Vector to search for
`topK`	number	No	Number of results to return (e.g., 10, 25)
`filter`	object	No	Filter to apply to the search (e.g., {"category": "tech", "year": {"$gte": 2020}})
`includeValues`	boolean	No	Include vector values in response
`includeMetadata`	boolean	No	Include metadata in response (true/false)
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`matches`	array	Vector search results with ID, score, values, and metadata
`namespace`	string	Namespace where the search was performed

Pinecone Fetch

Fetch vectors by ID from a Pinecone index

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexHost`	string	Yes	Full Pinecone index host URL (e.g., "https://my-index-abc123.svc.pinecone.io")
`ids`	array	Yes	Array of vector IDs to fetch (e.g., ["vec-001", "vec-002"])
`namespace`	string	No	Namespace to fetch vectors from (e.g., "documents", "embeddings")
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`matches`	array	Fetched vectors with ID, values, metadata, and score
↳ `id`	string	Vector ID
↳ `values`	array	Vector values
↳ `metadata`	object	Associated metadata
↳ `score`	number	Fixed score of 1.0 assigned by this fetch operation; not a similarity-query score
`data`	array	Vector data with values and vector type
↳ `values`	array	Vector values
↳ `vector_type`	string	Vector type (dense/sparse)
`usage`	object	Usage statistics including total read units
↳ `total_tokens`	number	Read units consumed

Pinecone List Vector IDs

List vector IDs in a Pinecone namespace by prefix (serverless indexes only)

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexHost`	string	Yes	Full Pinecone index host URL (e.g., "https://my-index-abc123.svc.pinecone.io")
`namespace`	string	Yes	Namespace to list vector IDs from (e.g., "documents", "embeddings")
`prefix`	string	No	Filter vector IDs by a common prefix (e.g., "doc1#")
`limit`	number	No	Maximum number of IDs to return per page (default 100)
`paginationToken`	string	No	Pagination token from a previous response to fetch the next page
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`vectorIds`	array	Vector IDs in the namespace
`pagination`	object	Pagination info with a next token when more results exist
↳ `next`	string	Token to fetch the next page
`namespace`	string	Namespace the IDs were listed from
`usage`	object	Usage statistics including read units
↳ `total_tokens`	number	Read units consumed

Pinecone Describe Index Stats

Get statistics about a Pinecone index, including per-namespace vector counts

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexHost`	string	Yes	Full Pinecone index host URL (e.g., "https://my-index-abc123.svc.pinecone.io")
`filter`	object	No	Metadata filter to limit which vectors are counted (pod-based indexes only, e.g., {"category": {"$eq": "product"}})
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`namespaces`	json	Map of namespace name to its summary including vectorCount
`dimension`	number	Dimensionality of the indexed vectors
`indexFullness`	number	Fullness of the index (pod-based indexes only)
`totalVectorCount`	number	Total number of vectors across all namespaces

Pinecone List Indexes

List all Pinecone indexes in the project

Inputs and outputs

Input

Parameter	Type	Required	Description
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`indexes`	array	List of indexes with name, dimension, metric, host, spec, and status
↳ `name`	string	Index name
↳ `dimension`	number	Vector dimensionality
↳ `metric`	string	Distance metric (cosine, euclidean, dotproduct)
↳ `host`	string	Index host URL for data-plane operations
↳ `vectorType`	string	Vector type (dense or sparse)
↳ `deletionProtection`	string	Deletion protection (enabled or disabled)
↳ `tags`	object	Custom user tags on the index
↳ `spec`	object	Index spec (serverless or pod configuration)
↳ `status`	object	Index status with ready and state

Pinecone Describe Index

Get the configuration and status of a Pinecone index by name

Inputs and outputs

Input

Parameter	Type	Required	Description
`indexName`	string	Yes	Name of the index to describe
`apiKey`	string	Yes	Pinecone API key

Output

Parameter	Type	Description
`index`	object	Index configuration and status
↳ `name`	string	Index name
↳ `dimension`	number	Vector dimensionality
↳ `metric`	string	Distance metric (cosine, euclidean, dotproduct)
↳ `host`	string	Index host URL for data-plane operations
↳ `vectorType`	string	Vector type (dense or sparse)
↳ `deletionProtection`	string	Deletion protection (enabled or disabled)
↳ `tags`	object	Custom user tags on the index
↳ `spec`	object	Index spec (serverless or pod configuration)
↳ `status`	object	Index status with ready and state