Skip to content
Wombat

pinecone

Inserts items into a Pinecone index.

Introduced in version 4.31.0.

# Common config fields, showing default values
output:
  label: ""
  pinecone:
    max_in_flight: 64
    batching:
      count: 0
      byte_size: 0
      period: ""
      check: ""
    host: "" # No default (required)
    api_key: "" # No default (required)
    operation: upsert-vectors
    id: "" # No default (required)
    vector_mapping: root = this.embeddings_vector # No default (optional)
    metadata_mapping: root = @ # No default (optional)

Performance

This output benefits from sending multiple messages in flight in parallel for improved performance. You can tune the max number of in flight messages (or message batches) with the field max_in_flight.

This output benefits from sending messages as a batch for improved performance. Batches can be formed at both the input and output level. You can find out more in this doc.

Fields

max_in_flight

The maximum number of messages to have in flight at a given time. Increase this to improve throughput.

Type: int

Default: 64

batching

Allows you to configure a batching policy.

Type: object

# Examples


batching:
  byte_size: 5000
  count: 0
  period: 1s


batching:
  count: 10
  period: 1s


batching:
  check: this.contains("END BATCH")
  count: 0
  period: 1m

batching.count

A number of messages at which the batch should be flushed. If 0 disables count based batching.

Type: int

Default: 0

batching.byte_size

An amount of bytes at which the batch should be flushed. If 0 disables size based batching.

Type: int

Default: 0

batching.period

A period in which an incomplete batch should be flushed regardless of its size.

Type: string

Default: ""

# Examples


period: 1s


period: 1m


period: 500ms

batching.check

A Bloblang query that should return a boolean value indicating whether a message should end a batch.

Type: string

Default: ""

# Examples


check: this.type == "end_of_transaction"

batching.processors

A list of processors to apply to a batch as it is flushed. This allows you to aggregate and archive the batch however you see fit. Please note that all resulting messages are flushed as a single batch, therefore splitting the batch into smaller batches using these processors is a no-op.

Type: array

# Examples


processors:
  - archive:
      format: concatenate


processors:
  - archive:
      format: lines


processors:
  - archive:
      format: json_array

host

The host for the Pinecone index.

Type: string

api_key

The Pinecone api key.

Type: string

operation

The operation to perform against the Pinecone index.

Type: string

Default: "upsert-vectors"

Options: update-vector , upsert-vectors , delete-vectors .

namespace

The namespace to write to - writes to the default namespace by default. This field supports interpolation functions.

Type: string

Default: ""

id

The ID for the index entry in Pinecone. This field supports interpolation functions.

Type: string

vector_mapping

The mapping to extract out the vector from the document. The result must be a floating point array. Required if not a delete operation.

Type: string

# Examples


vector_mapping: root = this.embeddings_vector


vector_mapping: root = [1.2, 0.5, 0.76]

metadata_mapping

An optional mapping of message to metadata in the Pinecone index entry.

Type: string

# Examples


metadata_mapping: root = @


metadata_mapping: root = metadata()


metadata_mapping: 'root = {"summary": this.summary, "foo": this.other_field}'