Property | Description |
|---|---|
Connection | Name of the target connection. |
Target Type | Target type. Select Single Object. |
Object | Name of the target object that represents an index in the Pinecone project. |
Operation | Target operation. You can use only the upsert operation. |
Update Columns | The id field of the Pinecone index that is used as the primary key column when you upsert target data. |
Property | Description |
|---|---|
Batch Size | The number of vectors that you can upsert into the Pinecone index in a single API request. Default is 100. Maximum value is 1000. |
Namespace | The namespace in the selected index where you want to upsert vectors. If you do not specify a namespace, the vectors are saved in the Default namespace in the index. Maximum value is 512 ASCII printable characters. |
Target field | Description |
|---|---|
id | Required. Unique identifier for each record. You can use a Sequence Generator or Expression transformation to create vector IDs. Maximum value is 512 characters. |
values | Required. A dense vector or a vector embedding which is a series of numerical values that represent different dimensions of the data that are essential for understanding patterns, relationships, and underlying structures such as semantic information. You can use a Vector Embedding transformation to create vector embeddings. Maximum value is 20000 dimensions. |
metadata | Optional. Metadata to write to a Pinecone index. Metadata is the additional information associated with the vector embeddings. For example, the original text of the embeddings can be stored in the metadata. Maximum value of metadata per record is 40 KB. |