Upsert Vectors

vector_stores.upsert(, ) -> VectorStoreUpsertResponse

POST/v5/vector-stores/{vector_store_name}/upsert

Insert new documents or update existing documents in a vector store.

Upsert Behavior: If a document ID already exists, it will be completely replaced with the new content and metadata. The previous document’s text, embedding, and all metadata fields are discarded. If the ID does not exist, a new document is created.

Document Content: Each document supports several modes:

content only: text is automatically embedded using the store’s configured model.
embedding only: pre-computed embedding vector is used directly. Dimension must match the store’s configuration.
Both content and embedding: the pre-computed embedding is stored and text is kept for retrieval/search.
Neither (metadata-only): only metadata is updated on an existing document without re-embedding. If the document does not exist, it will appear as a failure in the batch response.

A store created without an embedding model (dimensions-only) only accepts documents with pre-computed embedding.

Batch Operations: This endpoint supports batch operations with partial success handling and mixed document types (some with raw embeddings, some with content) in the same call.

Metadata: Supports nested metadata with string, number, boolean, object, and array types. Null values are not permitted—omit the field or use an empty string instead.

ParametersExpand Collapse

vector_store_name: str

The name of the vector store

vectors: Iterable[Vector]

Array of documents to upsert

id: str

Unique document ID

content: Optional[TextContentParam]

Text content for documents.

text: str

Text content to be embedded

type: Optional[Literal["text"]]

Content type identifier

embedding: Optional[Iterable[float]]

Pre-computed embedding vector

metadata: Optional[Dict[str, object]]

Key-value metadata

ReturnsExpand Collapse

class VectorStoreUpsertResponse: …

Response for batch insert/upsert operations.

failure_count: int

Number of failed documents

success_count: int

Number of successfully processed documents

failed: Optional[List[Failed]]

Failed documents with their error messages

id: str

Document ID

error: str

Error message describing why the document failed

succeeded: Optional[List[str]]

IDs of successfully processed documents

Upsert Vectors

import os
from scale_gp_beta import SGPClient

client = SGPClient(
    api_key=os.environ.get("SGP_API_KEY"),  # This is the default and can be omitted
)
response = client.vector_stores.upsert(
    vector_store_name="vector_store_name",
    vectors=[{
        "id": "id"
    }],
)
print(response.failure_count)

{
  "failure_count": 0,
  "success_count": 0,
  "failed": [
    {
      "id": "id",
      "error": "error"
    }
  ],
  "succeeded": [
    "string"
  ]
}

Returns Examples

{
  "failure_count": 0,
  "success_count": 0,
  "failed": [
    {
      "id": "id",
      "error": "error"
    }
  ],
  "succeeded": [
    "string"
  ]
}