Upsert Vectors

curl --request POST \
  --url https://api.egp.scale.com/v5/vector-stores/{vector_store_name}/upsert \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "vectors": [
    {
      "id": "<string>",
      "content": {
        "text": "<string>",
        "type": "text"
      },
      "metadata": {}
    }
  ]
}
'

{
  "success_count": 123,
  "failure_count": 123,
  "succeeded": [
    "<string>"
  ],
  "failed": [
    {
      "id": "<string>",
      "error": "<string>"
    }
  ]
}

Vector Stores

Upsert Vectors

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.

Automatic Embedding: Text content is automatically embedded using the vector store’s configured embedding model. Embedding generation is handled internally—only the text content needs to be provided.

Batch Operations: This endpoint supports batch operations with partial success handling. If some documents fail (e.g., due to validation errors), others will still be processed. The response includes detailed success/failure counts and error messages.

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.

POST

vector-stores

{vector_store_name}

upsert

Upsert Vectors

curl --request POST \
  --url https://api.egp.scale.com/v5/vector-stores/{vector_store_name}/upsert \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "vectors": [
    {
      "id": "<string>",
      "content": {
        "text": "<string>",
        "type": "text"
      },
      "metadata": {}
    }
  ]
}
'

{
  "success_count": 123,
  "failure_count": 123,
  "succeeded": [
    "<string>"
  ],
  "failed": [
    {
      "id": "<string>",
      "error": "<string>"
    }
  ]
}

Authorizations

x-api-key

string

header

required

Headers

x-selected-account-id

string | null

Path Parameters

vector_store_name

string

required

The name of the vector store

Body

application/json

Request to upsert documents.

vectors

VectorDocumentRequest · object[]

required

Array of documents to upsert

Show child attributes

Response

Successful Response

Response for batch insert/upsert operations.

success_count

integer

required

Number of successfully processed documents

failure_count

integer

required

Number of failed documents

succeeded

string[]

IDs of successfully processed documents

failed

FailedDocumentResponse · object[]

Failed documents with their error messages

Show child attributes

Drop Vector Store Delete Vectors

⌘I

Inference

Questions

Rubrics

Vector Stores

Files

Models

Datasets

Dataset Items

Evaluations

Evaluation Groups

Evaluation Charts

Evaluation Dashboards

Evaluation Items

Spans

Span Assessment

Credentials

Agentex Cloud Build

Upsert Vectors

Authorizations

Headers

Path Parameters

Body

Response