Skip to main content
POST
/
v5
/
vector-stores
/
create
Create Vector Store
curl --request POST \
  --url https://api.egp.scale.com/v5/vector-stores/create \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "name": "<string>",
  "embedding_config": {
    "type": "<string>",
    "model_deployment_id": "<string>"
  },
  "embedding_model": "sentence-transformers/all-MiniLM-L12-v2",
  "indexed_metadata_fields": {}
}
'
{
  "name": "<string>",
  "embedding_config": {
    "type": "<string>",
    "model_deployment_id": "<string>"
  },
  "embedding_dimensions": 123,
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "indexed_metadata_fields": {}
}

Authorizations

​
x-api-key
string
header
required

Headers

​
x-selected-account-id
string | null

Body

application/json

Request to create a vector store.

​
name
string
required

A unique name for the vector store within the account

​
embedding_config
EmbeddingConfigModelsAPI · object

The embedding configuration. Either 'base' type with an embedding_model, or 'models_api' type with a model_deployment_id for custom models.

​
embedding_model
enum<string>

The base embedding model to use. Shorthand for embedding_config with type 'base'. Provide either embedding_config or embedding_model, not both.

Available options:
sentence-transformers/all-MiniLM-L12-v2,
sentence-transformers/all-mpnet-base-v2,
sentence-transformers/multi-qa-distilbert-cos-v1,
sentence-transformers/paraphrase-multilingual-mpnet-base-v2,
openai/text-embedding-ada-002,
openai/text-embedding-3-small,
openai/text-embedding-3-large,
embed-english-v3.0,
embed-english-light-v3.0,
embed-multilingual-v3.0,
gemini/text-embedding-005,
gemini/text-multilingual-embedding-002,
gemini/gemini-embedding-001
​
indexed_metadata_fields
Indexed Metadata Fields · object

Dictionary mapping metadata field names to their types for efficient filtering. Only STRING, NUMBER, and BOOLEAN types can be indexed.

Response

Successful Response

Response model for vector store operations.

​
name
string
required

The name of the vector store

​
embedding_config
EmbeddingConfigModelsAPI · object
required

Embedding configuration identifying the model and its type

​
embedding_dimensions
integer
required

Dimensionality of the embedding vectors

​
created_at
string<date-time>
required

Timestamp of creation

​
updated_at
string<date-time>
required

Timestamp of last update

​
indexed_metadata_fields
Indexed Metadata Fields · object

Dictionary mapping metadata field names to their types