Create a new vector store

Create a new vector store for a project.

This endpoint creates a vector store using the specified engine and configuration. Currently supports SGP Knowledge Base engine, but we plan to support more engines in the future.

Authentication:

• For SGP Knowledge Base, SGP credentials are required

Returns:

• Created vector store entity with ID, name, engine, and creation timestamp

Example Request:

{
    "engine": "sgp_knowledge_base",
    "name": "My Knowledge Base",
    "embedding_model": "openai/text-embedding-3-large",
}

Example Response:

{
    "id": "vs_123456789",
    "project_id": "proj_987654321",
    "name": "My Knowledge Base",
    "engine": "sgp_knowledge_base",
    "created_at": "2024-01-15T10:30:00Z"
}

POST /v1/projects/{project_id}/vector-stores

Create a new vector store

cURL

curl --request POST \
  --url https://api.example.com/v1/projects/{project_id}/vector-stores \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --header 'x-selected-account-id: <api-key>' \
  --data '
{
  "name": "<string>",
  "embedding_model": "sentence-transformers/all-MiniLM-L12-v2",
  "engine": "sgp_vector_store",
  "vector_store_metadata_schema": {},
  "embedding_type": "base"
}
'

201

{
  "id": "<string>",
  "project_id": "<string>",
  "name": "<string>",
  "engine": "sgp_knowledge_base",
  "created_at": "2023-11-07T05:31:56Z",
  "external_id": "<string>"
}

Authorizations

x-api-key · string · header · required

API key for authentication

x-selected-account-id · string · header · required

Selected Account ID

Path Parameters

project_id · string · required

Body

application/json

SGPVectorStoreCreateRequestBase

SGPVectorStoreCreateRequestModelsApi

SGPKnowledgeBaseCreateRequestBase

SGPKnowledgeBaseCreateRequestModelsApi

Base embedding configuration using standard models.

name · string · required

Name of the vector store

embedding_model · enum<string> string · required

Embedding model to use for SGP Vector Store. e.g. openai/text-embedding-3-large

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

engine · string · default: sgp_vector_store

Allowed value: "sgp_vector_store"

vector_store_metadata_schema · Vector Store Metadata Schema · object

Schema of the vector store metadata. You can set metadata for parsed documents and they will be indexed as extra metadata in the vector store to filter on when searching.

Show child attributes

embedding_type · string · default: base

Type of embedding configuration for standard models

Allowed value: "base"

Response

201

application/json

Vector store created successfully

id · string · required

ID of the entity

project_id · string · required

ID of the project

name · string · required

Name of the vector store

engine · enum<string> · required

Engine used for vector store

Available options: sgp_knowledge_base, sgp_vector_store

created_at · string<date-time> · required

When the vector store was created

external_id · string | null

Engine-specific external identifier used when calling the upstream API. For SGP Knowledge Base this equals the SGP KB UUID (same as id). For SGP Vector Store this is '<account_id>::'.