> ## Documentation Index > Fetch the complete documentation index at: https://docs.gp.scale.com/llms.txt > Use this file to discover all available pages before exploring further. # 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:** ```json { "engine": "sgp_knowledge_base", "name": "My Knowledge Base", "embedding_model": "openai/text-embedding-3-large", } ``` **Example Response:** ```json { "id": "vs_123456789", "project_id": "proj_987654321", "name": "My Knowledge Base", "engine": "sgp_knowledge_base", "created_at": "2024-01-15T10:30:00Z" } ``` ## OpenAPI ````yaml https://dex.sgp.scale.com/openapi.json post /v1/projects/{project_id}/vector-stores openapi: 3.1.0 info: title: Document Understanding API description: API for uploading and processing documents version: 0.4.5 servers: [] security: - ApiKey: [] AccountId: [] tags: - name: Projects description: Operations related to project creation and management - name: Files description: Operations related to file upload and access - name: Parse description: Operations related to starting parse jobs and accessing their results - name: Vector Stores description: Operations related to vector store creation and management - name: Extract description: Operations related to starting extract jobs and accessing their results - name: Research description: Dex Research agent kickoff and results. - name: Jobs description: Operations related to monitoring jobs and their status paths: /v1/projects/{project_id}/vector-stores: post: tags: - Vector Stores summary: Create a new vector store description: |- 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:** ```json { "engine": "sgp_knowledge_base", "name": "My Knowledge Base", "embedding_model": "openai/text-embedding-3-large", } ``` **Example Response:** ```json { "id": "vs_123456789", "project_id": "proj_987654321", "name": "My Knowledge Base", "engine": "sgp_knowledge_base", "created_at": "2024-01-15T10:30:00Z" } ``` operationId: create_vector_store_v1_projects__project_id__vector_stores_post parameters: - name: project_id in: path required: true schema: type: string title: Project Id requestBody: required: true content: application/json: schema: anyOf: - $ref: '#/components/schemas/SGPVectorStoreCreateRequestBase' - $ref: '#/components/schemas/SGPVectorStoreCreateRequestModelsApi' - $ref: '#/components/schemas/SGPKnowledgeBaseCreateRequestBase' - $ref: '#/components/schemas/SGPKnowledgeBaseCreateRequestModelsApi' title: Request responses: '201': description: Vector store created successfully content: application/json: schema: $ref: '#/components/schemas/VectorStoreEntity' '400': description: Bad request - Missing required fields '404': description: Project not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '500': description: >- Internal server error - Failed to create vector store in third-party engine components: schemas: SGPVectorStoreCreateRequestBase: properties: engine: type: string const: sgp_vector_store title: Engine default: sgp_vector_store name: type: string title: Name description: Name of the vector store vector_store_metadata_schema: anyOf: - additionalProperties: type: string enum: - string - int - double - boolean type: object - type: 'null' title: Vector Store Metadata Schema description: >- 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. embedding_type: type: string const: base title: Embedding Type description: Type of embedding configuration for standard models default: base embedding_model: anyOf: - type: string enum: - 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 - type: string title: Embedding Model description: >- Embedding model to use for SGP Vector Store. e.g. openai/text-embedding-3-large type: object required: - name - embedding_model title: SGPVectorStoreCreateRequestBase description: Base embedding configuration using standard models. SGPVectorStoreCreateRequestModelsApi: properties: engine: type: string const: sgp_vector_store title: Engine default: sgp_vector_store name: type: string title: Name description: Name of the vector store vector_store_metadata_schema: anyOf: - additionalProperties: type: string enum: - string - int - double - boolean type: object - type: 'null' title: Vector Store Metadata Schema description: >- 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. embedding_type: type: string const: models_api title: Embedding Type description: Type of embedding configuration for custom deployed models default: models_api model_deployment_id: type: string title: Model Deployment Id description: Model deployment ID for 'models_api' type from Models API V4 type: object required: - name - model_deployment_id title: SGPVectorStoreCreateRequestModelsApi description: Models API embedding configuration using custom deployed models. SGPKnowledgeBaseCreateRequestBase: properties: engine: type: string const: sgp_knowledge_base title: Engine default: sgp_knowledge_base name: type: string title: Name description: Name of the vector store vector_store_metadata_schema: anyOf: - additionalProperties: type: string enum: - string - int - double - boolean type: object - type: 'null' title: Vector Store Metadata Schema description: >- 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. embedding_type: type: string const: base title: Embedding Type description: Type of embedding configuration for standard models default: base embedding_model: type: string title: Embedding Model description: >- Embedding model to use for 'base' type. e.g. openai/text-embedding-3-large type: object required: - name - embedding_model title: SGPKnowledgeBaseCreateRequestBase description: Base embedding configuration using standard models. SGPKnowledgeBaseCreateRequestModelsApi: properties: engine: type: string const: sgp_knowledge_base title: Engine default: sgp_knowledge_base name: type: string title: Name description: Name of the vector store vector_store_metadata_schema: anyOf: - additionalProperties: type: string enum: - string - int - double - boolean type: object - type: 'null' title: Vector Store Metadata Schema description: >- 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. embedding_type: type: string const: models_api title: Embedding Type description: Type of embedding configuration for custom deployed models default: models_api model_deployment_id: type: string title: Model Deployment Id description: Model deployment ID for 'models_api' type from Models API V4 type: object required: - name - model_deployment_id title: SGPKnowledgeBaseCreateRequestModelsApi description: Models API embedding configuration using custom deployed models. VectorStoreEntity: properties: id: type: string title: Id description: ID of the entity project_id: type: string title: Project Id description: ID of the project name: type: string title: Name description: Name of the vector store engine: $ref: '#/components/schemas/VectorStoreEngines' description: Engine used for vector store created_at: type: string format: date-time title: Created At description: When the vector store was created external_id: anyOf: - type: string - type: 'null' title: External Id description: >- 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 '::'. additionalProperties: true type: object required: - id - project_id - name - engine - created_at title: VectorStoreEntity HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError VectorStoreEngines: type: string enum: - sgp_knowledge_base - sgp_vector_store title: VectorStoreEngines ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: ApiKey: type: apiKey in: header name: x-api-key description: API key for authentication AccountId: type: apiKey in: header name: x-selected-account-id description: Selected Account ID ````