OpenAI · Capability

OpenAI Vector Stores — Vector Stores

OpenAI Vector Stores — Vector Stores. Self-contained Naftiko capability for managing collections of files chunked, embedded, and indexed for the file_search tool in the Responses and Assistants APIs.

OpenAI Vector Stores — Vector Stores is a Naftiko capability published by OpenAI, one of 20 capabilities the APIs.io network indexes for this provider. It bundles 1 operation across the POST method rooted at /v1/vector_stores.

The capability includes 1 read-only operation and 2 state-changing operations. Lead operation: Create a new vector store for file_search retrieval. Can be deployed as a REST endpoint, MCP tool, or Agent Skill via Naftiko.

Tagged areas include Openai, Vector Stores, Retrieval, and Search.

Run with Naftiko OpenaiVector StoresRetrievalSearch

What You Can Do

POST
Createvectorstore — Create a new vector store.
/v1/vector_stores

MCP Tools

openai-create-vector-store

Create a new vector store for file_search retrieval.

openai-search-vector-store

Query a vector store with a natural-language query.

read-only idempotent
openai-attach-file-to-vector-store

Attach a File to a vector store for chunking and indexing.

Capability Spec

vector-stores-vector-stores.yaml Raw ↑
naftiko: 1.0.0-alpha2
info:
  label: OpenAI Vector Stores — Vector Stores
  description: 'OpenAI Vector Stores — Vector Stores. Self-contained Naftiko capability for managing
    collections of files chunked, embedded, and indexed for the file_search tool in the Responses and
    Assistants APIs.'
  tags:
  - Openai
  - Vector Stores
  - Retrieval
  - Search
  created: '2026-05-22'
  modified: '2026-05-22'
binds:
- namespace: env
  keys:
    OPENAI_API_KEY: OPENAI_API_KEY
capability:
  consumes:
  - type: http
    namespace: vector-stores-vector-stores
    baseUri: https://api.openai.com/v1
    description: OpenAI Vector Stores business capability.
    resources:
    - name: vector-stores
      path: /vector_stores
      operations:
      - name: createvectorstore
        method: POST
        description: Create a new vector store.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: body
          in: body
          type: object
          required: true
      - name: listvectorstores
        method: GET
        description: List vector stores.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
    - name: vector-store
      path: /vector_stores/{vector_store_id}
      operations:
      - name: getvectorstore
        method: GET
        description: Retrieve a vector store.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: vector_store_id
          in: path
          type: string
          required: true
      - name: deletevectorstore
        method: DELETE
        description: Delete a vector store.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: vector_store_id
          in: path
          type: string
          required: true
    - name: vector-store-search
      path: /vector_stores/{vector_store_id}/search
      operations:
      - name: searchvectorstore
        method: POST
        description: Query a vector store with a natural language query to retrieve relevant chunks with similarity scores.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: vector_store_id
          in: path
          type: string
          required: true
        - name: body
          in: body
          type: object
          required: true
    - name: vector-store-files
      path: /vector_stores/{vector_store_id}/files
      operations:
      - name: listvectorstorefiles
        method: GET
        description: List files attached to a vector store.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: vector_store_id
          in: path
          type: string
          required: true
      - name: createvectorstorefile
        method: POST
        description: Attach a previously uploaded File to a vector store for chunking and indexing.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: vector_store_id
          in: path
          type: string
          required: true
        - name: body
          in: body
          type: object
          required: true
    authentication:
      type: bearer
      token: '{{env.OPENAI_API_KEY}}'
  exposes:
  - type: rest
    namespace: vector-stores-vector-stores-rest
    port: 8080
    description: REST adapter for OpenAI Vector Stores.
    resources:
    - path: /v1/vector_stores
      name: vector-stores
      operations:
      - method: POST
        name: createvectorstore
        description: Create a new vector store.
        call: vector-stores-vector-stores.createvectorstore
        with:
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
  - type: mcp
    namespace: vector-stores-vector-stores-mcp
    port: 9090
    transport: http
    description: MCP adapter for OpenAI Vector Stores.
    tools:
    - name: openai-create-vector-store
      description: Create a new vector store for file_search retrieval.
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: vector-stores-vector-stores.createvectorstore
      with:
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: openai-search-vector-store
      description: Query a vector store with a natural-language query.
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: vector-stores-vector-stores.searchvectorstore
      with:
        vector_store_id: tools.vector_store_id
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: openai-attach-file-to-vector-store
      description: Attach a File to a vector store for chunking and indexing.
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: vector-stores-vector-stores.createvectorstorefile
      with:
        vector_store_id: tools.vector_store_id
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.