Google Gemini · Capability

Google Gemini API — Embeddings

Google Gemini API — Embeddings. 1 operations. Lead operation: Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding model.. Self-contained Naftiko capability covering one Google Gemini business surface.

Run with Naftiko Google GeminiEmbeddings

What You Can Do

POST
Embedcontent — Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding model.
/v1/models/model-embedcontent

MCP Tools

google-gemini-generates-text-embedding

Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding model.

Capability Spec

google-gemini-embeddings.yaml Raw ↑
naftiko: 1.0.0-alpha2
info:
  label: Google Gemini API — Embeddings
  description: 'Google Gemini API — Embeddings. 1 operations. Lead operation: Google Gemini Generates a text embedding vector
    from the input Content using the specified Gemini Embedding model.. Self-contained Naftiko capability covering one Google
    Gemini business surface.'
  tags:
  - Google Gemini
  - Embeddings
  created: '2026-05-19'
  modified: '2026-05-19'
binds:
- namespace: env
  keys:
    GOOGLE_GEMINI_API_KEY: GOOGLE_GEMINI_API_KEY
capability:
  consumes:
  - type: http
    namespace: google-gemini-embeddings
    baseUri: https://generativelanguage.googleapis.com/v1beta
    description: Google Gemini API — Embeddings business capability. Self-contained, no shared references.
    resources:
    - name: models-model}:embedContent
      path: /models/{model}:embedContent
      operations:
      - name: embedcontent
        method: POST
        description: Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding
          model.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: model
          in: path
          type: string
          description: 'The model name to use for embedding. Format: models/{model}. Example: models/gemini-embedding-001.'
          required: true
        - name: key
          in: query
          type: string
          description: API key for authentication.
          required: true
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    authentication:
      type: apikey
      key: key
      value: '{{env.GOOGLE_GEMINI_API_KEY}}'
      placement: query
  exposes:
  - type: rest
    namespace: google-gemini-embeddings-rest
    port: 8080
    description: REST adapter for Google Gemini API — Embeddings. One Spectral-compliant resource per consumed operation,
      prefixed with /v1.
    resources:
    - path: /v1/models/model-embedcontent
      name: models-model-embedcontent
      description: REST surface for models-model}:embedContent.
      operations:
      - method: POST
        name: embedcontent
        description: Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding
          model.
        call: google-gemini-embeddings.embedcontent
        with:
          model: rest.model
          key: rest.key
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
  - type: mcp
    namespace: google-gemini-embeddings-mcp
    port: 9090
    transport: http
    description: MCP adapter for Google Gemini API — Embeddings. One tool per consumed operation, routed inline through this
      capability's consumes block.
    tools:
    - name: google-gemini-generates-text-embedding
      description: Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding
        model.
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: google-gemini-embeddings.embedcontent
      with:
        model: tools.model
        key: tools.key
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.