view release on metacpan or  search on metacpan

ollama/ollama-curated.yaml  view on Meta::CPAN

          schema:
            type: string
          required: true
          description: the SHA256 digest of the blob
          example: sha256:c8edda1f17edd2f1b60253b773d837bda7b9d249a61245931a4d7c9a8d350250
      responses:
        '200':
          description: Blob exists on the server
        '404':
          description: Blob was not found
    post:
      operationId: createBlob
      tags:
        - Models
      summary: Create a blob from a file. Returns the server file path.
      parameters:
        - in: path
          name: digest
          schema:
            type: string
          required: true
          description: the SHA256 digest of the blob
          example: sha256:c8edda1f17edd2f1b60253b773d837bda7b9d249a61245931a4d7c9a8d350250
      requestBody:
        content:
          application/octet-stream:
            schema:
              type: string
              format: binary
      responses:
        '201':
          description: Blob was successfully created

components:
  schemas:
    GenerateCompletionRequest:
      type: object
      description: Request class for the generate endpoint.
      properties:
        model:
          type: string
          description: &model_name |
            The model name.

            Model names follow a `model:tag` format. Some examples are `orca-mini:3b-q4_1` and `llama2:70b`. The tag is optional and, if not provided, will default to `latest`. The tag is used to identify a specific version.
          example: llama2:7b
        prompt:
          type: string
          description: The prompt to generate a response.
          example: Why is the sky blue?
        images:
          type: array
          description: (optional) a list of Base64-encoded images to include in the message (for multimodal models such as llava)
          items:
            type: string
            contentEncoding: base64
            description: Base64-encoded image (for multimodal models such as llava)
            example: iVBORw0KGgoAAAANSUhEUgAAAAkAAAANCAIAAAD0YtNRAAAABnRSTlMA/AD+APzoM1ogAAAAWklEQVR4AWP48+8PLkR7uUdzcMvtU8EhdykHKAciEXL3pvw5FQIURaBDJkARoDhY3zEXiCgCHbNBmAlUiyaBkENoxZSDWnOtBmoAQu7TnT+3WuDOA7KBIkAGAGwiNeqjusp/AAAAAElFTkSuQmCC
        system:
          type: string
          description: The system prompt to (overrides what is defined in the Modelfile).
        template:
          type: string
          description: The full prompt or prompt template (overrides what is defined in the Modelfile).
        context:
          type: array
          description: The context parameter returned from a previous request to [generateCompletion], this can be used to keep a short conversational memory.
          items:
            type: integer
        options:
          $ref: '#/components/schemas/RequestOptions'
        format:
          $ref: '#/components/schemas/ResponseFormat'
        raw:
          type: boolean
          description: |
            If `true` no formatting will be applied to the prompt and no context will be returned.

            You may choose to use the `raw` parameter if you are specifying a full templated prompt in your request to the API, and are managing history yourself.
        stream:
          type: boolean
          description: &stream |
            If `false` the response will be returned as a single response object, otherwise the response will be streamed as a series of objects.
          default: false
        keep_alive:
          type: integer
          description: &keep_alive |
            How long (in minutes) to keep the model loaded in memory.

            - If set to a positive duration (e.g. 20), the model will stay loaded for the provided duration.
            - If set to a negative duration (e.g. -1), the model will stay loaded indefinitely.
            - If set to 0, the model will be unloaded immediately once finished.
            - If not set, the model will stay loaded for 5 minutes by default
      required:
        - model
        - prompt
    RequestOptions:
      type: object
      description: Additional model parameters listed in the documentation for the Modelfile such as `temperature`.
      properties:
        num_keep:
          type: integer
          description: |
            Number of tokens to keep from the prompt.
        seed:
          type: integer
          description: |
            Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0)
        num_predict:
          type: integer
          description: |
            Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)
        top_k:
          type: integer
          description: |
            Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
        top_p:
          type: number
          format: float
          description: |
            Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
        tfs_z:
          type: number
          format: float

ollama/ollama-curated.yaml  view on Meta::CPAN

          example: llama2:7b
        destination:
          type: string
          description: Name of the new model.
          example: llama2-backup
      required:
        - source
        - destination
    DeleteModelRequest:
      description: Request class for deleting a model.
      type: object
      properties:
        name:
          type: string
          description: *model_name
          example: llama2:13b
      required:
        - name
    PullModelRequest:
      description: Request class for pulling a model.
      type: object
      properties:
        name:
          type: string
          description: *model_name
          example: llama2:7b
        insecure:
          type: boolean
          description: |
            Allow insecure connections to the library.

            Only use this if you are pulling from your own library during development.
          default: false
        stream:
          type: boolean
          description: *stream
          default: false
      required:
        - name
    PullModelResponse:
      description: |
        Response class for pulling a model.

        The first object is the manifest. Then there is a series of downloading responses. Until any of the download is completed, the `completed` key may not be included.

        The number of files to be downloaded depends on the number of layers specified in the manifest.
      type: object
      properties:
        status:
          $ref: '#/components/schemas/PullModelStatus'
        digest:
          type: string
          description: The model's digest.
          example: 'sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711a'
        total:
          type: integer
          description: Total size of the model.
          example: 2142590208
        completed:
          type: integer
          description: Total bytes transferred.
          example: 2142590208
    PullModelStatus:
      type: string
      description: Status pulling the model.
      enum:
        - pulling manifest
        - downloading digestname
        - verifying sha256 digest
        - writing manifest
        - removing any unused layers
        - success
      example: pulling manifest
    PushModelRequest:
      description: Request class for pushing a model.
      type: object
      properties:
        name:
          type: string
          description: The name of the model to push in the form of <namespace>/<model>:<tag>.
          example: 'mattw/pygmalion:latest'
        insecure:
          type: boolean
          description: |
            Allow insecure connections to the library.

            Only use this if you are pushing to your library during development.
          default: false
        stream:
          type: boolean
          description: *stream
          default: false
      required:
        - name
    PushModelResponse:
      type: object
      description: Response class for pushing a model.
      properties:
        status:
          $ref: '#/components/schemas/PushModelStatus'
        digest:
          type: string
          description: the model's digest
          example: 'sha256:bc07c81de745696fdf5afca05e065818a8149fb0c77266fb584d9b2cba3711a'
        total:
          type: integer
          description: total size of the model
          example: 2142590208
    PushModelStatus:
      type: string
      description: Status pushing the model.
      enum:
        - retrieving manifest
        - starting upload
        - pushing manifest
        - success