view release on metacpan or  search on metacpan

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

          description: |
            Enable embedding only. (Default: false)
        rope_frequency_base:
          type: number
          format: float
          description: |
            The base of the rope frequency scale. (Default: 1.0)
        rope_frequency_scale:
          type: number
          format: float
          description: |
            The scale of the rope frequency. (Default: 1.0)
        num_thread:
          type: integer
          description: |
            Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number o...
    ResponseFormat:
      type: string
      description: |
        The format to return a response in. Currently the only accepted value is json.

        Enable JSON mode by setting the format parameter to json. This will structure the response as valid JSON.

        Note: it's important to instruct the model to use JSON in the prompt. Otherwise, the model may generate large amounts whitespace.
      enum:
        - json
    GenerateCompletionResponse:
      type: object
      description: The response class for the generate endpoint.
      properties:
        model:
          type: string
          description: *model_name
          example: llama2:7b
        created_at:
          type: string
          format: date-time
          description: Date on which a model was created.
          example: 2023-08-04T19:22:45.499127Z
        response:
          type: string
          description: The response for a given prompt with a provided model.
          example: The sky appears blue because of a phenomenon called Rayleigh scattering.
        done:
          type: boolean
          description: Whether the response has completed.
          example: true
        context:
          type: array
          description: |
            An encoding of the conversation used in this response, this can be sent in the next request to keep a conversational memory.
          items:
            type: integer
          example: [ 1, 2, 3 ]
        total_duration:
          type: integer
          description: Time spent generating the response.
          example: 5589157167
        load_duration:
          type: integer
          description: Time spent in nanoseconds loading the model.
          example: 3013701500
        prompt_eval_count:
          type: integer
          description: Number of tokens in the prompt.
          example: 46
        prompt_eval_duration:
          type: integer
          description: Time spent in nanoseconds evaluating the prompt.
          example: 1160282000
        eval_count:
          type: integer
          description: Number of tokens the response.
          example: 113
        eval_duration:
          type: integer
          description: Time in nanoseconds spent generating the response.
          example: 1325948000
    GenerateChatCompletionRequest:
      type: object
      description: Request class for the chat endpoint.
      properties:
        model:
          type: string
          description: *model_name
          example: llama2:7b
        messages:
          type: array
          description: The messages of the chat, this can be used to keep a chat memory
          items:
            $ref: '#/components/schemas/Message'
        format:
          $ref: '#/components/schemas/ResponseFormat'
        options:
          $ref: '#/components/schemas/RequestOptions'
        stream:
          type: boolean
          description: *stream
          default: false
        keep_alive:
          type: integer
          description: *keep_alive
      required:
        - model
        - messages
    GenerateChatCompletionResponse:
      type: object
      description: The response class for the chat endpoint.
      properties:
        message:
          $ref: '#/components/schemas/Message'
        model:
          type: string
          description: *model_name
          example: llama2:7b
        created_at:
          type: string
          format: date-time
          description: Date on which a model was created.
          example: 2023-08-04T19:22:45.499127Z
        done:
          type: boolean
          description: Whether the response has completed.
          example: true
        total_duration:
          type: integer
          description: Time spent generating the response.
          example: 5589157167
        load_duration:
          type: integer
          description: Time spent in nanoseconds loading the model.
          example: 3013701500
        prompt_eval_count:
          type: integer
          description: Number of tokens in the prompt.
          example: 46
        prompt_eval_duration:
          type: integer
          description: Time spent in nanoseconds evaluating the prompt.
          example: 1160282000
        eval_count:
          type: integer
          description: Number of tokens the response.
          example: 113
        eval_duration:
          type: integer
          description: Time in nanoseconds spent generating the response.
          example: 1325948000
    Message:
      type: object
      description: A message in the chat endpoint
      properties:
        role:
          type: string
          description: The role of the message
          enum: [ "system", "user", "assistant" ]
        content:
          type: string
          description: The content of the message
          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
            description: Base64-encoded image (for multimodal models such as llava)
            example: iVBORw0KGgoAAAANSUhEUgAAAAkAAAANCAIAAAD0YtNRAAAABnRSTlMA/AD+APzoM1ogAAAAWklEQVR4AWP48+8PLkR7uUdzcMvtU8EhdykHKAciEXL3pvw5FQIURaBDJkARoDhY3zEXiCgCHbNBmAlUiyaBkENoxZSDWnOtBmoAQu7TnT+3WuDOA7KBIkAGAGwiNeqjusp/AAAAAElFTkSuQmCC
      required:
        - role
        - content
    GenerateEmbeddingRequest:
      description: Generate embeddings from a model.
      type: object
      properties:
        model:
          type: string
          description: *model_name
          example: llama2:7b
        prompt:
          type: string
          description: Text to generate embeddings for.
          example: 'Here is an article about llamas...'
        options:
          $ref: '#/components/schemas/RequestOptions'
      required:
        - model
        - prompt
    GenerateEmbeddingResponse:
      type: object
      description: Returns the embedding information.
      properties:
        embedding:
          type: array
          description: The embedding for the prompt.
          items:
            type: number
            format: double
          example: [ 0.5670403838157654, 0.009260174818336964, ... ]
    CreateModelRequest:
      type: object
      description: Create model request object.
      properties:
        name:
          type: string
          description: *model_name
          example: mario
        modelfile:

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

      properties:
        name:
          type: string
          description: *model_name
          example: llama2:7b
      required:
        - name
    ModelInfo:
      description: Details about a model including modelfile, template, parameters, license, and system prompt.
      type: object
      properties:
        license:
          type: string
          description: The model's license.
          example: <contents of license block>
        modelfile:
          type: string
          description: The modelfile associated with the model.
          example: 'Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llama2:latest\n\nFROM /Users/username/.ollama/models/blobs/sha256:8daa9615cce30c259a9555b1cc250d461d1bc69980...
        parameters:
          type: string
          description: The model parameters.
          example: 'stop [INST]\nstop [/INST]\nstop <<SYS>>\nstop <</SYS>>'
        template:
          type: string
          description: The prompt template for the model.
          example: '[INST] {{ if and .First .System }}<<SYS>>{{ .System }}<</SYS>>\n\n{{ end }}{{ .Prompt }} [/INST]'
    CopyModelRequest:
      description: Request class for copying a model.
      type: object
      properties:
        source:
          type: string
          description: Name of the model to copy.
          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