view release on metacpan or  search on metacpan

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

openapi: 3.1.0
# https://github.com/davidmigloz/langchain_dart/blob/main/packages/ollama_dart/oas/ollama-curated.yaml

info:
  title: Ollama API
  description: API Spec for Ollama API. Please see https://github.com/jmorganca/ollama/blob/main/docs/api.md for more details.
  version: 0.1.9

#servers:
#  - url: http://localhost:11434/api
#    description: Ollama server URL

tags:
  - name: Completions
    description: Given a prompt, the model will generate a completion.
  - name: Chat
    description: Given a list of messages comprising a conversation, the model will return a response.
  - name: Embeddings
    description: Get a vector representation of a given input.
  - name: Models
    description: List and describe the various models available.

paths:
  /generate:
    post:
      operationId: generateCompletion
      tags:
        - Completions
      summary: Generate a response for a given prompt with a provided model.
      description: The final response object will include statistics and additional data from the request.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenerateCompletionRequest'
      responses:
        '200':
          description: Successful operation.
          content:
            application/x-ndjson:
              schema:
                $ref: '#/components/schemas/GenerateCompletionResponse'
  /chat:
    post:
      operationId: generateChatCompletion
      tags:
        - Chat
      summary: Generate the next message in a chat with a provided model.
      description: This is a streaming endpoint, so there will be a series of responses. The final response object will include statistics and additional data from the request.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenerateChatCompletionRequest'
      responses:
        '200':
          description: Successful operation.
          content:
            application/x-ndjson:
              schema:
                $ref: '#/components/schemas/GenerateChatCompletionResponse'
  /embeddings:
    post:
      operationId: generateEmbedding
      tags:
        - Embeddings
      summary: Generate embeddings from a model.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenerateEmbeddingRequest'
      responses:
        '200':
          description: Successful operation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenerateEmbeddingResponse'
  /create:
    post:
      operationId: createModel
      tags:
        - Models
      summary: Create a model from a Modelfile.
      description: It is recommended to set `modelfile` to the content of the Modelfile rather than just set `path`. This is a requirement for remote create. Remote model creation should also create any file blobs, fields such as `FROM` and `ADAPTER`...
      requestBody:
        description: Create a new model from a Modelfile.
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateModelRequest'
      responses:
        '200':
          description: Successful operation.
          content:
            application/x-ndjson:
              schema:
                $ref: '#/components/schemas/CreateModelResponse'
  /tags:
    get:
      operationId: listModels
      tags:
        - Models
      summary: List models that are available locally.
      responses:
        '200':
          description: Successful operation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelsResponse'
  /show:
    post:
      operationId: showModelInfo
      tags:
        - Models
      summary: Show details about a model including modelfile, template, parameters, license, and system prompt.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ModelInfoRequest'
      responses:
        '200':
          description: Successful operation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelInfo'
  /copy:
    post:
      operationId: copyModel
      tags:
        - Models
      summary: Creates a model with another name from an existing model.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CopyModelRequest'
      responses:
        '200':
          description: Successful operation.
  /delete:
    delete:
      operationId: deleteModel
      tags:
        - Models
      summary: Delete a model and its data.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DeleteModelRequest'
      responses:
        '200':
          description: Successful operation.
  /pull:
    post:
      operationId: pullModel
      tags:
        - Models
      summary: Download a model from the ollama library.
      description: Cancelled pulls are resumed from where they left off, and multiple calls will share the same download progress.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PullModelRequest'
      responses:
        '200':
          description: Successful operation.
          content:
            application/x-ndjson:
              schema:
                $ref: '#/components/schemas/PullModelResponse'
  /push:
    post:
      operationId: pushModel
      tags:
        - Models
      summary: Upload a model to a model library.
      description: Requires registering for ollama.ai and adding a public key first.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PushModelRequest'
      responses:
        '200':
          description: Successful operation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PushModelResponse'
  "/blobs/{digest}":
    head:
      operationId: checkBlob
      tags:
        - Models
      summary: Check to see if a blob exists on the Ollama server which is useful when creating models.
      parameters:
        - in: path
          name: digest
          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'