SongGuess
    Preparing search index...

    Interface Ai_Cf_Google_Gemma_3_12B_It_Messages

    interface Ai_Cf_Google_Gemma_3_12B_It_Messages {
        frequency_penalty?: number;
        functions?: { code: string; name: string }[];
        guided_json?: object;
        max_tokens?: number;
        messages: {
            content?:
                | string
                | { image_url?: { url?: string }; text?: string; type?: string }[];
            role?: string;
        }[];
        presence_penalty?: number;
        raw?: boolean;
        repetition_penalty?: number;
        seed?: number;
        stream?: boolean;
        temperature?: number;
        tools?: (
            | {
                description: string;
                name: string;
                parameters: {
                    properties: { [k: string]: { description: string; type: string } };
                    required?: string[];
                    type: string;
                };
            }
            | {
                function: {
                    description: string;
                    name: string;
                    parameters: {
                        properties: { [k: string]: { description: string; type: string } };
                        required?: string[];
                        type: string;
                    };
                };
                type: string;
            }
        )[];
        top_k?: number;
        top_p?: number;
    }
    Index

    Properties

    frequency_penalty? functions? guided_json? max_tokens? messages presence_penalty? raw? repetition_penalty? seed? stream? temperature? tools? top_k? top_p?

    Properties

    frequency_penalty?: number

    Decreases the likelihood of the model repeating the same lines verbatim.

    functions?: { code: string; name: string }[]
    guided_json?: object

    JSON schema that should be fufilled for the response.

    max_tokens?: number

    The maximum number of tokens to generate in the response.

    messages: {
        content?:
            | string
            | { image_url?: { url?: string }; text?: string; type?: string }[];
        role?: string;
    }[]

    An array of message objects representing the conversation history.

    Type Declaration

    • Optionalcontent?: string | { image_url?: { url?: string }; text?: string; type?: string }[]
    • Optionalrole?: string

      The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool').

    presence_penalty?: number

    Increases the likelihood of the model introducing new topics.

    raw?: boolean

    If true, a chat template is not applied and you must adhere to the specific model's expected formatting.

    repetition_penalty?: number

    Penalty for repeated tokens; higher values discourage repetition.

    seed?: number

    Random seed for reproducibility of the generation.

    stream?: boolean

    If true, the response will be streamed back incrementally using SSE, Server Sent Events.

    temperature?: number

    Controls the randomness of the output; higher values produce more random results.

    tools?: (
        | {
            description: string;
            name: string;
            parameters: {
                properties: { [k: string]: { description: string; type: string } };
                required?: string[];
                type: string;
            };
        }
        | {
            function: {
                description: string;
                name: string;
                parameters: {
                    properties: { [k: string]: { description: string; type: string } };
                    required?: string[];
                    type: string;
                };
            };
            type: string;
        }
    )[]

    A list of tools available for the assistant to use.

    Type Declaration

    • {
          description: string;
          name: string;
          parameters: {
              properties: { [k: string]: { description: string; type: string } };
              required?: string[];
              type: string;
          };
      }
      • description: string

        A brief description of what the tool does.

      • name: string

        The name of the tool. More descriptive the better.

      • parameters: {
            properties: { [k: string]: { description: string; type: string } };
            required?: string[];
            type: string;
        }

        Schema defining the parameters accepted by the tool.

        • properties: { [k: string]: { description: string; type: string } }

          Definitions of each parameter.

        • Optionalrequired?: string[]

          List of required parameter names.

        • type: string

          The type of the parameters object (usually 'object').

    • {
          function: {
              description: string;
              name: string;
              parameters: {
                  properties: { [k: string]: { description: string; type: string } };
                  required?: string[];
                  type: string;
              };
          };
          type: string;
      }
      • function: {
            description: string;
            name: string;
            parameters: {
                properties: { [k: string]: { description: string; type: string } };
                required?: string[];
                type: string;
            };
        }

        Details of the function tool.

        • description: string

          A brief description of what the function does.

        • name: string

          The name of the function.

        • parameters: {
              properties: { [k: string]: { description: string; type: string } };
              required?: string[];
              type: string;
          }

          Schema defining the parameters accepted by the function.

          • properties: { [k: string]: { description: string; type: string } }

            Definitions of each parameter.

          • Optionalrequired?: string[]

            List of required parameter names.

          • type: string

            The type of the parameters object (usually 'object').

      • type: string

        Specifies the type of tool (e.g., 'function').

    top_k?: number

    Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises.

    top_p?: number

    Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses.

    Settings

    Member Visibility

    On This Page

    Properties