google/ai/generativelanguage/v1beta/model.proto

// Copyright 2023 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

syntax = "proto3";

package google.ai.generativelanguage.v1beta;

import "google/api/field_behavior.proto";
import "google/api/resource.proto";

option go_package = "cloud.google.com/go/ai/generativelanguage/apiv1beta/generativelanguagepb;generativelanguagepb";
option java_multiple_files = true;
option java_outer_classname = "ModelProto";
option java_package = "com.google.ai.generativelanguage.v1beta";

// Information about a Generative Language Model.
message Model {
  option (google.api.resource) = {
    type: "generativelanguage.googleapis.com/Model"
    pattern: "models/{model}"
  };

  // Required. The resource name of the `Model`.
  //
  // Format: `models/{model}` with a `{model}` naming convention of:
  //
  // * "{base_model_id}-{version}"
  //
  // Examples:
  //
  // * `models/chat-bison-001`
  string name = 1 [(google.api.field_behavior) = REQUIRED];

  // Required. The name of the base model, pass this to the generation request.
  //
  // Examples:
  //
  // * `chat-bison`
  string base_model_id = 2 [(google.api.field_behavior) = REQUIRED];

  // Required. The version number of the model.
  //
  // This represents the major version
  string version = 3 [(google.api.field_behavior) = REQUIRED];

  // The human-readable name of the model. E.g. "Chat Bison".
  //
  // The name can be up to 128 characters long and can consist of any UTF-8
  // characters.
  string display_name = 4;

  // A short description of the model.
  string description = 5;

  // Maximum number of input tokens allowed for this model.
  int32 input_token_limit = 6;

  // Maximum number of output tokens available for this model.
  int32 output_token_limit = 7;

  // The model's supported generation methods.
  //
  // The method names are defined as Pascal case
  // strings, such as `generateMessage` which correspond to API methods.
  repeated string supported_generation_methods = 8;

  // Controls the randomness of the output.
  //
  // Values can range over `[0.0,1.0]`, inclusive. A value closer to `1.0` will
  // produce responses that are more varied, while a value closer to `0.0` will
  // typically result in less surprising responses from the model.
  // This value specifies default to be used by the backend while making the
  // call to the model.
  optional float temperature = 9;

  // For Nucleus sampling.
  //
  // Nucleus sampling considers the smallest set of tokens whose probability
  // sum is at least `top_p`.
  // This value specifies default to be used by the backend while making the
  // call to the model.
  optional float top_p = 10;

  // For Top-k sampling.
  //
  // Top-k sampling considers the set of `top_k` most probable tokens.
  // This value specifies default to be used by the backend while making the
  // call to the model.
  // If empty, indicates the model doesn't use top-k sampling, and `top_k` isn't
  // allowed as a generation parameter.
  optional int32 top_k = 11;
}