contrib/libs/yandex-cloud-api-protos/yandex/cloud/ai/llm/v1alpha/llm.proto


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55

syntax = "proto3";

package yandex.cloud.ai.llm.v1alpha;

import "google/protobuf/wrappers.proto";

option go_package = "github.com/yandex-cloud/go-genproto/yandex/cloud/ai/llm/v1alpha;llm";
option java_package = "yandex.cloud.api.ai.llm.v1alpha";

// Defines the options for text generation.
message GenerationOptions {
  // Enables streaming of partially generated text.
  bool partial_results = 1;

  // Affects creativity and randomness of responses. Should be a double number between 0 (inclusive) and 1 (inclusive).
  // Lower values produce more straightforward responses, while higher values lead to increased creativity and randomness.
  google.protobuf.DoubleValue temperature = 2;

  // Sets the maximum limit on the total number of tokens used for both the input prompt and the generated response.
  // Must be greater than zero and not exceed 7400 tokens.
  google.protobuf.Int64Value max_tokens = 3;
}

// Represents an alternative generated response, including its score and token count.
message Alternative {
  // The generated text response.
  string text = 1;

  // The score or confidence of the generated text.
  double score = 2;

  // The number of tokens in the generated response.
  int64 num_tokens = 3;
}

// Represents a message within a chat.
message Message {
  // Identifies the sender of the message.
  string role = 1;

  // The text content of the message.
  string text = 2;
}

// Represents a token, the basic unit of text, used by the LLM.
message Token {
  // An internal token identifier.
  int64 id = 1;

  // The textual representation of the token.
  string text = 2;

  // Indicates whether the token is special or not. Special tokens define the model's behavior and are not visible to users.
  bool special = 3;
}