Foundation Models Text Generation API, gRPC: TokenizerService.TokenizeCompletion
RPC method for tokenizing content of CompletionRequest
gRPC request
rpc TokenizeCompletion (CompletionRequest) returns (TokenizeResponse)
CompletionRequest
{
"modelUri": "string",
"completionOptions": {
"stream": "bool",
"temperature": "google.protobuf.DoubleValue",
"maxTokens": "google.protobuf.Int64Value"
},
"messages": [
{
"role": "string",
// Includes only one of the fields `text`, `toolCallList`, `toolResultList`
"text": "string",
"toolCallList": {
"toolCalls": [
{
// Includes only one of the fields `functionCall`
"functionCall": {
"name": "string",
"arguments": "google.protobuf.Struct"
}
// end of the list of possible fields
}
]
},
"toolResultList": {
"toolResults": [
{
// Includes only one of the fields `functionResult`
"functionResult": {
"name": "string",
// Includes only one of the fields `content`
"content": "string"
// end of the list of possible fields
}
// end of the list of possible fields
}
]
}
// end of the list of possible fields
}
],
"tools": [
{
// Includes only one of the fields `function`
"function": {
"name": "string",
"description": "string",
"parameters": "google.protobuf.Struct"
}
// end of the list of possible fields
}
]
}
Request for the service to generate text completion.
Field |
Description |
modelUri |
string The ID of the model to be used for completion generation. |
completionOptions |
Configuration options for completion generation. |
messages[] |
A list of messages representing the context for the completion model. |
tools[] |
List of tools that are available for the model to invoke during the completion generation. |
CompletionOptions
Defines the options for completion generation.
Field |
Description |
stream |
bool Enables streaming of partially generated text. |
temperature |
Affects creativity and randomness of responses. Should be a double number between 0 (inclusive) and 1 (inclusive). |
maxTokens |
The limit on the number of tokens used for single completion generation. |
Message
A message object representing a wrapper over the inputs and outputs of the completion model.
Field |
Description |
role |
string The ID of the message sender. Supported roles:
|
text |
string Textual content of the message. Includes only one of the fields Message content. |
toolCallList |
List of tool calls made by the model as part of the response generation. Includes only one of the fields Message content. |
toolResultList |
List of tool results returned from external tools that were invoked by the model. Includes only one of the fields Message content. |
ToolCallList
Represents a list of tool calls.
Field |
Description |
toolCalls[] |
A list of tool calls to be executed. |
ToolCall
Represents a call to a tool.
Field |
Description |
functionCall |
Represents a call to a function. Includes only one of the fields |
FunctionCall
Represents the invocation of a function with specific arguments.
Field |
Description |
name |
string The name of the function being called. |
arguments |
The structured arguments passed to the function. |
ToolResultList
Represents a list of tool results.
Field |
Description |
toolResults[] |
A list of tool results. |
ToolResult
Represents the result of a tool call.
Field |
Description |
functionResult |
Represents the result of a function call. Includes only one of the fields |
FunctionResult
Represents the result of a function call.
Field |
Description |
name |
string The name of the function that was executed. |
content |
string The result of the function call, represented as a string. Includes only one of the fields |
Tool
Represents a tool that can be invoked during completion generation.
Field |
Description |
function |
Represents a function that can be called. Includes only one of the fields |
FunctionTool
Represents a function tool that can be invoked during completion generation.
Field |
Description |
name |
string The name of the function. |
description |
string A description of the function's purpose or behavior. |
parameters |
A JSON Schema that defines the expected parameters for the function. |
TokenizeResponse
{
"tokens": [
{
"id": "int64",
"text": "string",
"special": "bool"
}
],
"modelVersion": "string"
}
Response containing tokenized content from request.
Field |
Description |
tokens[] |
A list of tokens obtained from tokenization. |
modelVersion |
string Model version (changes with model releases). |
Token
Represents a token, the basic unit of content, used by the foundation model.
Field |
Description |
id |
int64 An internal token identifier. |
text |
string The textual representation of the token. |
special |
bool Indicates whether the token is special or not. Special tokens may define the model's behavior and are not visible to users. |