类别：: :doc:`/sql-reference/functions-string`（AI 函数）

AI_COUNT_TOKENS¶

备注

AI_COUNT_TOKENS 是 COUNT_TOKENS (SNOWFLAKE.CORTEX) 的更新版本。要获得最新功能，请使用 AI_COUNT_TOKENS。

返回指定大型语言模型或特定于任务的函数的提示中的词元数。

语法¶

AI_COUNT_TOKENS(<function_name>, <model_name> , <input_text> )
AI_COUNT_TOKENS(<function_name>, <input_text> )
AI_COUNT_TOKENS(<function_name>, <input_text>, <categories> )

Copy

实参¶

必填：

function_name

包含要作为词元计数基础的函数名称的字符串，例如 'ai_complete' 或 'ai_sentiment'。函数的名称必须以“ai_”开头，并且只能使用小写字母。

Regional availability 表提供了支持的函数的完整列表。

input_text

输入文本，计算其中的令牌。

可选：

model_name

包含要作为词元内容基础的模型名称的字符串。如果 function_name 指定的函数要求您选择要使用的模型（例如 AI_COMPLETE 或 AI_EMBED），则为必需项。

Regional availability 表提供了可用 LLM 模型的列表。但是，目前并非所有模型都受支持。

AI_COMPLETE 不支持以下模型：

claude-4-opus
claude-4-sonnet
claude-3-7-sonnet
claude-3-5-sonnet
openai-gpt-4.1
openai-o4-mini

AI_EMBED 不支持以下模型：

snowflake-arctic-embed-l-v2.0-8k

categories

VARIANT 值的数组，为需要此数据的函数指定要使用的一个或多个类别或标签。类别计入输入词元计数。

返回¶

INTEGER 值，使用给定参数值计算的输入文本词元数。

使用说明¶

函数和模型名称只能使用小写字母。
COUNT_TOKENS 不适用于 SNOWFLAKE.CORTEX 命名空间或微调模型中的 LLM 函数。必须指定以“AI_”开头的函数名称。
COUNT_TOKENS 仅接受文本，不接受图片或音频输入。
COUNT_TOKENS 不使用基于词元的计费方式，仅产生计算成本。
即使某些模型在特定区域不可用，COUNT_TOKENS 也可在所有区域使用。

示例¶

AI_COMPLETE 示例¶

以下 SQL 语句计算 AI_COMPLETE 和 llama3.3-70b 模型提示中的词元数：

SELECT AI_COUNT_TOKENS('ai_complete', 'llama3.3-70b', 'Summarize the insights from this
call transcript in 20 words: "I finally splurged on these after months of hesitation about
the price, and I\'m mostly impressed. The Nulu fabric really is as buttery-soft as everyone says,
and they\'re incredibly comfortable for yoga and lounging. The high-rise waistband stays put
and doesn\'t dig in, which is rare for me. However, I\'m already seeing some pilling after
just a few wears, and they definitely require gentle care. They\'re also quite delicate -
I snagged them slightly on my gym bag zipper. Great for low-impact activities, but I wouldn\'t
recommend for high-intensity workouts. Worth it for the comfort factor"');

Copy

响应：

AI_EMBED 示例¶

以下 SQL 语句计算使用 AI_EMBED 函数和 nv-embed-qa-4' 模型嵌入的文本中的词元数：

SELECT AI_COUNT_TOKENS('ai_embed', 'nv-embed-qa-4', '"I finally splurged on these after months
of hesitation about the price, and I\'m mostly impressed. The Nulu fabric really is as buttery-soft
as everyone says, and they\'re incredibly comfortable for yoga and lounging. The high-rise waistband
stays put and doesn\'t dig in, which is rare for me. However, I\'m already seeing some pilling after
just a few wears, and they definitely require gentle care. They\'re also quite delicate - I snagged
them slightly on my gym bag zipper. Great for low-impact activities, but I wouldn\'t recommend for
high-intensity workouts. Worth it for the comfort factor"');

Copy

响应：

AI_CLASSIFY 示例¶

此示例计算使用给定输入和标签进行文本分类所需的输入词元总数：

SELECT AI_COUNT_TOKENS('ai_classify',
  'One day I will see the world and learn to cook my favorite dishes',
  [
      {'label': 'travel'},
      {'label': 'cooking'},
      {'label': 'reading'},
      {'label': 'driving'}
  ]
);

Copy

响应：

以下示例在上一个示例的基础上添加了每个标签的描述和总体任务描述：

SELECT AI_COUNT_TOKENS('ai_classify',
  'One day I will see the world and learn to cook my favorite dishes',
  [
    {'label': 'travel', 'description': 'content related to traveling'},
    {'label': 'cooking','description': 'content related to food preparation'},
    {'label': 'reading','description': 'content related to reading'},
    {'label': 'driving','description': 'content related to driving a car'}
  ],
  {
    'task_description': 'Determine topics related to the given text'
  };

Copy

响应：

以下示例在前两个示例的基础上添加了标签示例：

SELECT AI_COUNT_TOKENS('ai_classify',
  'One day I will see the world and learn to cook my favorite dishes',
  [
    {'label': 'travel', 'description': 'content related to traveling'},
    {'label': 'cooking','description': 'content related to food preparation'},
    {'label': 'reading','description': 'content related to reading'},
    {'label': 'driving','description': 'content related to driving a car'}
  ],
  {
    'task_description': 'Determine topics related to the given text',
    'examples': [
      {
        'input': 'i love traveling with a good book',
        'labels': ['travel', 'reading'],
        'explanation': 'the text mentions traveling and a good book which relates to reading'
      }
    ]
  }
);

Copy

响应：

AI_SENTIMENT 示例¶

以下 SQL 语句计算使用 AI_SENTIMENT 函数对其进行情绪分析的文本中的词元数量：

SELECT AI_COUNT_TOKENS('ai_sentiment',
  'This place makes the best truffle pizza in the world! Too bad I cannot afford it');

Copy

响应：

以下示例为上一个示例添加了标签：

SELECT AI_COUNT_TOKENS('ai_sentiment',
  'This place makes the best truffle pizza in the world! Too bad I cannot afford it',
  [
    {'label': 'positive'},
    {'label': 'negative'},
    {'label': 'neutral'}
  ]
);

Copy

响应：

法律声明¶

请参阅 Snowflake AI 和 ML。