MaxCompute:AI_SIMILARITY

Syntax

FLOAT AI_SIMILARITY(
  STRING <model_name>,
  STRING <version_name>,
  STRING <input1>,
  STRING <input2>
  [, STRING <model_parameters>]
);

Parameters

• model_name: Required. A string that specifies the name of the model to use. For more information, see SQL AI functions.

• version_name: Required. A string that specifies the name of the model version to use. To call the default version, you can use DEFAULT_VERSION.

• input1: Required. A string representing the first text for the semantic similarity calculation.

• input2: Required. A string representing the second text for the semantic similarity calculation.

• model_parameters: Optional. A JSON-formatted string that specifies model parameters, such as max_tokens, temperature, and top_p.For example: '{"max_tokens": 500, "temperature": 0.6, "top_p": 0.95}'. The following parameters are supported:

  • max_tokens: Sets the maximum number of tokens to generate in a single model call. For MaxCompute public models, the default value is 4096.

  • temperature: A value between 0 and 1 that controls the randomness of the model's output. A higher value results in more creative and diverse output, while a lower value makes the output more deterministic and conservative.

  • top_p: A value between 0 and 1 that limits the range of candidate tokens the model considers. A higher value results in a wider range and more diversity, while a lower value results in a narrower range and more focused output.

Return value

Returns a FLOAT value between 0 and 1, representing the similarity score of the two input texts. The return rules are as follows:

• A score of 1.0 indicates that the two texts are identical, while a score of 0.0 indicates that they are completely unrelated.

• If input1 or input2 is NULL, the function returns NULL.

• If input1 or input2 is not a STRING, the function returns an error.

Examples

SET odps.sql.ai.treat.as.common.model=true;
SET odps.namespace.schema=true;

SELECT AI_SIMILARITY(
    bigdata_public_modelset.default.`Qwen3-4B-GGUF`,
    DEFAULT_VERSION,
    'MaxCompute is a big data computing platform.',
    'MaxCompute provides large-scale data processing capabilities.'
) AS similarity_score;

-- Result:
+------------------+
| similarity_score |
+------------------+
| 0.85             |
+------------------+

-- Sample data
CREATE TABLE text_pairs (
    text1 STRING,
    text2 STRING
);

INSERT INTO text_pairs VALUES
    ('Cloud computing enables scalable infrastructure.', 'Businesses can scale their IT resources using cloud services.'),
    ('The weather is sunny today.', 'Machine learning algorithms require large datasets.'),
    ('Data warehousing stores historical data for analysis.', 'A data warehouse provides analytical processing of large data volumes.'),
    ('I enjoy reading books.', 'Reading is my favorite hobby.');

-- Compare multiple text pairs for semantic similarity
SET odps.sql.ai.treat.as.common.model=true;
SET odps.namespace.schema=true;

SELECT
    text1,
    text2,
    AI_SIMILARITY(
        bigdata_public_modelset.default.`Qwen3-4B-GGUF`,
        DEFAULT_VERSION,
        text1,
        text2
    ) AS similarity_score
FROM text_pairs
ORDER BY similarity_score DESC;

-- Result
+------------------------------------------------------+-----------------------------------------------------------------------+------------------+
| text1                                                | text2                                                                 | similarity_score |
+------------------------------------------------------+-----------------------------------------------------------------------+------------------+
| Cloud computing enables scalable infrastructure.     | Businesses can scale their IT resources using cloud services.         | 0.92             |
| Data warehousing stores historical data for analysis.| A data warehouse provides analytical processing of large data volumes.| 0.88             |
| I enjoy reading books.                               | Reading is my favorite hobby.                                         | 0.82             |
| The weather is sunny today.                          | Machine learning algorithms require large datasets.                   | 0.05             |
+------------------------------------------------------+-----------------------------------------------------------------------+------------------+