E-MapReduce:AI Center (Beta)

Enable trial access

AI functions currently require trial access. Apply through one of these channels:

• Contact the StarRocks team through your Alibaba Cloud technical support manager or cloud architect.

• Join the DingTalk group by searching for group number 24010016636 in the DingTalk app.

• Fill out the AI Center Application Form.

Configure network access

StarRocks BE nodes need outbound internet access to reach external model service endpoints. Set up a NAT Gateway on the VPC where your cluster runs:

1. Create a NAT Gateway and bind an Elastic IP Address (EIP) to it.

2. Add an SNAT rule that routes traffic from the BE node CIDR block through the NAT Gateway.

3. Confirm that your VPC route tables and security group policies allow outbound traffic.

For setup details, see Public NAT Gateway.

ai_analyze_sentiment

Classifies the sentiment of input text.

Syntax

ai_analyze_sentiment(content)

Parameters

Returns

STRING — 'positive', 'negative', or 'neutral'. Returns NULL if sentiment cannot be determined.

Examples

Single-value test:

SELECT ai_analyze_sentiment('I am happy');
-- Returns: 'positive'

Apply to a table column:

SELECT
  review_id,
  review_text,
  ai_analyze_sentiment(review_text) AS sentiment
FROM customer_reviews
LIMIT 10;

ai_classify

Assigns one label from a list you define.

Syntax

ai_classify(content, labels)

Parameters

Returns

STRING — one element from labels. Returns NULL if classification fails.

Examples

Single-value test:

SELECT ai_classify('My password is leaked.', ['urgent', 'not urgent']);
-- Returns: 'urgent'

Tag product descriptions in bulk:

SELECT
  product_id,
  description,
  ai_classify(description, ['clothing', 'shoes', 'accessories', 'furniture']) AS category
FROM products
LIMIT 10;

ai_extract

Extracts named entities from text and returns them as a JSON object.

Syntax

ai_extract(content, labels)

Parameters

Returns

JSON object where keys are the entity types and values are the extracted text.

Example

SELECT ai_extract(
  'John Doe lives in New York and works for Acme Corp.',
  ['person', 'location', 'organization']
);
-- Returns: {"person":"John Doe","location":"New York","organization":"Acme Corp"}

ai_mask

Replaces specified entity types with [MASKED].

Syntax

ai_mask(content, labels)

Parameters

Returns

STRING with matched entities replaced by [MASKED].

Examples

Single-value test:

SELECT ai_mask(
  'John Doe lives in New York. His email is john.doe@example.com.',
  ['person', 'email']
);
-- Returns: "[MASKED] lives in New York. His email is [MASKED]."

Mask PII across a log table before export:

SELECT
  log_id,
  ai_mask(log_text, ['person', 'email', 'phone']) AS masked_log
FROM audit_logs
LIMIT 10;

ai_fix_grammar

Corrects grammar and spelling in text.

Syntax

ai_fix_grammar(content)

Parameters

Returns

STRING with corrected grammar and spelling.

Example

SELECT ai_fix_grammar('This sentence have some mistake');
-- Returns: "This sentence has some mistake"

ai_summarize

Generates a concise summary of the input text.

Syntax

ai_summarize(content [, max_words])

Parameters

Returns

STRING summary.

Example

SELECT ai_summarize(
  'Apache Spark is a unified analytics engine for large-scale data processing...',
  10
);
-- Returns: "Spark: unified engine for large-scale data processing with APIs and tools."

ai_translate

Translates text into a target language.

Syntax

ai_translate(content, to_lang)

Parameters

Common language codes:

Returns

Translated STRING.

Example

SELECT ai_translate('Hello, how are you?', 'es');
-- Returns: "Hola, ¿cómo estás?"

ai_similarity

Calculates the semantic similarity between two texts.

Syntax

ai_similarity(text1, text2)

Parameters

Returns

FLOAT between 0 and 1. A score of 1.0 means the texts are identical. This score is primarily used for sorting.

Example

SELECT ai_similarity(
  'I enjoy hiking in the mountains.',
  'I love walking through mountain trails.'
);
-- Returns: 0.82

ai_gen

Generates content from a prompt.

Syntax

ai_gen(prompt)

Parameters

Returns

Generated STRING.

Example

SELECT ai_gen('Write a catchy email subject for a summer bike sale with a 20% discount');
-- Returns: "Summer Cycling Carnival: 20% Off for a Limited Time!"

ai_query

Runs general Q&A using a pre-configured system prompt combined with user input.

Syntax

ai_query(prompt)

Parameters

Returns

STRING — the model's answer.

Example

SELECT ai_query('What is the capital of France?');
-- Returns: "Paris"

ai_custom_query

Calls a custom or private model endpoint. All connection and model parameters are passed inline.

Syntax

ai_custom_query(content, parameters)

Parameters

Supported keys in parameters:

Returns

STRING.

Example

SELECT ai_custom_query(
  'I am happy',
  map{
    'endpoint': 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions',
    'model': 'qwen-plus',
    'api_key': 'sk-89c1***********95d0',
    'prompt': 'Classify each text into [positive, negative, neutral, mixed]. Return only the labels in a JSON array, in the same order as the input. Do not include any explanation, markdown formatting, or code block delimiters. Text: ',
    'max_tokens': '100',
    'top_p': '1',
    'temperature': '0.8'
  }
);
-- Returns: "positive"

Model connection

Batch sizes

Each function sends requests to the model in batches. Larger batches reduce the number of model calls and can shorten total response time.

Prompt templates

Each function uses a configurable prompt template. Template placeholders use $0, $1, etc.