Built-in discriminator for CHOOSE stages without explicit BY clause.
Table-in, table-out — composes downstream of SELECTs.
| name | type | description |
|---|---|---|
| _table | TABLE | — |
| _conditions | JSON | — |
Routes data through CHOOSE using the built-in discriminator
SELECT
*
FROM
(
VALUES
('revenue', 100),
('profit', 20)
) AS t (metric, amount) THEN CHOOSE (
WHEN 'financial metrics' THEN PASS WHEN 'customer feedback' THEN PASS
) THEN PYTHON ('result = pd.DataFrame({"row_count":[len(df)]})')Identify target audience via zero-shot NLI
LLM-backed audience identification (escape hatch for AUDIENCE)
Assess authenticity of content via zero-shot NLI
LLM-backed authenticity assessment (escape hatch for AUTHENTICITY)
Classify text into user-specified buckets via zero-shot NLI
LLM-backed bucketing (escape hatch for BUCKET)
Built-in discriminator for CHOOSE stages without explicit BY clause.
Table-in, table-out — composes downstream of SELECTs.
| name | type | description |
|---|---|---|
| _table | TABLE | — |
| _conditions | JSON | — |
Routes data through CHOOSE using the built-in discriminator
SELECT
*
FROM
(
VALUES
('revenue', 100),
('profit', 20)
) AS t (metric, amount) THEN CHOOSE (
WHEN 'financial metrics' THEN PASS WHEN 'customer feedback' THEN PASS
) THEN PYTHON ('result = pd.DataFrame({"row_count":[len(df)]})')Identify target audience via zero-shot NLI
LLM-backed audience identification (escape hatch for AUDIENCE)
Assess authenticity of content via zero-shot NLI
LLM-backed authenticity assessment (escape hatch for AUTHENTICITY)
Classify text into user-specified buckets via zero-shot NLI
LLM-backed bucketing (escape hatch for BUCKET)