LLM-backed data quality assessment (0.0-1.0)
Per-row — runs once for each row.
QUALITY_LLM({{ value }})QUALITY_LLM({{ value }}, '{{ expected_type }}')| name | type | description |
|---|---|---|
| value | VARCHAR | — |
| expected_type(optional) | VARCHAR | Expected type hint |
LLM escape hatch: perfect email
SELECT
quality_llm ('john.smith@gmail.com')LLM escape hatch: empty value
SELECT
quality_llm ('')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)
LLM-backed data quality assessment (0.0-1.0)
Per-row — runs once for each row.
QUALITY_LLM({{ value }})QUALITY_LLM({{ value }}, '{{ expected_type }}')| name | type | description |
|---|---|---|
| value | VARCHAR | — |
| expected_type(optional) | VARCHAR | Expected type hint |
LLM escape hatch: perfect email
SELECT
quality_llm ('john.smith@gmail.com')LLM escape hatch: empty value
SELECT
quality_llm ('')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)