Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Status


Background & Motivation

In today's evolving data landscape, organizations face significant challenges:

...

We propose both embedded and separate HITL patterns:

Option A: Embedded HITLHITL 

(Out of scope this scenario moving this to New AIP)

Code Block
languagepy
collapsetrue
quality_check = LLMDataQualityOperator(

    task_id="customer_quality_analysis",

    data_sources=[customer_s3],

    prompt="Generate data quality validation queries",

    require_approval=True,  # Built-in HITL

    approval_timeout=timedelta(hours=2)

)

...

By completing all the phases


Future Scope:

  1. Embedded HITL as mentioned in the Option A example.
  2. Progress reporting the task running in cycliness, eg: see comment from Unknown User (potiuk)