EditValidation

Edit an existing validation plan with a plain-English instruction using an LLM.

Usage

EditValidation(
    validation,
    instruction,
    model,
    data=None,
    api_key=None,
    verify_ssl=True,
    max_reprompts=1
)

While DraftValidation generates a validation plan from scratch by profiling a table, EditValidation takes an existing plan plus a natural-language instruction (e.g., “add a freshness check on updated_at, tighten the email regex, and drop the price > 0 check”) and produces a revised plan. You review the change as a diff and explicitly accept() it before anything runs, keeping a human in control.

EditValidation reuses the same provider abstraction as DraftValidation (via the chatlas package), supporting the "anthropic", "openai", "ollama", "bedrock", and "azure-openai" providers. Install the optional requirements with pip install pointblank[generate].

Warning

The EditValidation class is experimental. Please report any issues you encounter in the Pointblank issue tracker.

Parameters

validation: Any: The existing validation plan to edit. This can be a Validate object, a Python code string (such as the output of Validate.to_code()), a YAML configuration string, or a path to a .py or .yaml/.yml file. All inputs are normalized to Pointblank code before being sent to the model.
instruction: str: A plain-English description of the changes to make to the plan.
model: str: The model to be used. This should be in the form of provider:model (e.g., "anthropic:claude-opus-4-8"). Supported providers are "anthropic", "openai", "ollama", "bedrock", and "azure-openai".
data: Any = None: Optional data table. When provided, a DataScan summary of the table is included in the prompt so the model can make informed edits (e.g., tightening a range using observed min/max values). It is also used as the default data source when building a Validate via accept().
api_key: str | None = None: The API key to be used for the model.
verify_ssl: bool = True: Whether to verify SSL certificates when making requests to the LLM provider. Defaults to True. Use with caution as disabling SSL verification can pose security risks.
max_reprompts: int = 1: The maximum number of times to automatically re-prompt the model when the returned code fails the syntax/lint check, before surfacing the result to the user. Defaults to 1.

Returns

EditValidation: An EditValidation object exposing the revised plan through to_code(), diff(), changed_steps(), and accept().

Notes On Data Sent To The Model Provider

As with DraftValidation, only a JSON summary of the table (generated by DataScan) is ever sent to the model, never the underlying rows. If data= is omitted, no table information is sent at all; the model edits the plan using only the plan code and your instruction.

Examples

import pointblank as pb

# An existing plan
validation = (
    pb.Validate(data=pb.load_dataset("small_table"))
    .col_vals_gt(columns="d", value=100)
    .col_vals_regex(columns="b", pattern="[0-9]-[a-z]{3}")
)

# Edit it with a plain-English instruction
edited = pb.EditValidation(
    validation=validation,
    instruction="Loosen the `d` check to value=50 and add a not-null check on column `a`.",
    model="anthropic:claude-opus-4-8",
    data=pb.load_dataset("small_table"),
)

print(edited.diff())        # review the change
plan = edited.accept()      # a Validate you can .interrogate()

Methods

Name	Description
accept()	Execute the revised plan and return the resulting Validate object.
changed_steps()	Return a structured, step-level list of the changes between the plans.
diff()	Return a unified textual diff of the original plan versus the revised plan.
from_plans()	Build an EditValidation from two known plans, without calling a model.
review()	Return a `great_tables` GT object summarizing the step-level changes.
to_code()	Return the revised validation plan as Python code.
validate_syntax()	Return whether the revised plan parses and uses only known validation methods.

accept()

Execute the revised plan and return the resulting Validate object.

Usage

Source

accept(data=None)

The returned Validate has NOT been interrogated; call .interrogate() on it to run the validation.

Parameters

data: Any = None: The data table to bind to the plan’s your_data placeholder. If omitted, the data= provided to EditValidation is used. One of the two must be present.

Returns

Validate: The revised validation plan as a Validate object.

changed_steps()

Return a structured, step-level list of the changes between the plans.

Usage

Source

changed_steps()

Unlike diff(), which is a textual diff sensitive to formatting, this compares the two plans at the level of validation steps and is robust to reformatting. Each entry is a dict with an "action" of "add", "remove", or "modify", a "method" name, and the relevant "old"/"new" step text.

Returns

list[dict]: One record per changed step, e.g. [{"action": "modify", "method": "col_vals_gt", "old": "col_vals_gt(columns="d", " "value=100)", "new": "col_vals_gt(columns="d", value=50)"}].

diff()

Return a unified textual diff of the original plan versus the revised plan.

Usage

Source

diff()

from_plans()

Build an EditValidation from two known plans, without calling a model.

Usage

Source

from_plans(original, revised, instruction="Manual plan comparison")

This is a lightweight way to compare an original plan against a revised one and review the difference with diff(), changed_steps(), and review(). It is useful for reviewing the change between two saved versions of a plan (for example, in code review) and does not require an LLM provider or any API key.

Parameters

original: Any: The original plan. Accepts anything the validation= argument accepts: a Validate object, a code string, a YAML string, or a file path.
revised: Any: The revised plan, in any of the same forms as original.
instruction: str = "Manual plan comparison": An optional label describing the comparison (shown as the subtitle in review()).

Returns

EditValidation: An EditValidation whose original/revised plans are the ones supplied, ready for diff(), changed_steps(), review(), and accept().

Examples

import pointblank as pb

v1 = pb.Validate(data=pb.load_dataset("small_table")).col_vals_gt(columns="d", value=100)
v2 = pb.Validate(data=pb.load_dataset("small_table")).col_vals_gt(columns="d", value=50)

comparison = pb.EditValidation.from_plans(v1, v2)
print(comparison.diff())

review()

Return a great_tables GT object summarizing the step-level changes.

Usage

Source

review()

This renders the added, removed, and modified steps side by side for quick human review before accepting the edit. It pairs with accept(): review the change, then accept it.

Returns

GT: A great_tables table with one row per changed step.

to_code()

Return the revised validation plan as Python code.

Usage

Source

to_code()

validate_syntax()

Return whether the revised plan parses and uses only known validation methods.

Usage

Source

validate_syntax()