Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Ucbepic Docetl Directive MapResolveToMapWithCategories

From Leeroopedia


Knowledge Sources
Domains Pipeline_Optimization, LLM_Operations
Last Updated 2026-02-08 00:00 GMT

Overview

Concrete tool for replacing a Map -> Resolve pattern with a single Map that uses predefined categories provided by the DocETL reasoning optimizer.

Description

The MapResolveToMapWithCategoriesDirective class replaces a Map -> Resolve pattern with a single Map operation that has predefined categories. The agent analyzes the data and task to propose a set of canonical categories, and the new Map forces outputs into one of these categories (or "none of the above"). This performs entity resolution deterministically by standardizing outputs upfront, avoiding the need for pairwise comparisons.

Usage

The MOAR agent applies this directive when a Map operation produces outputs that are then resolved/deduplicated, and the set of valid output categories can be enumerated upfront. More efficient than Resolve when the category space is small and well-defined (e.g., standardizing company types, product categories, sentiment labels).

Code Reference

Source Location

Signature

class MapResolveToMapWithCategoriesDirective(Directive):
    name = "map_resolve_to_map_with_categories"
    description = "Replace a Map -> Resolve pattern with a single Map using predefined categories for deterministic entity resolution."

    def check_applicability(self, ...) -> Tuple[bool, str]: ...
    def apply(self, ...) -> Tuple[List[Dict], List[Dict], str, dict]: ...

Import

from docetl.reasoning_optimizer.directives.map_resolve_to_map_with_categories import MapResolveToMapWithCategoriesDirective

I/O Contract

Inputs

Name Type Required Description
op_config Dict Yes Operation configuration to transform
pipeline_ops List[Dict] Yes Full pipeline operations list
op_idx int Yes Index of target operation
dataset_descriptions Dict Yes Dataset schema descriptions

Outputs

Name Type Description
new_ops List[Dict] Transformed operation configs
new_steps List[Dict] Updated pipeline steps
explanation str Human-readable description of changes
metadata dict Additional metadata about the transformation

Usage Examples

# Directives are typically invoked by the MOAR agent automatically
# Example of manual invocation:
from docetl.reasoning_optimizer.directives.map_resolve_to_map_with_categories import MapResolveToMapWithCategoriesDirective

directive = MapResolveToMapWithCategoriesDirective()
applicable, reason = directive.check_applicability(op_config, pipeline_ops, op_idx, dataset_descriptions)
if applicable:
    new_ops, new_steps, explanation, metadata = directive.apply(op_config, pipeline_ops, op_idx, dataset_descriptions)

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment