Implementation:Ucbepic Docetl Directive ChangeModelCost
| Knowledge Sources | |
|---|---|
| Domains | Pipeline_Optimization, LLM_Operations |
| Last Updated | 2026-02-08 00:00 GMT |
Overview
Concrete tool for switching an operator to a more cost-effective LLM model provided by the DocETL reasoning optimizer.
Description
The ChangeModelCostDirective class rewrites an operator to use a more cost-effective LLM model to optimize expenses. It prioritizes cost savings while maintaining adequate performance, typically suggesting cheaper models like gpt-4o-mini or gpt-5-nano for simpler tasks. The module also includes a get_cheaper_models helper function and a create_model_specific_directives factory that generates model-targeted directive instances.
Usage
The MOAR agent applies this directive when cost optimization is the primary concern and the task can be performed adequately by a less expensive model. Suitable for simple extraction, basic classification, or high-volume processing where budget constraints are important.
Code Reference
Source Location
- Repository: Ucbepic_Docetl
- File: docetl/reasoning_optimizer/directives/change_model_cost.py
- Lines: 1-395
Signature
class ChangeModelCostDirective(Directive):
name = "change model cost"
description = "Rewrites an operator to use a more cost-effective LLM model to optimize expenses."
def check_applicability(self, ...) -> Tuple[bool, str]: ...
def apply(self, ...) -> Tuple[List[Dict], List[Dict], str, dict]: ...
Import
from docetl.reasoning_optimizer.directives.change_model_cost import ChangeModelCostDirective
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.change_model_cost import ChangeModelCostDirective
directive = ChangeModelCostDirective()
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)