AxGEPA

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/dsp/optimizers/gepa.ts#L140

Single-module GEPA (reflective prompt evolution with Pareto sampling)

Extends

AxBaseOptimizer

Constructors

Constructor

TypeScript

new AxGEPA(args: Readonly<AxOptimizerArgs>): AxGEPA;

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/dsp/optimizers/gepa.ts#L192

Parameters

Parameter	Type
`args`	`Readonly`<`AxOptimizerArgs`>

Returns

AxGEPA

Overrides

AxBaseOptimizer.constructor

Methods

compile()

TypeScript

compile<IN, OUT>(
   program: Readonly<AxProgrammable<IN, OUT>>, 
   examples: readonly AxTypedExample<IN>[], 
   metricFn: 
  | AxMetricFn
  | AxMultiMetricFn, 
options?: AxCompileOptions): Promise<AxParetoResult<OUT>>;

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/dsp/optimizers/gepa.ts#L257

Multi-objective GEPA: reflective evolution with Pareto frontier

Type Parameters

Type Parameter
`IN`
`OUT` extends `AxGenOut`

Parameters

Parameter	Type
`program`	`Readonly`<`AxProgrammable`<`IN`, `OUT`>>
`examples`	readonly `AxTypedExample`<`IN`>[]
`metricFn`	\| `AxMetricFn` \| `AxMultiMetricFn`
`options?`	`AxCompileOptions`

Returns

Promise<AxParetoResult<OUT>>

Overrides

AxBaseOptimizer.compile

compilePareto()

TypeScript

compilePareto<IN, OUT>(
   program: Readonly<AxGen<IN, OUT>>, 
   examples: readonly AxTypedExample<IN>[], 
   metricFn: AxMultiMetricFn, 
options?: AxCompileOptions): Promise<AxParetoResult<OUT>>;

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/dsp/optimizer.ts#L1688

Multi-objective optimization using Pareto frontier Default implementation that leverages the single-objective compile method

Type Parameters

Type Parameter
`IN`
`OUT` extends `AxGenOut`

Parameters

Parameter	Type	Description
`program`	`Readonly`<`AxGen`<`IN`, `OUT`>>	The program to optimize
`examples`	readonly `AxTypedExample`<`IN`>[]	Training examples
`metricFn`	`AxMultiMetricFn`	Multi-objective metric function that returns multiple scores
`options?`	`AxCompileOptions`	Optional configuration options

Returns

Promise<AxParetoResult<OUT>>

Pareto optimization result with frontier of non-dominated solutions

Inherited from

AxBaseOptimizer.compilePareto

compileStream()

TypeScript

compileStream<IN, OUT>(
   program: Readonly<AxGen<IN, OUT>>, 
   examples: readonly AxTypedExample<IN>[], 
   metricFn: AxMetricFn, 
options?: AxCompileOptions): AsyncIterableIterator<AxOptimizationProgress>;

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/dsp/optimizer.ts#L1574

Optimize a program with real-time streaming updates

Type Parameters

Type Parameter
`IN`
`OUT` extends `AxGenOut`

Parameters

Parameter	Type	Description
`program`	`Readonly`<`AxGen`<`IN`, `OUT`>>	The program to optimize
`examples`	readonly `AxTypedExample`<`IN`>[]	Training examples
`metricFn`	`AxMetricFn`	Evaluation metric function
`options?`	`AxCompileOptions`	Optional configuration options

Returns

AsyncIterableIterator<AxOptimizationProgress>

Async iterator yielding optimization progress

Inherited from

AxBaseOptimizer.compileStream

configureAuto()

TypeScript

configureAuto(level: "medium" | "light" | "heavy"): void;

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/dsp/optimizers/gepa.ts#L1032

Lightweight auto presets

Parameters

Parameter	Type
`level`	`"medium"` \| `"light"` \| `"heavy"`

Returns

void

getStats()

TypeScript

getStats(): AxOptimizationStats;

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/dsp/optimizer.ts#L2685

Get current optimization statistics

Returns

AxOptimizationStats

Current optimization statistics

Inherited from

AxBaseOptimizer.getStats

reset()

TypeScript

reset(): void;

Defined in: https://github.com/ax-llm/ax/blob/5b28f9093bb70863b59459bb6df5062d005bce41/src/ax/dsp/optimizers/gepa.ts#L236

Reset optimizer state for reuse with different programs

Returns

void

Overrides

AxBaseOptimizer.reset