AxGEPA

Defined in: https://github.com/ax-llm/ax/blob/d2df625e2c2fd70a090d6321c042579c2819f0d1/src/ax/dsp/optimizers/gepa.ts#L29

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

Extends

AxBaseOptimizer

Constructors

Constructor

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

Defined in: https://github.com/ax-llm/ax/blob/d2df625e2c2fd70a090d6321c042579c2819f0d1/src/ax/dsp/optimizers/gepa.ts#L67

Parameters

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

Returns

AxGEPA

Overrides

AxBaseOptimizer.constructor

Methods

compile()

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

Defined in: https://github.com/ax-llm/ax/blob/d2df625e2c2fd70a090d6321c042579c2819f0d1/src/ax/dsp/optimizers/gepa.ts#L131

Multi-objective GEPA: reflective evolution with Pareto frontier

Type Parameters

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

Parameters

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

Returns

Promise<AxParetoResult<OUT>>

Overrides

AxBaseOptimizer.compile

compilePareto()

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/d2df625e2c2fd70a090d6321c042579c2819f0d1/src/ax/dsp/optimizer.ts#L1561

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()

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/d2df625e2c2fd70a090d6321c042579c2819f0d1/src/ax/dsp/optimizer.ts#L1448

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()

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

Defined in: https://github.com/ax-llm/ax/blob/d2df625e2c2fd70a090d6321c042579c2819f0d1/src/ax/dsp/optimizers/gepa.ts#L814

Lightweight auto presets

Parameters

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

Returns

void

getStats()

getStats(): AxOptimizationStats;

Defined in: https://github.com/ax-llm/ax/blob/d2df625e2c2fd70a090d6321c042579c2819f0d1/src/ax/dsp/optimizer.ts#L2494

Get current optimization statistics

Returns

AxOptimizationStats

Current optimization statistics

Inherited from

AxBaseOptimizer.getStats

reset()

reset(): void;

Defined in: https://github.com/ax-llm/ax/blob/d2df625e2c2fd70a090d6321c042579c2819f0d1/src/ax/dsp/optimizers/gepa.ts#L110

Reset optimizer state for reuse with different programs

Returns

void

Overrides

AxBaseOptimizer.reset