Documentation

Build LLM-powered agents
with production-ready TypeScript

DSPy for TypeScript. Working with LLMs is complex—they don't always do what you want. DSPy makes it easier to build amazing things with LLMs. Just define your inputs and outputs (signature) and an efficient prompt is auto-generated and used. Connect together various signatures to build complex systems and workflows using LLMs.

15+ LLM Providers
End-to-end Streaming
Auto Prompt Tuning

AxGEPAOptimizationReport

Defined in: https://github.com/ax-llm/ax/blob/242cf18d21de9f9d58c7c82f53305f0605497473/src/ax/dsp/optimizers/gepa.ts#L29

Structured optimization report

Properties

PropertyType
bestSolutionobject
bestSolution.objectivesRecord<string, { percentage: number; value: number; }>
bestSolution.overallScorenumber
paretoFrontierobject
paretoFrontier.hypervolumenumber
paretoFrontier.objectiveSpaceCoveragenumber
paretoFrontier.solutionCountnumber
paretoFrontier.tradeoffs?Record<string, number>[]
recommendationsobject
recommendations.status"good" | "limited" | "single"
recommendations.suggestionsstring[]
statisticsobject
statistics.candidatesExplorednumber
statistics.convergedboolean
statistics.totalEvaluationsnumber
summarystring