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
GitHub Stars NPM Package Twitter Follow

AxCompileOptions

Defined in: https://github.com/ax-llm/ax/blob/242cf18d21de9f9d58c7c82f53305f0605497473/src/ax/dsp/common_types.ts#L159

Properties

PropertyTypeDescription
auto?"light" | "medium" | "heavy"-
customLabels?Record<string, string>Custom labels to include in OpenTelemetry metrics. These labels are merged with axGlobals.customLabels and AI service customLabels.
earlyStoppingPatience?number-
feedbackExamples?readonly any[]-
feedbackFn?(args: Readonly<{ example: AxExample; prediction: unknown; }>) => undefined | string | string[]-
gepaAdapter?AxGEPAAdapter<any, any, any>-
maxDemos?number-
maxIterations?number-
maxMetricCalls?number-
overrideCheckpointInterval?number-
overrideCheckpointLoad?AxCheckpointLoadFn-
overrideCheckpointSave?AxCheckpointSaveFn-
overrideCostTracker?AxCostTracker-
overrideOnEarlyStop?(reason: string, stats: Readonly<AxOptimizationStats>) => void-
overrideOnProgress?(progress: Readonly<AxOptimizationProgress>) => void-
overrideTargetScore?number-
overrideTeacherAI?AxAIService<unknown, unknown, string>-
perfectScore?number-
saveCheckpointOnComplete?boolean-
skipPerfectScore?boolean-
validationExamples?readonly any[]-
verbose?boolean-