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

AxContextCacheRegistryEntry

type AxContextCacheRegistryEntry = object;

Defined in: https://github.com/ax-llm/ax/blob/242cf18d21de9f9d58c7c82f53305f0605497473/src/ax/ai/types.ts#L463

Entry stored in the context cache registry. Used for persisting cache metadata across process restarts.

Properties

cacheName

cacheName: string;

Defined in: https://github.com/ax-llm/ax/blob/242cf18d21de9f9d58c7c82f53305f0605497473/src/ax/ai/types.ts#L465

Provider-specific cache resource name (e.g., “cachedContents/abc123”)


expiresAt

expiresAt: number;

Defined in: https://github.com/ax-llm/ax/blob/242cf18d21de9f9d58c7c82f53305f0605497473/src/ax/ai/types.ts#L467

When the cache expires (timestamp in milliseconds)


tokenCount?

optional tokenCount: number;

Defined in: https://github.com/ax-llm/ax/blob/242cf18d21de9f9d58c7c82f53305f0605497473/src/ax/ai/types.ts#L469

Number of tokens in the cached content