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

AxAIHuggingFaceRequest

type AxAIHuggingFaceRequest = object;

Defined in: https://github.com/ax-llm/ax/blob/9a5a7060a48f9eef46efc680b0cdf6b42bff5df2/src/ax/ai/huggingface/types.ts#L16

Properties

inputs

inputs: string;

Defined in: https://github.com/ax-llm/ax/blob/9a5a7060a48f9eef46efc680b0cdf6b42bff5df2/src/ax/ai/huggingface/types.ts#L18


model

model: AxAIHuggingFaceModel;

Defined in: https://github.com/ax-llm/ax/blob/9a5a7060a48f9eef46efc680b0cdf6b42bff5df2/src/ax/ai/huggingface/types.ts#L17


options?

optional options: object;

Defined in: https://github.com/ax-llm/ax/blob/9a5a7060a48f9eef46efc680b0cdf6b42bff5df2/src/ax/ai/huggingface/types.ts#L30

use_cache?

optional use_cache: boolean;

wait_for_model?

optional wait_for_model: boolean;

parameters

parameters: object;

Defined in: https://github.com/ax-llm/ax/blob/9a5a7060a48f9eef46efc680b0cdf6b42bff5df2/src/ax/ai/huggingface/types.ts#L19

do_sample?

optional do_sample: boolean;

max_new_tokens?

optional max_new_tokens: number;

max_time?

optional max_time: number;

num_return_sequences?

optional num_return_sequences: number;

repetition_penalty?

optional repetition_penalty: number;

return_full_text?

optional return_full_text: boolean;

temperature?

optional temperature: number;

top_k?

optional top_k: number;

top_p?

optional top_p: number;