@juspay/neurolink/dist/providers/sagemaker/streaming.d.ts

The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002

/**
 * Streaming response handling for Amazon SageMaker Provider (Phase 2)
 *
 * This module provides full streaming support with automatic protocol detection
 * and model-specific parsing for various SageMaker deployment patterns.
 */
import { ReadableStream } from "stream/web";
import type { SageMakerStreamChunk, SageMakerUsage, SageMakerConfig } from "../../types/index.js";
/**
 * Create a SageMaker streaming response with automatic protocol detection
 *
 * @param responseStream - Raw response stream from SageMaker endpoint
 * @param endpointName - SageMaker endpoint name for capability detection
 * @param config - SageMaker configuration
 * @param options - Stream options and metadata
 * @returns Promise resolving to ReadableStream compatible with AI SDK
 */
export declare function createSageMakerStream(responseStream: AsyncIterable<Uint8Array>, endpointName: string, config: SageMakerConfig, options?: {
    prompt?: string;
    abortSignal?: AbortSignal;
    onChunk?: (chunk: SageMakerStreamChunk) => void;
    onComplete?: (usage: SageMakerUsage) => void;
    onError?: (error: Error) => void;
}): Promise<ReadableStream<unknown>>;
/**
 * Create a synthetic stream from complete text (for backward compatibility)
 */
export declare function createSyntheticStream(text: string, usage: SageMakerUsage, options?: {
    onChunk?: (chunk: SageMakerStreamChunk) => void;
    onComplete?: (usage: SageMakerUsage) => void;
}): Promise<ReadableStream<unknown>>;
/**
 * Extract REAL token usage from a complete (non-streaming) SageMaker
 * response body when the endpoint reports it. Covers the OpenAI-compatible
 * shape (vLLM / TGI-OpenAI: usage.prompt_tokens/completion_tokens), the
 * generic input_tokens/output_tokens shape, and the HuggingFace TGI shape
 * (details.tokens.input/generated). Returns undefined when no real counts
 * are present so callers can fall back to estimateTokenUsage.
 */
export declare function parseUsageFromResponseBody(body: Record<string, unknown> | Array<Record<string, unknown>>): SageMakerUsage | undefined;
/**
 * Estimate token usage from text content
 *
 * @param prompt - Input prompt text
 * @param completion - Generated completion text
 * @returns Estimated usage information
 */
export declare function estimateTokenUsage(prompt: string, completion: string): SageMakerUsage;