@juspay/neurolink/dist/providers/amazonSagemaker.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

import type { AIProviderName } from "../constants/enums.js";
import { BaseProvider } from "../core/baseProvider.js";
import type { NeuroLink } from "../neurolink.js";
import type { EnhancedGenerateResult, TextGenerationOptions, ValidationSchema, StreamOptions } from "../types/index.js";
import type { LanguageModel } from "../types/index.js";
/**
 * Amazon SageMaker Provider extending BaseProvider
 */
export declare class AmazonSageMakerProvider extends BaseProvider {
    private sagemakerModel;
    private sagemakerConfig;
    private modelConfig;
    constructor(modelName?: string, endpointName?: string, region?: string, neurolink?: NeuroLink, credentials?: {
        accessKeyId?: string;
        secretAccessKey?: string;
        sessionToken?: string;
        region?: string;
        endpoint?: string;
    });
    protected getProviderName(): AIProviderName;
    protected getDefaultModel(): string;
    protected getAISDKModel(): LanguageModel;
    /**
     * Native non-streaming generate.
     *
     * SageMaker's doGenerate makes one invokeEndpoint call and already returns
     * toolCalls; no streaming is involved, so the wire hazard that reverted the
     * first migration does not apply here. This supplies only the multi-step
     * iteration the ai package used to.
     *
     * NOT EXERCISED LIVE. This machine has no SageMaker endpoint or credentials.
     * The single-step shape is identical by construction — with no tool calls the
     * loop breaks after exactly one doGenerate carrying the same options the ai
     * loop passed. The multi-step branch is the new code and wants a real
     * endpoint before it is trusted.
     */
    generate(optionsOrPrompt: TextGenerationOptions | string, analysisSchema?: ValidationSchema): Promise<EnhancedGenerateResult | null>;
    private executeNativeGenerate;
    /**
     * Streaming was previously an `executeStream` override that unconditionally
     * threw "not yet fully implemented" — while `SageMakerLanguageModel.doStream`
     * sat one property access away, complete and working, with its own fallback
     * to a synthetic stream when the endpoint does not support true streaming.
     *
     * This adapts that AI-SDK-shaped result to `BaseProvider`'s `doStream` hook,
     * and the inherited default supplies `executeStream`. The two shapes differ:
     * the language model emits typed parts (`text-delta`, `finish`) on a
     * `ReadableStream`, while the hook wants text chunks plus promises for how
     * the turn ended. Those promises are resolved from the `finish` part by a
     * detached pump, so they settle whether or not the caller reads a chunk.
     */
    protected doStream(options: StreamOptions): Promise<{
        stream: AsyncIterable<{
            content: string;
        }>;
        finishReason: Promise<string>;
        usage: Promise<{
            inputTokens: number;
            outputTokens: number;
        }>;
        warnings?: string[];
    }>;
    protected formatProviderError(error: unknown): Error;
    /**
     * Get SageMaker-specific provider information
     */
    getSageMakerInfo(): {
        endpointName: string;
        modelType: string;
        region: string;
        configured: boolean;
    };
    /**
     * Test basic configuration
     */
    testConnection(): Promise<{
        connected: boolean;
        error?: string;
    }>;
    /**
     * Public method to get the AI SDK model for CLI and external usage
     */
    getModel(): Promise<LanguageModel>;
    /**
     * Test connectivity to the SageMaker endpoint
     */
    testConnectivity(): Promise<{
        success: boolean;
        error?: string;
    }>;
    /**
     * Get model capabilities and information
     */
    getModelCapabilities(): {
        capabilities: {
            streaming: boolean;
            toolCalling: boolean;
            structuredOutput: boolean;
            batchInference: boolean;
            supportedResponseFormats: string[];
            supportedToolTypes: string[];
            maxBatchSize: number;
            adaptiveConcurrency: boolean;
            errorRecovery: boolean;
        };
        modelId: string;
        provider: string;
        specificationVersion: "v2";
        endpointName: string;
        modelType: "huggingface" | "mistral" | "custom" | "llama" | "claude" | "jumpstart" | undefined;
        region: string;
    } | {
        capabilities: {
            streaming: boolean;
            toolCalling: boolean;
            structuredOutput: boolean;
            batchInference: boolean;
            supportedResponseFormats: string[];
            supportedToolTypes: string[];
            maxBatchSize: number;
        };
    };
}
export default AmazonSageMakerProvider;