@juspay/neurolink/dist/providers/nvidiaNim/client.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 { AIProviderName } from "../../constants/enums.js";
import type { NeurolinkCredentials, OpenAICompatBuildBodyArgs, OpenAICompatChatRequest } from "../../types/index.js";
import { OpenAIChatCompletionsProvider } from "../openaiChatCompletionsBase.js";
declare const isNimFieldRejection: (body: string, field: string) => boolean;
/**
 * Strip an offending field from a JSON request body and return the rebuilt
 * stringified body. Returns `null` if the body isn't JSON-parseable or the
 * field isn't present (signal: nothing to retry).
 */
declare const stripFieldFromJsonBody: (body: string, field: "reasoning_budget" | "chat_template") => string | null;
/**
 * NVIDIA NIM Provider — native HTTP+SSE, no AI SDK.
 *
 * Wraps NVIDIA's hosted (or self-hosted) inference endpoints.
 * Passes NIM-specific extras (top_k, min_p, repetition_penalty, min_tokens,
 * chat_template, chat_template_kwargs.reasoning_budget) to the wire via the
 * `extraBody` channel of adjustBuildBodyOptions, and retries once without
 * `chat_template`/`reasoning_budget` when a model server rejects them with a
 * 400 (adjustBodyAfter400 — applies on both generate and stream paths).
 * reasoning_content is surfaced automatically by the native base client
 * (streamed as `{ content: "", reasoning }` chunks; `result.reasoning` on
 * the non-streaming path); all other behavior is preserved.
 *
 * @see https://docs.api.nvidia.com/nim/reference/
 */
export declare class NvidiaNimProvider extends OpenAIChatCompletionsProvider {
    constructor(modelName?: string, sdk?: unknown, _region?: string, credentials?: NeurolinkCredentials["nvidiaNim"]);
    protected getProviderName(): AIProviderName;
    protected getDefaultModel(): string;
    /**
     * Inject NIM-specific body fields (top_k, min_p, repetition_penalty,
     * min_tokens, chat_template, chat_template_kwargs) into the wire body.
     *
     * The base passes the full StreamOptions as `opts` at runtime (typed
     * narrowly as OpenAICompatBuildBodyArgs["options"] for standard fields).
     * We access thinkingLevel via an indexed-access cast since the runtime
     * value is the full StreamOptions object.
     */
    protected adjustBuildBodyOptions(_modelId: string, opts: OpenAICompatBuildBodyArgs["options"]): OpenAICompatBuildBodyArgs["options"] & Record<string, unknown>;
    /**
     * One-shot 400 retry (base hook): some NIM model servers reject
     * `chat_template` or `chat_template_kwargs.reasoning_budget` with a 400
     * naming the field. Strip the rejected field(s) and let the base retry
     * once, restoring the pre-migration fetch-level behavior. Returns
     * undefined for unrelated 400s so they propagate unchanged.
     */
    protected adjustBodyAfter400(body: OpenAICompatChatRequest, error: Error & {
        statusCode?: number;
        responseBody?: string;
    }): OpenAICompatChatRequest | undefined;
    protected formatProviderError(error: unknown): Error;
    validateConfiguration(): Promise<boolean>;
    getConfiguration(): {
        provider: AIProviderName;
        model: string;
        defaultModel: string;
        baseURL: string;
    };
}
export { isNimFieldRejection, stripFieldFromJsonBody };