/**
 * lm/text_embedder.ts — text → vector, on the CPU, from an `EvermindLM`.
 *
 * `EvermindLM.embed()` turns TOKENS into a `dModel` vector. Every consumer that
 * wants SEMANTIC RECALL wants it over TEXT, and needs the vector to be stable
 * across processes, so it also needs (a) the tokenizer that produced those ids
 * and (b) a way to tell whether a cached vector came from this exact model. This
 * class is that pairing, in one place, so no consumer re-derives it.
 *
 * It deliberately satisfies the SAME structural shape the memory runtime's
 * `embed(text)` seam expects (`MemoryStore.recallRanked(query, k, runtime)`
 * accepts anything with an async `embed(text): Float32Array`), so a headless host
 * can hand one of these straight to the memory layer and get embedding-ranked
 * recall with NO GPU — the CPU LM is the whole dependency.
 */
import type { EvermindLM, TextCodec } from "./evermind_lm.js";
/** The minimal text-embedder seam the memory/recall layers consume. */
export interface TextEmbedder {
    /** Embed `text` as an L2-normalised vector of length {@link dimensions}. */
    embed(text: string): Promise<Float32Array>;
    /** Vector width (the model's `dModel`). */
    readonly dimensions: number;
    /**
     * Identity of the model+tokenizer that produces these vectors. Vectors are only
     * comparable within one fingerprint, so a persistent cache MUST discard entries
     * stamped with a different one.
     */
    readonly fingerprint: string;
}
/** A tokenizer this embedder can encode through (the engine's `BPETokenizer` fits). */
export type EmbedderCodec = Pick<TextCodec, "encode">;
/**
 * Pairs an `EvermindLM` with the tokenizer whose ids it was trained on.
 *
 * Pure compute and stateless: caching belongs to whoever owns a lifetime (the
 * memory store's in-process LRU, or a host's on-disk vector cache), not here.
 */
export declare class EvermindTextEmbedder implements TextEmbedder {
    private readonly model;
    private readonly codec;
    readonly dimensions: number;
    readonly fingerprint: string;
    constructor(model: EvermindLM, codec: EmbedderCodec, 
    /** Override the derived fingerprint (e.g. with a published model version). */
    fingerprint?: string);
    /**
     * Embed `text`. Async only to match the seam — the work is synchronous CPU, so
     * a caller that wants the vector without a microtask can use
     * {@link embedSync}.
     */
    embed(text: string): Promise<Float32Array>;
    /** The synchronous form — encode with the codec, then run the CPU LM. */
    embedSync(text: string): Float32Array;
}
//# sourceMappingURL=text_embedder.d.ts.map