trueref-legacy/src/lib/server/embeddings/local.provider.ts

/**
 * LocalEmbeddingProvider — uses @xenova/transformers (optional dependency).
 *
 * @xenova/transformers is NOT installed by default. This provider uses a
 * dynamic import so the module is only required at runtime when the local
 * provider is actually configured. If the package is absent, isAvailable()
 * returns false and embed() throws a clear error.
 */

import { EmbeddingError, type EmbeddingProvider, type EmbeddingVector } from './provider.js';

export class LocalEmbeddingProvider implements EmbeddingProvider {
	readonly name = 'local';
	readonly model = 'Xenova/all-MiniLM-L6-v2';
	readonly dimensions = 384;

	// eslint-disable-next-line @typescript-eslint/no-explicit-any
	private pipeline: ((text: string, options: Record<string, unknown>) => Promise<any>) | null =
		null;

	async embed(texts: string[]): Promise<EmbeddingVector[]> {
		if (!this.pipeline) {
			let transformers: { pipeline: Function };
			try {
				// Dynamic import — only succeeds when @xenova/transformers is installed.
				// eslint-disable-next-line @typescript-eslint/no-explicit-any
				transformers = (await import('@xenova/transformers' as any)) as {
					pipeline: Function;
				};
			} catch {
				throw new EmbeddingError(
					'@xenova/transformers is not installed. Install it to use the local embedding provider.'
				);
			}
			this.pipeline = await transformers.pipeline('feature-extraction', this.model);
		}

		const results: EmbeddingVector[] = [];
		for (const text of texts) {
			const output = await this.pipeline!(text, {
				pooling: 'mean',
				normalize: true
			});
			results.push({
				values: new Float32Array(output.data),
				dimensions: this.dimensions,
				model: this.model
			});
		}
		return results;
	}

	async isAvailable(): Promise<boolean> {
		try {
			await import('@xenova/transformers' as never);
			return true;
		} catch {
			return false;
		}
	}
}