/**
 * Client for the embed-service (BGE-M3 + BGE-Reranker-v2-M3).
 *
 * Self-hosted at EMBED_SERVICE_URL. CPU-only on the VPS.
 */

const EMBED_URL = process.env.EMBED_SERVICE_URL || "http://localhost:8000";

export async function embedQuery(text: string): Promise<number[]> {
  const res = await fetch(`${EMBED_URL}/embed`, {
    method: "POST",
    headers: { "content-type": "application/json" },
    body: JSON.stringify({ texts: [text], normalize: true }),
    // The first embed call after a cold start can take several seconds while
    // BGE-M3 loads into RAM. After that it stabilizes around 150-300ms.
    signal: AbortSignal.timeout(60_000),
  });
  if (!res.ok) throw new Error(`embed-service /embed ${res.status}`);
  const data = (await res.json()) as { embeddings: number[][] };
  return data.embeddings[0];
}

export async function rerank(
  query: string,
  docs: string[],
): Promise<number[]> {
  if (docs.length === 0) return [];
  const res = await fetch(`${EMBED_URL}/rerank`, {
    method: "POST",
    headers: { "content-type": "application/json" },
    body: JSON.stringify({ query, docs, normalize: true }),
    signal: AbortSignal.timeout(60_000),
  });
  if (!res.ok) throw new Error(`embed-service /rerank ${res.status}`);
  const data = (await res.json()) as { scores: number[] };
  return data.scores;
}

/** pgvector accepts the textual `[1.0,2.0,...]` form. */
export function toPgVectorLiteral(vec: number[]): string {
  return "[" + vec.map((v) => v.toFixed(6)).join(",") + "]";
}