Function loadEmbeddingConfig

src/services/embedding-config.ts:144–291

()

 * Called once on first access; cached thereafter.
 */
export function loadEmbeddingConfig(): EmbeddingConfig {
  if (_config) return _config;

  // ── Provider ────────────────────────────────────────────────────────
  const rawProvider = process.env.EMBEDDING_PROVIDER || "ollama";
  if (
    rawProvider !== "ollama" &&
    rawProvider !== "openai" &&
    rawProvider !== "google" &&
    rawProvider !== "lmstudio" &&
    rawProvider !== "litellm"
  ) {
    throw new Error(
      `Invalid EMBEDDING_PROVIDER: "${rawProvider}". Must be "ollama", "openai", "google", "lmstudio", or "litellm".`,
    );
  }
  const embeddingProvider: EmbeddingProvider = rawProvider;
  const providerDefaults = PROVIDER_DEFAULTS[embeddingProvider];

  // LM Studio has no sensible defaults — model and dimensions vary per loaded model.
  // Fail fast with an actionable message rather than silently sending empty values.
  if (embeddingProvider === "lmstudio") {
    if (!process.env.EMBEDDING_MODEL) {
      throw new Error(
        "EMBEDDING_MODEL is required when EMBEDDING_PROVIDER=lmstudio. " +
        "LM Studio has no built-in default — set it to the model identifier shown in " +
        "LM Studio's Local Server tab (e.g. EMBEDDING_MODEL=nomic-embed-text-v1.5).",
      );
    }
    if (!process.env.EMBEDDING_DIMENSIONS) {
      throw new Error(
        "EMBEDDING_DIMENSIONS is required when EMBEDDING_PROVIDER=lmstudio. " +
        "Different LM Studio models have different output dimensions — check the model card " +
        "and set EMBEDDING_DIMENSIONS accordingly (e.g. 768 for nomic-embed-text-v1.5, " +
        "1024 for bge-large-en-v1.5, 4096 for qwen3-embedding-8b).",
      );
    }
  }

  // LiteLLM proxy aliases are user-defined in config.yaml — there is no canonical
  // default model name and the underlying dimension depends on which provider the
  // alias resolves to. Authentication is also mandatory (the proxy enforces it
  // even for read-only /v1/models). Fail fast on each missing piece so the
  // operator gets a single, specific error rather than a generic 401 / 404 from
  // the proxy at first embed().
  if (embeddingProvider === "litellm") {
    if (!process.env.LITELLM_API_KEY) {
      throw new Error(
        "LITELLM_API_KEY is required when EMBEDDING_PROVIDER=litellm. " +
        "Set it to the proxy's master key (general_settings.master_key in config.yaml) " +
        "or to a virtual key issued via LiteLLM's /key/generate endpoint.",
      );
    }
    if (!process.env.EMBEDDING_MODEL) {
      throw new Error(
        "EMBEDDING_MODEL is required when EMBEDDING_PROVIDER=litellm. " +
        "Set it to a model_name from your LiteLLM config.yaml (e.g. EMBEDDING_MODEL=text-embedding-3-small " +
        "if your proxy aliases that name; LiteLLM rewrites the call to whichever litellm_params.model " +