socraticode/dist/services/provider-litellm.d.ts

SocratiCode — MCP server for local codebase indexing, semantic search, and code dependency graphs. All private, all local via Docker.

/**
 * LiteLLM embedding provider.
 *
 * LiteLLM Proxy Server (https://docs.litellm.ai/docs/simple_proxy) exposes an
 * OpenAI-compatible /v1/embeddings endpoint that fans out to 100+ underlying
 * model providers (OpenAI, Anthropic, Cohere, Voyage, HuggingFace, Bedrock,
 * Vertex AI, Ollama, ...). Model aliases are defined in the proxy's config.yaml,
 * so from this client's perspective LiteLLM looks like an OpenAI server speaking
 * arbitrary model names.
 *
 * This provider is intentionally separate from `provider-openai.ts` and
 * `provider-lmstudio.ts` because:
 *   - LiteLLM ALWAYS requires an API key (virtual or master), unlike LM Studio.
 *   - Default port is 4000 and /v1/models lists proxy-registered aliases, not
 *     loaded local models.
 *   - Whether the `dimensions` parameter is honoured depends on the underlying
 *     provider chosen by the proxy alias, so we make it opt-in via
 *     LITELLM_SEND_DIMENSIONS instead of hardcoding it like provider-openai
 *     does for text-embedding-3-*.
 *   - Health check messaging points at proxy-side issues (master key, alias
 *     missing in config.yaml) rather than at SaaS quotas or local model loads.
 *
 * Required env when using this provider:
 *   EMBEDDING_PROVIDER=litellm
 *   LITELLM_API_KEY=<virtual-or-master-key>
 *   EMBEDDING_MODEL=<alias-from-litellm-config-yaml>
 *   EMBEDDING_DIMENSIONS=<dim-of-underlying-model>
 *
 * Optional env:
 *   LITELLM_URL=http://localhost:4000/v1   (default; must include /v1 suffix)
 *   LITELLM_SEND_DIMENSIONS=true           (opt-in; forwards `dimensions` to the
 *                                           proxy for Matryoshka-aware models like
 *                                           text-embedding-3-* or voyage-3 routed
 *                                           via LiteLLM. Default false because
 *                                           non-Matryoshka backends raise on it.)
 *   EMBEDDING_CONTEXT_LENGTH=<tokens>      (defaults to 2048 if model unknown)
 */
import type { EmbeddingHealthStatus, EmbeddingProvider, EmbeddingReadinessResult } from "./embedding-types.js";
/** Reset client (for testing or LITELLM_URL / LITELLM_API_KEY hot-swap). */
export declare function resetLiteLLMClient(): void;
export declare class LiteLLMEmbeddingProvider implements EmbeddingProvider {
    readonly name = "litellm";
    ensureReady(): Promise<EmbeddingReadinessResult>;
    embed(texts: string[]): Promise<number[][]>;
    embedSingle(text: string): Promise<number[]>;
    healthCheck(): Promise<EmbeddingHealthStatus>;
    private _embedBatch;
}
//# sourceMappingURL=provider-litellm.d.ts.map