mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-26 17:12:27 +03:00
1255b5869b
The memory Engine tab quick-select built its model list only from a keyword heuristic over the chat catalog plus OpenRouter live discovery, so configured providers whose embedding models are not in that catalog (e.g. Cloudflare Workers AI cf/@cf/baai/bge-m3) never appeared, and requests for them failed with 'Unknown embedding provider'. - add cloudflare-ai to EMBEDDING_PROVIDERS with a requiresAccountId URL template resolved per-request via buildEmbeddingProviderUrl() (mirrors CloudflareAIExecutor on the chat side) plus the cf provider alias - merge curated registry models into the quick-select catalog and add a generic fallback listing: any configured OpenAI-compatible chat provider without a curated entry appears with free-text model input - same treatment for rerank: listRerankProviders + generic Cohere- compatible fallback, new /api/memory/rerank-providers endpoint, selectors fall back to free-text when no static models exist - runtime: embeddings service/handler and rerank route/handler resolve derived providers instead of rejecting unlisted ones
78 lines
3.0 KiB
TypeScript
78 lines
3.0 KiB
TypeScript
import { describe, it } from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import {
|
|
getEmbeddingProvider,
|
|
parseEmbeddingModel,
|
|
deriveEmbeddingProviderForChatProvider,
|
|
type EmbeddingProvider,
|
|
} from "@omniroute/open-sse/config/embeddingRegistry.ts";
|
|
|
|
describe("deriveEmbeddingProviderForChatProvider (global OpenAI-compatible fallback)", () => {
|
|
it("derives an embeddings endpoint from a chat-completions base URL", () => {
|
|
const derived = deriveEmbeddingProviderForChatProvider("groq", {
|
|
id: "groq",
|
|
baseUrl: "https://api.groq.com/openai/v1/chat/completions",
|
|
});
|
|
assert.ok(derived, "groq should derive an embedding provider");
|
|
assert.equal(derived.baseUrl, "https://api.groq.com/openai/v1/embeddings");
|
|
assert.equal(derived.authType, "apikey");
|
|
assert.equal(derived.authHeader, "bearer");
|
|
assert.deepEqual(derived.models, []);
|
|
});
|
|
|
|
it("returns null for providers without a usable static base URL", () => {
|
|
assert.equal(deriveEmbeddingProviderForChatProvider("x", null), null);
|
|
assert.equal(
|
|
deriveEmbeddingProviderForChatProvider("dynamic-provider", {
|
|
id: "dynamic-provider",
|
|
baseUrl: "https://host.example/accounts",
|
|
}),
|
|
null,
|
|
"non chat/completions bases must not derive a bogus /embeddings endpoint"
|
|
);
|
|
});
|
|
|
|
it("is a fallback only: curated registry entries stay authoritative", () => {
|
|
const derived = deriveEmbeddingProviderForChatProvider("deepinfra", {
|
|
id: "deepinfra",
|
|
baseUrl: "https://api.deepinfra.com/v1/openai/chat/completions",
|
|
});
|
|
// deepinfra IS in EMBEDDING_PROVIDERS — the helper still derives mechanically;
|
|
// callers must check getEmbeddingProvider() first.
|
|
assert.ok(derived);
|
|
assert.ok(getEmbeddingProvider("deepinfra"), "curated entry remains authoritative");
|
|
});
|
|
|
|
it("covers known embedding-capable chat providers with derivable endpoints", () => {
|
|
for (const id of ["mistral", "together", "upstage", "fireworks", "nvidia"]) {
|
|
const derived = deriveEmbeddingProviderForChatProvider(id, {
|
|
id,
|
|
baseUrl: `https://${id}.example.com/v1/chat/completions`,
|
|
});
|
|
assert.ok(derived, `${id} should derive`);
|
|
assert.equal(derived?.baseUrl, `https://${id}.example.com/v1/embeddings`);
|
|
}
|
|
});
|
|
});
|
|
|
|
describe("parseEmbeddingModel precedence (provider_node vs registry)", () => {
|
|
it("a configured provider_node prefix wins over alias resolution", () => {
|
|
const dynamic: EmbeddingProvider[] = [
|
|
{
|
|
id: "jina-ai",
|
|
baseUrl: "http://127.0.0.1:9/embeddings",
|
|
authType: "none",
|
|
authHeader: "none",
|
|
models: [],
|
|
},
|
|
];
|
|
const parsed = parseEmbeddingModel("jina-ai/my-local-model", dynamic);
|
|
assert.deepEqual(parsed, { provider: "jina-ai", model: "my-local-model" });
|
|
});
|
|
|
|
it("unknown prefixes fall through to the generic provider segment", () => {
|
|
const parsed = parseEmbeddingModel("totally-unknown/model-id");
|
|
assert.deepEqual(parsed, { provider: "totally-unknown", model: "model-id" });
|
|
});
|
|
});
|