fix(node): defer built-in embedding registration

This commit is contained in:
Gatefixer
2026-08-08 12:21:46 +00:00
parent 0e611c9f35
commit 4dd31b4207
5 changed files with 115 additions and 20 deletions
+39 -5
View File
@@ -1,9 +1,14 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
import { execFileSync } from "node:child_process";
import { resolve } from "node:path";
import type { OpenAIEmbeddingFunction } from "../lancedb/embedding/openai";
import type { EmbeddingFunctionRegistry } from "../lancedb/embedding/registry";
type EmbeddingModule = typeof import("../lancedb/embedding");
type OpenAIModule = typeof import("../lancedb/embedding/openai");
type RegistryModule = typeof import("../lancedb/embedding/registry");
describe("embedding function registry", () => {
@@ -16,20 +21,32 @@ describe("embedding function registry", () => {
registries.length = 0;
});
it("registers built-in providers through the public embedding API", () => {
it("defers built-in providers until the public registry API is used", () => {
jest.isolateModules(() => {
const { getRegistry } =
require("../lancedb/embedding") as EmbeddingModule;
const registry = getRegistry();
const embedding = require("../lancedb/embedding") as EmbeddingModule;
const { getRegistry: getInternalRegistry } =
require("../lancedb/embedding/registry") as RegistryModule;
const registry = getInternalRegistry();
registries.push(registry);
expect(registry.length()).toBe(0);
expect(embedding.getRegistry()).toBe(registry);
expect(registry.get("openai")).toBeDefined();
expect(registry.get("huggingface")).toBeDefined();
});
});
it("preserves automatic FTS search in a fresh process", () => {
execFileSync(
process.execPath,
[resolve(__dirname, "fixtures", "auto_fts_search.cjs")],
{ stdio: "pipe" },
);
});
it("shares registrations across duplicated provider module graphs", () => {
let registeringRegistry: EmbeddingFunctionRegistry | undefined;
let latestOpenAIConstructor: typeof OpenAIEmbeddingFunction | undefined;
jest.isolateModules(() => {
require("../lancedb/embedding/openai");
@@ -42,13 +59,30 @@ describe("embedding function registry", () => {
expect(() => {
jest.isolateModules(() => {
require("../lancedb/embedding/openai");
const { OpenAIEmbeddingFunction } =
require("../lancedb/embedding/openai") as OpenAIModule;
latestOpenAIConstructor = OpenAIEmbeddingFunction;
const { getRegistry } =
require("../lancedb/embedding/registry") as RegistryModule;
registries.push(getRegistry());
});
}).not.toThrow();
const previousApiKey = process.env.OPENAI_API_KEY;
process.env.OPENAI_API_KEY = "test";
try {
const latestOpenAI = registeringRegistry!
.get<OpenAIEmbeddingFunction>("openai")!
.create();
expect(latestOpenAI).toBeInstanceOf(latestOpenAIConstructor!);
} finally {
if (previousApiKey === undefined) {
delete process.env.OPENAI_API_KEY;
} else {
process.env.OPENAI_API_KEY = previousApiKey;
}
}
jest.isolateModules(() => {
const { getRegistry } =
require("../lancedb/embedding") as EmbeddingModule;
@@ -0,0 +1,31 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
const assert = require("node:assert/strict");
const tmp = require("tmp");
const { connect, embedding, Index } = require("../../dist");
const { getRegistry } = require("../../dist/embedding/registry");
async function main() {
assert.equal(typeof embedding.getRegistry, "function");
assert.equal(getRegistry().length(), 0);
const dir = tmp.dirSync({ unsafeCleanup: true });
let db;
try {
db = await connect(dir.name);
const table = await db.createTable("docs", [{ text: "hello world" }]);
await table.createIndex("text", { config: Index.fts() });
const rows = await table.search("hello").toArray();
assert.equal(rows[0].text, "hello world");
} finally {
db?.close();
dir.removeCallback();
}
}
main().catch((error) => {
console.error(error);
process.exitCode = 1;
});