@dengxifeng/lancedb 0.26.2

package/dist/embedding/embedding_function.js

@@ -0,0 +1,192 @@
+"use strict";
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.TextEmbeddingFunction = exports.EmbeddingFunction = void 0;
+require("reflect-metadata");
+const arrow_1 = require("../arrow");
+const sanitize_1 = require("../sanitize");
+const registry_1 = require("./registry");
+/**
+ * An embedding function that automatically creates vector representation for a given column.
+ *
+ * It's important subclasses pass the **original** options to the super constructor
+ * and then pass those options to `resolveVariables` to resolve any variables before
+ * using them.
+ *
+ * @example
+ * ```ts
+ * class MyEmbeddingFunction extends EmbeddingFunction {
+ *   constructor(options: {model: string, timeout: number}) {
+ *     super(optionsRaw);
+ *     const options = this.resolveVariables(optionsRaw);
+ *     this.model = options.model;
+ *     this.timeout = options.timeout;
+ *   }
+ * }
+ * ```
+ */
+class EmbeddingFunction {
+    /**
+     * @ignore
+     *  This is only used for associating the options type with the class for type checking
+     */
+    // biome-ignore lint/style/useNamingConvention: we want to keep the name as it is
+    TOptions;
+    #config;
+    /**
+     * Get the original arguments to the constructor, to serialize them so they
+     * can be used to recreate the embedding function later.
+     */
+    // biome-ignore lint/suspicious/noExplicitAny :
+    toJSON() {
+        return JSON.parse(JSON.stringify(this.#config));
+    }
+    constructor() {
+        this.#config = {};
+    }
+    /**
+     * Provide a list of keys in the function options that should be treated as
+     * sensitive. If users pass raw values for these keys, they will be rejected.
+     */
+    getSensitiveKeys() {
+        return [];
+    }
+    /**
+     * Apply variables to the config.
+     */
+    resolveVariables(config) {
+        this.#config = config;
+        const registry = (0, registry_1.getRegistry)();
+        const newConfig = { ...config };
+        for (const [key_, value] of Object.entries(newConfig)) {
+            if (this.getSensitiveKeys().includes(key_) &&
+                !value.startsWith("$var:")) {
+                throw new Error(`The key "${key_}" is sensitive and cannot be set directly. Please use the $var: syntax to set it.`);
+            }
+            // Makes TS happy (https://stackoverflow.com/a/78391854)
+            const key = key_;
+            if (typeof value === "string" && value.startsWith("$var:")) {
+                const [name, defaultValue] = value.slice(5).split(":", 2);
+                const variableValue = registry.getVar(name);
+                if (!variableValue) {
+                    if (defaultValue) {
+                        // biome-ignore lint/suspicious/noExplicitAny:
+                        newConfig[key] = defaultValue;
+                    }
+                    else {
+                        throw new Error(`Variable "${name}" not found`);
+                    }
+                }
+                else {
+                    // biome-ignore lint/suspicious/noExplicitAny:
+                    newConfig[key] = variableValue;
+                }
+            }
+        }
+        return newConfig;
+    }
+    /**
+     * sourceField is used in combination with `LanceSchema` to provide a declarative data model
+     *
+     * @param optionsOrDatatype - The options for the field or the datatype
+     *
+     * @see {@link LanceSchema}
+     */
+    sourceField(optionsOrDatatype) {
+        let datatype = "datatype" in optionsOrDatatype
+            ? optionsOrDatatype.datatype
+            : optionsOrDatatype;
+        if (!datatype) {
+            throw new Error("Datatype is required");
+        }
+        datatype = (0, sanitize_1.sanitizeType)(datatype);
+        const metadata = new Map();
+        metadata.set("source_column_for", this);
+        return [datatype, metadata];
+    }
+    /**
+     * vectorField is used in combination with `LanceSchema` to provide a declarative data model
+     *
+     * @param optionsOrDatatype - The options for the field
+     *
+     * @see {@link LanceSchema}
+     */
+    vectorField(optionsOrDatatype) {
+        let dtype;
+        let vectorType;
+        let dims = this.ndims();
+        // `func.vectorField(new Float32())`
+        if (optionsOrDatatype === undefined) {
+            dtype = new arrow_1.Float32();
+        }
+        else if (!("datatype" in optionsOrDatatype)) {
+            dtype = (0, sanitize_1.sanitizeType)(optionsOrDatatype);
+        }
+        else {
+            // `func.vectorField({
+            //  datatype: new Float32(),
+            //  dims: 10
+            // })`
+            dims = dims ?? optionsOrDatatype?.dims;
+            dtype = (0, sanitize_1.sanitizeType)(optionsOrDatatype?.datatype);
+        }
+        if (dtype !== undefined) {
+            // `func.vectorField(new FixedSizeList(dims, new Field("item", new Float32(), true)))`
+            // or `func.vectorField({datatype: new FixedSizeList(dims, new Field("item", new Float32(), true))})`
+            if ((0, arrow_1.isFixedSizeList)(dtype)) {
+                vectorType = dtype;
+                // `func.vectorField(new Float32())`
+                // or `func.vectorField({datatype: new Float32()})`
+            }
+            else if ((0, arrow_1.isFloat)(dtype)) {
+                // No `ndims` impl and no `{dims: n}` provided;
+                if (dims === undefined) {
+                    throw new Error("ndims is required for vector field");
+                }
+                vectorType = (0, arrow_1.newVectorType)(dims, dtype);
+            }
+            else {
+                throw new Error("Expected FixedSizeList or Float as datatype for vector field");
+            }
+        }
+        else {
+            if (dims === undefined) {
+                throw new Error("ndims is required for vector field");
+            }
+            vectorType = new arrow_1.FixedSizeList(dims, new arrow_1.Field("item", new arrow_1.Float32(), true));
+        }
+        const metadata = new Map();
+        metadata.set("vector_column_for", this);
+        return [vectorType, metadata];
+    }
+    /** The number of dimensions of the embeddings */
+    ndims() {
+        return undefined;
+    }
+    /**
+    Compute the embeddings for a single query
+   */
+    async computeQueryEmbeddings(data) {
+        return this.computeSourceEmbeddings([data]).then((embeddings) => embeddings[0]);
+    }
+}
+exports.EmbeddingFunction = EmbeddingFunction;
+/**
+ * an abstract class for implementing embedding functions that take text as input
+ */
+class TextEmbeddingFunction extends EmbeddingFunction {
+    async computeQueryEmbeddings(data) {
+        return this.generateEmbeddings([data]).then((data) => data[0]);
+    }
+    embeddingDataType() {
+        return new arrow_1.Float32();
+    }
+    sourceField() {
+        return super.sourceField(new arrow_1.Utf8());
+    }
+    computeSourceEmbeddings(data) {
+        return this.generateEmbeddings(data);
+    }
+}
+exports.TextEmbeddingFunction = TextEmbeddingFunction;

package/dist/embedding/index.d.ts

@@ -0,0 +1,27 @@
+import { Schema } from "../arrow";
+import { EmbeddingFunction } from "./embedding_function";
+export { FieldOptions, EmbeddingFunction, TextEmbeddingFunction, FunctionOptions, EmbeddingFunctionConstructor, } from "./embedding_function";
+export * from "./registry";
+/**
+ * Create a schema with embedding functions.
+ *
+ * @param fields
+ * @returns Schema
+ * @example
+ * ```ts
+ * class MyEmbeddingFunction extends EmbeddingFunction {
+ * // ...
+ * }
+ * const func = new MyEmbeddingFunction();
+ * const schema = LanceSchema({
+ *   id: new Int32(),
+ *   text: func.sourceField(new Utf8()),
+ *   vector: func.vectorField(),
+ *   // optional: specify the datatype and/or dimensions
+ *   vector2: func.vectorField({ datatype: new Float32(), dims: 3}),
+ * });
+ *
+ * const table = await db.createTable("my_table", data, { schema });
+ * ```
+ */
+export declare function LanceSchema(fields: Record<string, [object, Map<string, EmbeddingFunction>] | object>): Schema;

package/dist/embedding/index.js

@@ -0,0 +1,101 @@
+"use strict";
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __exportStar = (this && this.__exportStar) || function(m, exports) {
+    for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.TextEmbeddingFunction = exports.EmbeddingFunction = void 0;
+exports.LanceSchema = LanceSchema;
+const arrow_1 = require("../arrow");
+const sanitize_1 = require("../sanitize");
+const registry_1 = require("./registry");
+var embedding_function_1 = require("./embedding_function");
+Object.defineProperty(exports, "EmbeddingFunction", { enumerable: true, get: function () { return embedding_function_1.EmbeddingFunction; } });
+Object.defineProperty(exports, "TextEmbeddingFunction", { enumerable: true, get: function () { return embedding_function_1.TextEmbeddingFunction; } });
+__exportStar(require("./registry"), exports);
+/**
+ * Create a schema with embedding functions.
+ *
+ * @param fields
+ * @returns Schema
+ * @example
+ * ```ts
+ * class MyEmbeddingFunction extends EmbeddingFunction {
+ * // ...
+ * }
+ * const func = new MyEmbeddingFunction();
+ * const schema = LanceSchema({
+ *   id: new Int32(),
+ *   text: func.sourceField(new Utf8()),
+ *   vector: func.vectorField(),
+ *   // optional: specify the datatype and/or dimensions
+ *   vector2: func.vectorField({ datatype: new Float32(), dims: 3}),
+ * });
+ *
+ * const table = await db.createTable("my_table", data, { schema });
+ * ```
+ */
+function LanceSchema(fields) {
+    const arrowFields = [];
+    const embeddingFunctions = new Map();
+    Object.entries(fields).forEach(([key, value]) => {
+        if (Array.isArray(value)) {
+            const [dtype, metadata] = value;
+            arrowFields.push(new arrow_1.Field(key, (0, sanitize_1.sanitizeType)(dtype), true));
+            parseEmbeddingFunctions(embeddingFunctions, key, metadata);
+        }
+        else {
+            arrowFields.push(new arrow_1.Field(key, (0, sanitize_1.sanitizeType)(value), true));
+        }
+    });
+    const registry = (0, registry_1.getRegistry)();
+    const metadata = registry.getTableMetadata(Array.from(embeddingFunctions.values()));
+    const schema = new arrow_1.Schema(arrowFields, metadata);
+    return schema;
+}
+function parseEmbeddingFunctions(embeddingFunctions, key, metadata) {
+    if (metadata.has("source_column_for")) {
+        const embedFunction = metadata.get("source_column_for");
+        const current = embeddingFunctions.get(embedFunction);
+        if (current !== undefined) {
+            embeddingFunctions.set(embedFunction, {
+                ...current,
+                sourceColumn: key,
+            });
+        }
+        else {
+            embeddingFunctions.set(embedFunction, {
+                sourceColumn: key,
+                function: embedFunction,
+            });
+        }
+    }
+    else if (metadata.has("vector_column_for")) {
+        const embedFunction = metadata.get("vector_column_for");
+        const current = embeddingFunctions.get(embedFunction);
+        if (current !== undefined) {
+            embeddingFunctions.set(embedFunction, {
+                ...current,
+                vectorColumn: key,
+            });
+        }
+        else {
+            embeddingFunctions.set(embedFunction, {
+                vectorColumn: key,
+                function: embedFunction,
+            });
+        }
+    }
+}

package/dist/embedding/openai.d.ts

@@ -0,0 +1,16 @@
+import type { EmbeddingCreateParams } from "openai/resources/index";
+import { Float } from "../arrow";
+import { EmbeddingFunction } from "./embedding_function";
+export type OpenAIOptions = {
+    apiKey: string;
+    model: EmbeddingCreateParams["model"];
+};
+export declare class OpenAIEmbeddingFunction extends EmbeddingFunction<string, Partial<OpenAIOptions>> {
+    #private;
+    constructor(optionsRaw?: Partial<OpenAIOptions>);
+    protected getSensitiveKeys(): string[];
+    ndims(): number;
+    embeddingDataType(): Float;
+    computeSourceEmbeddings(data: string[]): Promise<number[][]>;
+    computeQueryEmbeddings(data: string): Promise<number[]>;
+}

package/dist/embedding/openai.js

@@ -0,0 +1,93 @@
+"use strict";
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+var __decorate = (this && this.__decorate) || function (decorators, target, key, desc) {
+    var c = arguments.length, r = c < 3 ? target : desc === null ? desc = Object.getOwnPropertyDescriptor(target, key) : desc, d;
+    if (typeof Reflect === "object" && typeof Reflect.decorate === "function") r = Reflect.decorate(decorators, target, key, desc);
+    else for (var i = decorators.length - 1; i >= 0; i--) if (d = decorators[i]) r = (c < 3 ? d(r) : c > 3 ? d(target, key, r) : d(target, key)) || r;
+    return c > 3 && r && Object.defineProperty(target, key, r), r;
+};
+var __metadata = (this && this.__metadata) || function (k, v) {
+    if (typeof Reflect === "object" && typeof Reflect.metadata === "function") return Reflect.metadata(k, v);
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.OpenAIEmbeddingFunction = void 0;
+const arrow_1 = require("../arrow");
+const embedding_function_1 = require("./embedding_function");
+const registry_1 = require("./registry");
+let OpenAIEmbeddingFunction = class OpenAIEmbeddingFunction extends embedding_function_1.EmbeddingFunction {
+    #openai;
+    #modelName;
+    constructor(optionsRaw = {
+        model: "text-embedding-ada-002",
+    }) {
+        super();
+        const options = this.resolveVariables(optionsRaw);
+        const openAIKey = options?.apiKey ?? process.env.OPENAI_API_KEY;
+        if (!openAIKey) {
+            throw new Error("OpenAI API key is required");
+        }
+        const modelName = options?.model ?? "text-embedding-ada-002";
+        /**
+         * @type {import("openai").default}
+         */
+        // eslint-disable-next-line @typescript-eslint/naming-convention
+        let Openai;
+        try {
+            // eslint-disable-next-line @typescript-eslint/no-var-requires
+            Openai = require("openai");
+        }
+        catch {
+            throw new Error("please install openai@^4.24.1 using npm install openai");
+        }
+        const configuration = {
+            apiKey: openAIKey,
+        };
+        this.#openai = new Openai(configuration);
+        this.#modelName = modelName;
+    }
+    getSensitiveKeys() {
+        return ["apiKey"];
+    }
+    ndims() {
+        switch (this.#modelName) {
+            case "text-embedding-ada-002":
+                return 1536;
+            case "text-embedding-3-large":
+                return 3072;
+            case "text-embedding-3-small":
+                return 1536;
+            default:
+                throw new Error(`Unknown model: ${this.#modelName}`);
+        }
+    }
+    embeddingDataType() {
+        return new arrow_1.Float32();
+    }
+    async computeSourceEmbeddings(data) {
+        const response = await this.#openai.embeddings.create({
+            model: this.#modelName,
+            input: data,
+        });
+        const embeddings = [];
+        for (let i = 0; i < response.data.length; i++) {
+            embeddings.push(response.data[i].embedding);
+        }
+        return embeddings;
+    }
+    async computeQueryEmbeddings(data) {
+        if (typeof data !== "string") {
+            throw new Error("Data must be a string");
+        }
+        const response = await this.#openai.embeddings.create({
+            model: this.#modelName,
+            input: data,
+        });
+        return response.data[0].embedding;
+    }
+};
+exports.OpenAIEmbeddingFunction = OpenAIEmbeddingFunction;
+exports.OpenAIEmbeddingFunction = OpenAIEmbeddingFunction = __decorate([
+    (0, registry_1.register)("openai"),
+    __metadata("design:paramtypes", [Object])
+], OpenAIEmbeddingFunction);

package/dist/embedding/registry.d.ts

@@ -0,0 +1,74 @@
+import { type EmbeddingFunction, type EmbeddingFunctionConstructor } from "./embedding_function";
+import "reflect-metadata";
+export type CreateReturnType<T> = T extends {
+    init: () => Promise<void>;
+} ? Promise<T> : T;
+export interface EmbeddingFunctionCreate<T extends EmbeddingFunction> {
+    create(options?: T["TOptions"]): CreateReturnType<T>;
+}
+/**
+ * This is a singleton class used to register embedding functions
+ * and fetch them by name. It also handles serializing and deserializing.
+ * You can implement your own embedding function by subclassing EmbeddingFunction
+ * or TextEmbeddingFunction and registering it with the registry
+ */
+export declare class EmbeddingFunctionRegistry {
+    #private;
+    /**
+     * Get the number of registered functions
+     */
+    length(): number;
+    /**
+     * Register an embedding function
+     * @throws Error if the function is already registered
+     */
+    register<T extends EmbeddingFunctionConstructor = EmbeddingFunctionConstructor>(this: EmbeddingFunctionRegistry, alias?: string): (ctor: T) => any;
+    get<T extends EmbeddingFunction<unknown>>(name: string): EmbeddingFunctionCreate<T> | undefined;
+    /**
+     * reset the registry to the initial state
+     */
+    reset(this: EmbeddingFunctionRegistry): void;
+    /**
+     * @ignore
+     */
+    parseFunctions(this: EmbeddingFunctionRegistry, metadata: Map<string, string>): Promise<Map<string, EmbeddingFunctionConfig>>;
+    functionToMetadata(conf: EmbeddingFunctionConfig): Record<string, any>;
+    getTableMetadata(functions: EmbeddingFunctionConfig[]): Map<string, string>;
+    /**
+     * Set a variable. These can be accessed in the embedding function
+     * configuration using the syntax `$var:variable_name`. If they are not
+     * set, an error will be thrown letting you know which key is unset. If you
+     * want to supply a default value, you can add an additional part in the
+     * configuration like so: `$var:variable_name:default_value`. Default values
+     * can be used for runtime configurations that are not sensitive, such as
+     * whether to use a GPU for inference.
+     *
+     * The name must not contain colons. The default value can contain colons.
+     *
+     * @param name
+     * @param value
+     */
+    setVar(name: string, value: string): void;
+    /**
+     * Get a variable.
+     * @param name
+     * @returns
+     * @see {@link setVar}
+     */
+    getVar(name: string): string | undefined;
+}
+export declare function register(name?: string): (ctor: EmbeddingFunctionConstructor<EmbeddingFunction<any, import("./embedding_function").FunctionOptions>>) => any;
+/**
+ * Utility function to get the global instance of the registry
+ * @returns `EmbeddingFunctionRegistry` The global instance of the registry
+ * @example
+ * ```ts
+ * const registry = getRegistry();
+ * const openai = registry.get("openai").create();
+ */
+export declare function getRegistry(): EmbeddingFunctionRegistry;
+export interface EmbeddingFunctionConfig {
+    sourceColumn: string;
+    vectorColumn?: string;
+    function: EmbeddingFunction;
+}

package/dist/embedding/registry.js

@@ -0,0 +1,165 @@
+"use strict";
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.EmbeddingFunctionRegistry = void 0;
+exports.register = register;
+exports.getRegistry = getRegistry;
+require("reflect-metadata");
+/**
+ * This is a singleton class used to register embedding functions
+ * and fetch them by name. It also handles serializing and deserializing.
+ * You can implement your own embedding function by subclassing EmbeddingFunction
+ * or TextEmbeddingFunction and registering it with the registry
+ */
+class EmbeddingFunctionRegistry {
+    #functions = new Map();
+    #variables = new Map();
+    /**
+     * Get the number of registered functions
+     */
+    length() {
+        return this.#functions.size;
+    }
+    /**
+     * Register an embedding function
+     * @throws Error if the function is already registered
+     */
+    register(alias) {
+        const self = this;
+        return function (ctor) {
+            if (!alias) {
+                alias = ctor.name;
+            }
+            if (self.#functions.has(alias)) {
+                throw new Error(`Embedding function with alias "${alias}" already exists`);
+            }
+            self.#functions.set(alias, ctor);
+            Reflect.defineMetadata("lancedb::embedding::name", alias, ctor);
+            return ctor;
+        };
+    }
+    /**
+     * Fetch an embedding function by name
+     * @param name The name of the function
+     */
+    get(name) {
+        const factory = this.#functions.get(name);
+        if (!factory) {
+            // biome-ignore lint/suspicious/noExplicitAny: <explanation>
+            return undefined;
+        }
+        // biome-ignore lint/suspicious/noExplicitAny: <explanation>
+        let create;
+        if (factory.prototype.init) {
+            // biome-ignore lint/suspicious/noExplicitAny: <explanation>
+            create = async function (options) {
+                const instance = new factory(options);
+                await instance.init();
+                return instance;
+            };
+        }
+        else {
+            // biome-ignore lint/suspicious/noExplicitAny: <explanation>
+            create = (options) => new factory(options);
+        }
+        return {
+            create,
+        };
+    }
+    /**
+     * reset the registry to the initial state
+     */
+    reset() {
+        this.#functions.clear();
+    }
+    /**
+     * @ignore
+     */
+    async parseFunctions(metadata) {
+        if (!metadata.has("embedding_functions")) {
+            return new Map();
+        }
+        else {
+            const functions = (JSON.parse(metadata.get("embedding_functions")));
+            const items = await Promise.all(functions.map(async (f) => {
+                const fn = this.get(f.name);
+                if (!fn) {
+                    throw new Error(`Function "${f.name}" not found in registry`);
+                }
+                const func = await this.get(f.name).create(f.model);
+                return [
+                    f.name,
+                    {
+                        sourceColumn: f.sourceColumn,
+                        vectorColumn: f.vectorColumn,
+                        function: func,
+                    },
+                ];
+            }));
+            return new Map(items);
+        }
+    }
+    // biome-ignore lint/suspicious/noExplicitAny: <explanation>
+    functionToMetadata(conf) {
+        // biome-ignore lint/suspicious/noExplicitAny: <explanation>
+        const metadata = {};
+        const name = Reflect.getMetadata("lancedb::embedding::name", conf.function.constructor);
+        metadata["sourceColumn"] = conf.sourceColumn;
+        metadata["vectorColumn"] = conf.vectorColumn ?? "vector";
+        metadata["name"] = name ?? conf.function.constructor.name;
+        metadata["model"] = conf.function.toJSON();
+        return metadata;
+    }
+    getTableMetadata(functions) {
+        const metadata = new Map();
+        const jsonData = functions.map((conf) => this.functionToMetadata(conf));
+        metadata.set("embedding_functions", JSON.stringify(jsonData));
+        return metadata;
+    }
+    /**
+     * Set a variable. These can be accessed in the embedding function
+     * configuration using the syntax `$var:variable_name`. If they are not
+     * set, an error will be thrown letting you know which key is unset. If you
+     * want to supply a default value, you can add an additional part in the
+     * configuration like so: `$var:variable_name:default_value`. Default values
+     * can be used for runtime configurations that are not sensitive, such as
+     * whether to use a GPU for inference.
+     *
+     * The name must not contain colons. The default value can contain colons.
+     *
+     * @param name
+     * @param value
+     */
+    setVar(name, value) {
+        if (name.includes(":")) {
+            throw new Error("Variable names cannot contain colons");
+        }
+        this.#variables.set(name, value);
+    }
+    /**
+     * Get a variable.
+     * @param name
+     * @returns
+     * @see {@link setVar}
+     */
+    getVar(name) {
+        return this.#variables.get(name);
+    }
+}
+exports.EmbeddingFunctionRegistry = EmbeddingFunctionRegistry;
+const _REGISTRY = new EmbeddingFunctionRegistry();
+function register(name) {
+    return _REGISTRY.register(name);
+}
+/**
+ * Utility function to get the global instance of the registry
+ * @returns `EmbeddingFunctionRegistry` The global instance of the registry
+ * @example
+ * ```ts
+ * const registry = getRegistry();
+ * const openai = registry.get("openai").create();
+ */
+function getRegistry() {
+    return _REGISTRY;
+}