🧵 refactor: Migrate Endpoint Initialization to TypeScript (#10794)

* refactor: move endpoint initialization methods to typescript * refactor: move agent init to packages/api - Introduced `initialize.ts` for agent initialization, including file processing and tool loading. - Updated `resources.ts` to allow optional appConfig parameter. - Enhanced endpoint configuration handling in various initialization files to support model parameters. - Added new artifacts and prompts for React component generation. - Refactored existing code to improve type safety and maintainability. * refactor: streamline endpoint initialization and enhance type safety - Updated initialization functions across various endpoints to use a consistent request structure, replacing `unknown` types with `ServerResponse`. - Simplified request handling by directly extracting keys from the request body. - Improved type safety by ensuring user IDs are safely accessed with optional chaining. - Removed unnecessary parameters and streamlined model options handling for better clarity and maintainability. * refactor: moved ModelService and extractBaseURL to packages/api - Added comprehensive tests for the models fetching functionality, covering scenarios for OpenAI, Anthropic, Google, and Ollama models. - Updated existing endpoint index to include the new models module. - Enhanced utility functions for URL extraction and model data processing. - Improved type safety and error handling across the models fetching logic. * refactor: consolidate utility functions and remove unused files - Merged `deriveBaseURL` and `extractBaseURL` into the `@librechat/api` module for better organization. - Removed redundant utility files and their associated tests to streamline the codebase. - Updated imports across various client files to utilize the new consolidated functions. - Enhanced overall maintainability by reducing the number of utility modules. * refactor: replace ModelService references with direct imports from @librechat/api and remove ModelService file * refactor: move encrypt/decrypt methods and key db methods to data-schemas, use `getProviderConfig` from `@librechat/api` * chore: remove unused 'res' from options in AgentClient * refactor: file model imports and methods - Updated imports in various controllers and services to use the unified file model from '~/models' instead of '~/models/File'. - Consolidated file-related methods into a new file methods module in the data-schemas package. - Added comprehensive tests for file methods including creation, retrieval, updating, and deletion. - Enhanced the initializeAgent function to accept dependency injection for file-related methods. - Improved error handling and logging in file methods. * refactor: streamline database method references in agent initialization * refactor: enhance file method tests and update type references to IMongoFile * refactor: consolidate database method imports in agent client and initialization * chore: remove redundant import of initializeAgent from @librechat/api * refactor: move checkUserKeyExpiry utility to @librechat/api and update references across endpoints * refactor: move updateUserPlugins logic to user.ts and simplify UserController * refactor: update imports for user key management and remove UserService * refactor: remove unused Anthropics and Bedrock endpoint files and clean up imports * refactor: consolidate and update encryption imports across various files to use @librechat/data-schemas * chore: update file model mock to use unified import from '~/models' * chore: import order * refactor: remove migrated to TS agent.js file and its associated logic from the endpoints * chore: add reusable function to extract imports from source code in unused-packages workflow * chore: enhance unused-packages workflow to include @librechat/api dependencies and improve dependency extraction * chore: improve dependency extraction in unused-packages workflow with enhanced error handling and debugging output * chore: add detailed debugging output to unused-packages workflow for better visibility into unused dependencies and exclusion lists * chore: refine subpath handling in unused-packages workflow to correctly process scoped and non-scoped package imports * chore: clean up unused debug output in unused-packages workflow and reorganize type imports in initialize.ts
2025-12-18 17:30:16 +01:00 · 2025-12-03 17:21:41 -05:00 · 2025-12-03 17:21:41 -05:00 · b478560c81
commit b478560c81
parent f2ba1696bc
103 changed files with 4135 additions and 2647 deletions
--- a/packages/api/src/endpoints/models.ts
+++ b/packages/api/src/endpoints/models.ts
@ -0,0 +1,383 @@
+import axios from 'axios';
+import { logger } from '@librechat/data-schemas';
+import { HttpsProxyAgent } from 'https-proxy-agent';
+import { CacheKeys, KnownEndpoints, EModelEndpoint, defaultModels } from 'librechat-data-provider';
+import type { IUser } from '@librechat/data-schemas';
+import {
+  processModelData,
+  extractBaseURL,
+  isUserProvided,
+  resolveHeaders,
+  deriveBaseURL,
+  logAxiosError,
+  inputSchema,
+} from '~/utils';
+import { standardCache } from '~/cache';
+
+export interface FetchModelsParams {
+  /** User ID for API requests */
+  user?: string;
+  /** API key for authentication */
+  apiKey: string;
+  /** Base URL for the API */
+  baseURL?: string;
+  /** Endpoint name (defaults to 'openAI') */
+  name?: string;
+  /** Whether directEndpoint was configured */
+  direct?: boolean;
+  /** Whether to fetch from Azure */
+  azure?: boolean;
+  /** Whether to send user ID as query parameter */
+  userIdQuery?: boolean;
+  /** Whether to create token configuration from API response */
+  createTokenConfig?: boolean;
+  /** Cache key for token configuration (uses name if omitted) */
+  tokenKey?: string;
+  /** Optional headers for the request */
+  headers?: Record<string, string> | null;
+  /** Optional user object for header resolution */
+  userObject?: Partial<IUser>;
+}
+
+/**
+ * Fetches Ollama models from the specified base API path.
+ * @param baseURL - The Ollama server URL
+ * @param options - Optional configuration
+ * @returns Promise resolving to array of model names
+ */
+async function fetchOllamaModels(
+  baseURL: string,
+  options: { headers?: Record<string, string> | null; user?: Partial<IUser> } = {},
+): Promise<string[]> {
+  if (!baseURL) {
+    return [];
+  }
+
+  const ollamaEndpoint = deriveBaseURL(baseURL);
+
+  const resolvedHeaders = resolveHeaders({
+    headers: options.headers ?? undefined,
+    user: options.user,
+  });
+
+  const response = await axios.get<{ models: Array<{ name: string }> }>(
+    `${ollamaEndpoint}/api/tags`,
+    {
+      headers: resolvedHeaders,
+      timeout: 5000,
+    },
+  );
+
+  return response.data.models.map((tag) => tag.name);
+}
+
+/**
+ * Splits a string by commas and trims each resulting value.
+ * @param input - The input string to split.
+ * @returns An array of trimmed values.
+ */
+export function splitAndTrim(input: string | null | undefined): string[] {
+  if (!input || typeof input !== 'string') {
+    return [];
+  }
+  return input
+    .split(',')
+    .map((item) => item.trim())
+    .filter(Boolean);
+}
+
+/**
+ * Fetches models from the specified base API path or Azure, based on the provided configuration.
+ *
+ * @param params - The parameters for fetching the models.
+ * @returns A promise that resolves to an array of model identifiers.
+ */
+export async function fetchModels({
+  user,
+  apiKey,
+  baseURL: _baseURL,
+  name = EModelEndpoint.openAI,
+  direct = false,
+  azure = false,
+  userIdQuery = false,
+  createTokenConfig = true,
+  tokenKey,
+  headers,
+  userObject,
+}: FetchModelsParams): Promise<string[]> {
+  let models: string[] = [];
+  const baseURL = direct ? extractBaseURL(_baseURL ?? '') : _baseURL;
+
+  if (!baseURL && !azure) {
+    return models;
+  }
+
+  if (!apiKey) {
+    return models;
+  }
+
+  if (name && name.toLowerCase().startsWith(KnownEndpoints.ollama)) {
+    try {
+      return await fetchOllamaModels(baseURL ?? '', { headers, user: userObject });
+    } catch (ollamaError) {
+      const logMessage =
+        'Failed to fetch models from Ollama API. Attempting to fetch via OpenAI-compatible endpoint.';
+      logAxiosError({ message: logMessage, error: ollamaError as Error });
+    }
+  }
+
+  try {
+    const options: {
+      headers: Record<string, string>;
+      timeout: number;
+      httpsAgent?: HttpsProxyAgent;
+    } = {
+      headers: {
+        ...(headers ?? {}),
+      },
+      timeout: 5000,
+    };
+
+    if (name === EModelEndpoint.anthropic) {
+      options.headers = {
+        'x-api-key': apiKey,
+        'anthropic-version': process.env.ANTHROPIC_VERSION || '2023-06-01',
+      };
+    } else {
+      options.headers.Authorization = `Bearer ${apiKey}`;
+    }
+
+    if (process.env.PROXY) {
+      options.httpsAgent = new HttpsProxyAgent(process.env.PROXY);
+    }
+
+    if (process.env.OPENAI_ORGANIZATION && baseURL?.includes('openai')) {
+      options.headers['OpenAI-Organization'] = process.env.OPENAI_ORGANIZATION;
+    }
+
+    const url = new URL(`${(baseURL ?? '').replace(/\/+$/, '')}${azure ? '' : '/models'}`);
+    if (user && userIdQuery) {
+      url.searchParams.append('user', user);
+    }
+    const res = await axios.get(url.toString(), options);
+
+    const input = res.data;
+
+    const validationResult = inputSchema.safeParse(input);
+    if (validationResult.success && createTokenConfig) {
+      const endpointTokenConfig = processModelData(input);
+      const cache = standardCache(CacheKeys.TOKEN_CONFIG);
+      await cache.set(tokenKey ?? name, endpointTokenConfig);
+    }
+    models = input.data.map((item: { id: string }) => item.id);
+  } catch (error) {
+    const logMessage = `Failed to fetch models from ${azure ? 'Azure ' : ''}${name} API`;
+    logAxiosError({ message: logMessage, error: error as Error });
+  }
+
+  return models;
+}
+
+/** Options for fetching OpenAI models */
+export interface GetOpenAIModelsOptions {
+  /** User ID for API requests */
+  user?: string;
+  /** Whether to fetch from Azure */
+  azure?: boolean;
+  /** Whether to fetch models for the Assistants endpoint */
+  assistants?: boolean;
+  /** OpenAI API key (if not using environment variable) */
+  openAIApiKey?: string;
+  /** Whether user provides their own API key */
+  userProvidedOpenAI?: boolean;
+}
+
+/**
+ * Fetches models from OpenAI or Azure based on the provided options.
+ * @param opts - Options for fetching models
+ * @param _models - Fallback models array
+ * @returns Promise resolving to array of model IDs
+ */
+export async function fetchOpenAIModels(
+  opts: GetOpenAIModelsOptions,
+  _models: string[] = [],
+): Promise<string[]> {
+  let models = _models.slice() ?? [];
+  const apiKey = opts.openAIApiKey ?? process.env.OPENAI_API_KEY;
+  const openaiBaseURL = 'https://api.openai.com/v1';
+  let baseURL = openaiBaseURL;
+  let reverseProxyUrl = process.env.OPENAI_REVERSE_PROXY;
+
+  if (opts.assistants && process.env.ASSISTANTS_BASE_URL) {
+    reverseProxyUrl = process.env.ASSISTANTS_BASE_URL;
+  } else if (opts.azure) {
+    return models;
+  }
+
+  if (reverseProxyUrl) {
+    baseURL = extractBaseURL(reverseProxyUrl) ?? openaiBaseURL;
+  }
+
+  const modelsCache = standardCache(CacheKeys.MODEL_QUERIES);
+
+  const cachedModels = await modelsCache.get(baseURL);
+  if (cachedModels) {
+    return cachedModels as string[];
+  }
+
+  if (baseURL || opts.azure) {
+    models = await fetchModels({
+      apiKey: apiKey ?? '',
+      baseURL,
+      azure: opts.azure,
+      user: opts.user,
+      name: EModelEndpoint.openAI,
+    });
+  }
+
+  if (models.length === 0) {
+    return _models;
+  }
+
+  if (baseURL === openaiBaseURL) {
+    const regex = /(text-davinci-003|gpt-|o\d+)/;
+    const excludeRegex = /audio|realtime/;
+    models = models.filter((model) => regex.test(model) && !excludeRegex.test(model));
+    const instructModels = models.filter((model) => model.includes('instruct'));
+    const otherModels = models.filter((model) => !model.includes('instruct'));
+    models = otherModels.concat(instructModels);
+  }
+
+  await modelsCache.set(baseURL, models);
+  return models;
+}
+
+/**
+ * Loads the default models for OpenAI or Azure.
+ * @param opts - Options for getting models
+ * @returns Promise resolving to array of model IDs
+ */
+export async function getOpenAIModels(opts: GetOpenAIModelsOptions = {}): Promise<string[]> {
+  let models = defaultModels[EModelEndpoint.openAI];
+
+  if (opts.assistants) {
+    models = defaultModels[EModelEndpoint.assistants];
+  } else if (opts.azure) {
+    models = defaultModels[EModelEndpoint.azureAssistants];
+  }
+
+  let key: string;
+  if (opts.assistants) {
+    key = 'ASSISTANTS_MODELS';
+  } else if (opts.azure) {
+    key = 'AZURE_OPENAI_MODELS';
+  } else {
+    key = 'OPENAI_MODELS';
+  }
+
+  if (process.env[key]) {
+    return splitAndTrim(process.env[key]);
+  }
+
+  if (opts.userProvidedOpenAI) {
+    return models;
+  }
+
+  return await fetchOpenAIModels(opts, models);
+}
+
+/**
+ * Fetches models from the Anthropic API.
+ * @param opts - Options for fetching models
+ * @param _models - Fallback models array
+ * @returns Promise resolving to array of model IDs
+ */
+export async function fetchAnthropicModels(
+  opts: { user?: string } = {},
+  _models: string[] = [],
+): Promise<string[]> {
+  let models = _models.slice() ?? [];
+  const apiKey = process.env.ANTHROPIC_API_KEY;
+  const anthropicBaseURL = 'https://api.anthropic.com/v1';
+  let baseURL = anthropicBaseURL;
+  const reverseProxyUrl = process.env.ANTHROPIC_REVERSE_PROXY;
+
+  if (reverseProxyUrl) {
+    baseURL = extractBaseURL(reverseProxyUrl) ?? anthropicBaseURL;
+  }
+
+  if (!apiKey) {
+    return models;
+  }
+
+  const modelsCache = standardCache(CacheKeys.MODEL_QUERIES);
+
+  const cachedModels = await modelsCache.get(baseURL);
+  if (cachedModels) {
+    return cachedModels as string[];
+  }
+
+  if (baseURL) {
+    models = await fetchModels({
+      apiKey,
+      baseURL,
+      user: opts.user,
+      name: EModelEndpoint.anthropic,
+      tokenKey: EModelEndpoint.anthropic,
+    });
+  }
+
+  if (models.length === 0) {
+    return _models;
+  }
+
+  await modelsCache.set(baseURL, models);
+  return models;
+}
+
+/**
+ * Gets Anthropic models from environment or API.
+ * @param opts - Options for fetching models
+ * @returns Promise resolving to array of model IDs
+ */
+export async function getAnthropicModels(opts: { user?: string } = {}): Promise<string[]> {
+  const models = defaultModels[EModelEndpoint.anthropic];
+  if (process.env.ANTHROPIC_MODELS) {
+    return splitAndTrim(process.env.ANTHROPIC_MODELS);
+  }
+
+  if (isUserProvided(process.env.ANTHROPIC_API_KEY)) {
+    return models;
+  }
+
+  try {
+    return await fetchAnthropicModels(opts, models);
+  } catch (error) {
+    logger.error('Error fetching Anthropic models:', error);
+    return models;
+  }
+}
+
+/**
+ * Gets Google models from environment or defaults.
+ * @returns Array of model IDs
+ */
+export function getGoogleModels(): string[] {
+  let models = defaultModels[EModelEndpoint.google];
+  if (process.env.GOOGLE_MODELS) {
+    models = splitAndTrim(process.env.GOOGLE_MODELS);
+  }
+  return models;
+}
+
+/**
+ * Gets Bedrock models from environment or defaults.
+ * @returns Array of model IDs
+ */
+export function getBedrockModels(): string[] {
+  let models = defaultModels[EModelEndpoint.bedrock];
+  if (process.env.BEDROCK_AWS_MODELS) {
+    models = splitAndTrim(process.env.BEDROCK_AWS_MODELS);
+  }
+  return models;
+}