🧩 feat: Web Search Config Validations & Clipboard Citation Processing (#7530)

* 🔧 chore: Add missing optional `scraperTimeout` to webSearchSchema

* chore: Add missing optional `scraperTimeout` to web search authentication result

* chore: linting

* feat: Integrate attachment handling and citation processing in message components

- Added `useAttachments` hook to manage message attachments and search results.
- Updated `MessageParts`, `ContentParts`, and `ContentRender` components to utilize the new hook for improved attachment handling.
- Enhanced `useCopyToClipboard` to format citations correctly, including support for composite citations and deduplication.
- Introduced utility functions for citation processing and cleanup.
- Added tests for the new `useCopyToClipboard` functionality to ensure proper citation formatting and handling.

* feat: Add configuration for LibreChat Code Interpreter API and Web Search variables

* fix: Update searchResults type to use SearchResultData for better type safety

* feat: Add web search configuration validation and logging

- Introduced `checkWebSearchConfig` function to validate web search configuration values, ensuring they are environment variable references.
- Added logging for proper configuration and warnings for incorrect values.
- Created unit tests for `checkWebSearchConfig` to cover various scenarios, including valid and invalid configurations.

* docs: Update README to include Web Search feature details

- Added a section for the Web Search feature, highlighting its capabilities to search the internet and enhance AI context.
- Included links for further information on the Web Search functionality.

* ci: Add mock for checkWebSearchConfig in AppService tests

* chore: linting

* feat: Enhance Shared Messages with Web Search UI by adding searchResults prop to SearchContent and MinimalHoverButtons components

* chore: linting

* refactor: remove Meilisearch index sync from importConversations function

* feat: update safeSearch implementation to use SafeSearchTypes enum

* refactor: remove commented-out code in loadTools function

* fix: ensure responseMessageId handles latestMessage ID correctly

* feat: enhance Vite configuration for improved chunking and caching

- Added additional globIgnores for map files in Workbox configuration.
- Implemented high-impact chunking for various large libraries to optimize performance.
- Increased chunkSizeWarningLimit from 1200 to 1500 for better handling of larger chunks.

* refactor: move health check hook to Root, fix bad setState for Temporary state

- Enhanced the `useHealthCheck` hook to initiate health checks only when the user is authenticated.
- Added logic for managing health check intervals and handling window focus events.
- Introduced a new test suite for `useHealthCheck` to cover various scenarios including authentication state changes and error handling.
- Removed the health check invocation from `ChatRoute` and added it to `Root` for global health monitoring.

* fix: update font alias in Vite configuration for correct path resolution

Author: danny-avila

.env.example

@@ -590,3 +590,33 @@ HELP_AND_FAQ_URL=https://librechat.ai
 #                  OpenWeather                        #
 #=====================================================#
 OPENWEATHER_API_KEY=
+
+#====================================#
+# LibreChat Code Interpreter API     #
+#====================================#
+
+# https://code.librechat.ai
+# LIBRECHAT_CODE_API_KEY=your-key
+
+#======================#
+# Web Search           #
+#======================#
+
+# Note: All of the following variable names can be customized.
+# Omit values to allow user to provide them.
+
+# For more information on configuration values, see:
+# https://librechat.ai/docs/features/web_search
+
+# Search Provider (Required)
+# SERPER_API_KEY=your_serper_api_key
+
+# Scraper (Required)
+# FIRECRAWL_API_KEY=your_firecrawl_api_key
+# Optional: Custom Firecrawl API URL
+# FIRECRAWL_API_URL=your_firecrawl_api_url
+
+# Reranker (Required)
+# JINA_API_KEY=your_jina_api_key
+# or
+# COHERE_API_KEY=your_cohere_api_key

README.md

@@ -71,6 +71,11 @@
     - [Model Context Protocol (MCP) Support](https://modelcontextprotocol.io/clients#librechat) for Tools
   - Use LibreChat Agents and OpenAI Assistants with Files, Code Interpreter, Tools, and API Actions
 
+- 🔍 **Web Search**:  
+  - Search the internet and retrieve relevant information to enhance your AI context
+  - Combines search providers, content scrapers, and result rerankers for optimal results
+  - **[Learn More →](https://www.librechat.ai/docs/features/web_search)**
+
 - 🪄 **Generative UI with Code Artifacts**:  
   - [Code Artifacts](https://youtu.be/GfTj7O4gmd0?si=WJbdnemZpJzBrJo3) allow creation of React, HTML, and Mermaid diagrams directly in chat
 

api/app/clients/tools/util/handleTools.js

@@ -277,10 +277,6 @@ const loadTools = async ({
       });
       const { onSearchResults, onGetHighlights } = options?.[Tools.web_search] ?? {};
       requestedTools[tool] = async () => {
-        // const { files, toolContext } = await primeSearchFiles(options);
-        // if (toolContext) {
-        //   toolContextMap[tool] = toolContext;
-        // }
         toolContextMap[tool] = `# \`${tool}\`:
 Current Date & Time: ${replaceSpecialVars({ text: '{{iso_datetime}}' })}
 1. **Execute immediately without preface** when using \`${tool}\`.

api/server/routes/convos.js

@@ -74,7 +74,7 @@ router.post('/gen_title', async (req, res) => {
     res.status(200).json({ title });
   } else {
     res.status(404).json({
-      message: 'Title not found or method not implemented for the conversation\'s endpoint',
+      message: "Title not found or method not implemented for the conversation's endpoint",
     });
   }
 });

api/server/services/AppService.interface.spec.js

@@ -25,6 +25,7 @@ jest.mock('./start/checks', () => ({
   checkHealth: jest.fn(),
   checkConfig: jest.fn(),
   checkAzureVariables: jest.fn(),
+  checkWebSearchConfig: jest.fn(),
 }));
 
 const AppService = require('./AppService');

api/server/services/AppService.js

@@ -6,7 +6,13 @@ const {
   getConfigDefaults,
   loadWebSearchConfig,
 } = require('librechat-data-provider');
-const { checkVariables, checkHealth, checkConfig, checkAzureVariables } = require('./start/checks');
+const {
+  checkHealth,
+  checkConfig,
+  checkVariables,
+  checkAzureVariables,
+  checkWebSearchConfig,
+} = require('./start/checks');
 const { azureAssistantsDefaults, assistantsConfigSetup } = require('./start/assistants');
 const { initializeAzureBlobService } = require('./Files/Azure/initialize');
 const { initializeFirebase } = require('./Files/Firebase/initialize');
@@ -37,6 +43,7 @@ const AppService = async (app) => {
 
   const ocr = loadOCRConfig(config.ocr);
   const webSearch = loadWebSearchConfig(config.webSearch);
+  checkWebSearchConfig(webSearch);
   const filteredTools = config.filteredTools;
   const includedTools = config.includedTools;
   const fileStrategy = config.fileStrategy ?? configDefaults.fileStrategy;

api/server/services/AppService.spec.js

@@ -146,7 +146,7 @@ describe('AppService', () => {
         firecrawlApiKey: '${FIRECRAWL_API_KEY}',
         firecrawlApiUrl: '${FIRECRAWL_API_URL}',
         jinaApiKey: '${JINA_API_KEY}',
-        safeSearch: true,
+        safeSearch: 1,
         serperApiKey: '${SERPER_API_KEY}',
       },
     });

api/server/services/start/checks.js

@@ -1,7 +1,9 @@
 const {
   Constants,
+  webSearchKeys,
   deprecatedAzureVariables,
   conflictingAzureVariables,
+  extractVariableName,
 } = require('librechat-data-provider');
 const { isEnabled, checkEmailConfig } = require('~/server/utils');
 const { logger } = require('~/config');
@@ -141,4 +143,56 @@ function checkPasswordReset() {
   }
 }
 
-module.exports = { checkVariables, checkHealth, checkConfig, checkAzureVariables };
+/**
+ * Checks web search configuration values to ensure they are environment variable references.
+ * Warns if actual API keys or URLs are used instead of environment variable references.
+ * Logs debug information for properly configured environment variable references.
+ * @param {Object} webSearchConfig - The loaded web search configuration object.
+ */
+function checkWebSearchConfig(webSearchConfig) {
+  if (!webSearchConfig) {
+    return;
+  }
+
+  webSearchKeys.forEach((key) => {
+    const value = webSearchConfig[key];
+
+    if (typeof value === 'string') {
+      const varName = extractVariableName(value);
+
+      if (varName) {
+        // This is a proper environment variable reference
+        const actualValue = process.env[varName];
+        if (actualValue) {
+          logger.debug(`Web search ${key}: Using environment variable ${varName} with value set`);
+        } else {
+          logger.debug(
+            `Web search ${key}: Using environment variable ${varName} (not set in environment, user provided value)`,
+          );
+        }
+      } else {
+        // This is not an environment variable reference - warn user
+        logger.warn(
+          `❗ Web search configuration error: ${key} contains an actual value instead of an environment variable reference.
+          
+          Current value: "${value.substring(0, 10)}..."
+          
+          This is incorrect! You should use environment variable references in your librechat.yaml file, such as:
+          ${key}: "\${YOUR_ENV_VAR_NAME}"
+          
+          Then set the actual API key in your .env file or environment variables.
+          
+          More info: https://www.librechat.ai/docs/configuration/librechat_yaml/web_search`,
+        );
+      }
+    }
+  });
+}
+
+module.exports = {
+  checkHealth,
+  checkConfig,
+  checkVariables,
+  checkAzureVariables,
+  checkWebSearchConfig,
+};

api/server/services/start/checks.spec.js

@@ -0,0 +1,203 @@
+// Mock librechat-data-provider
+jest.mock('librechat-data-provider', () => ({
+  ...jest.requireActual('librechat-data-provider'),
+  extractVariableName: jest.fn(),
+}));
+
+// Mock the config logger
+jest.mock('~/config', () => ({
+  logger: {
+    debug: jest.fn(),
+    warn: jest.fn(),
+  },
+}));
+
+const { checkWebSearchConfig } = require('./checks');
+const { logger } = require('~/config');
+const { extractVariableName } = require('librechat-data-provider');
+
+describe('checkWebSearchConfig', () => {
+  let originalEnv;
+
+  beforeEach(() => {
+    // Clear all mocks
+    jest.clearAllMocks();
+
+    // Store original environment
+    originalEnv = process.env;
+
+    // Reset process.env
+    process.env = { ...originalEnv };
+  });
+
+  afterEach(() => {
+    // Restore original environment
+    process.env = originalEnv;
+  });
+
+  describe('when webSearchConfig is undefined or null', () => {
+    it('should return early without logging when config is undefined', () => {
+      checkWebSearchConfig(undefined);
+
+      expect(logger.debug).not.toHaveBeenCalled();
+      expect(logger.warn).not.toHaveBeenCalled();
+    });
+
+    it('should return early without logging when config is null', () => {
+      checkWebSearchConfig(null);
+
+      expect(logger.debug).not.toHaveBeenCalled();
+      expect(logger.warn).not.toHaveBeenCalled();
+    });
+  });
+
+  describe('when config values are proper environment variable references', () => {
+    it('should log debug message for each valid environment variable with value set', () => {
+      const config = {
+        serperApiKey: '${SERPER_API_KEY}',
+        jinaApiKey: '${JINA_API_KEY}',
+      };
+
+      extractVariableName.mockReturnValueOnce('SERPER_API_KEY').mockReturnValueOnce('JINA_API_KEY');
+
+      process.env.SERPER_API_KEY = 'test-serper-key';
+      process.env.JINA_API_KEY = 'test-jina-key';
+
+      checkWebSearchConfig(config);
+
+      expect(extractVariableName).toHaveBeenCalledWith('${SERPER_API_KEY}');
+      expect(extractVariableName).toHaveBeenCalledWith('${JINA_API_KEY}');
+      expect(logger.debug).toHaveBeenCalledWith(
+        'Web search serperApiKey: Using environment variable SERPER_API_KEY with value set',
+      );
+      expect(logger.debug).toHaveBeenCalledWith(
+        'Web search jinaApiKey: Using environment variable JINA_API_KEY with value set',
+      );
+      expect(logger.warn).not.toHaveBeenCalled();
+    });
+
+    it('should log debug message for environment variables not set in environment', () => {
+      const config = {
+        cohereApiKey: '${COHERE_API_KEY}',
+      };
+
+      extractVariableName.mockReturnValue('COHERE_API_KEY');
+
+      delete process.env.COHERE_API_KEY;
+
+      checkWebSearchConfig(config);
+
+      expect(logger.debug).toHaveBeenCalledWith(
+        'Web search cohereApiKey: Using environment variable COHERE_API_KEY (not set in environment, user provided value)',
+      );
+      expect(logger.warn).not.toHaveBeenCalled();
+    });
+  });
+
+  describe('when config values are actual values instead of environment variable references', () => {
+    it('should warn when serperApiKey contains actual API key', () => {
+      const config = {
+        serperApiKey: 'sk-1234567890abcdef',
+      };
+
+      extractVariableName.mockReturnValue(null);
+
+      checkWebSearchConfig(config);
+
+      expect(logger.warn).toHaveBeenCalledWith(
+        expect.stringContaining(
+          '❗ Web search configuration error: serperApiKey contains an actual value',
+        ),
+      );
+      expect(logger.warn).toHaveBeenCalledWith(
+        expect.stringContaining('Current value: "sk-1234567..."'),
+      );
+      expect(logger.debug).not.toHaveBeenCalled();
+    });
+
+    it('should warn when firecrawlApiUrl contains actual URL', () => {
+      const config = {
+        firecrawlApiUrl: 'https://api.firecrawl.dev',
+      };
+
+      extractVariableName.mockReturnValue(null);
+
+      checkWebSearchConfig(config);
+
+      expect(logger.warn).toHaveBeenCalledWith(
+        expect.stringContaining(
+          '❗ Web search configuration error: firecrawlApiUrl contains an actual value',
+        ),
+      );
+      expect(logger.warn).toHaveBeenCalledWith(
+        expect.stringContaining('Current value: "https://ap..."'),
+      );
+    });
+
+    it('should include documentation link in warning message', () => {
+      const config = {
+        firecrawlApiKey: 'fc-actual-key',
+      };
+
+      extractVariableName.mockReturnValue(null);
+
+      checkWebSearchConfig(config);
+
+      expect(logger.warn).toHaveBeenCalledWith(
+        expect.stringContaining(
+          'More info: https://www.librechat.ai/docs/configuration/librechat_yaml/web_search',
+        ),
+      );
+    });
+  });
+
+  describe('when config contains mixed value types', () => {
+    it('should only process string values and ignore non-string values', () => {
+      const config = {
+        serperApiKey: '${SERPER_API_KEY}',
+        safeSearch: 1,
+        scraperTimeout: 7500,
+        jinaApiKey: 'actual-key',
+      };
+
+      extractVariableName.mockReturnValueOnce('SERPER_API_KEY').mockReturnValueOnce(null);
+
+      process.env.SERPER_API_KEY = 'test-key';
+
+      checkWebSearchConfig(config);
+
+      expect(extractVariableName).toHaveBeenCalledTimes(2);
+      expect(logger.debug).toHaveBeenCalledTimes(1);
+      expect(logger.warn).toHaveBeenCalledTimes(1);
+    });
+  });
+
+  describe('edge cases', () => {
+    it('should handle config with no web search keys', () => {
+      const config = {
+        someOtherKey: 'value',
+        anotherKey: '${SOME_VAR}',
+      };
+
+      checkWebSearchConfig(config);
+
+      expect(extractVariableName).not.toHaveBeenCalled();
+      expect(logger.debug).not.toHaveBeenCalled();
+      expect(logger.warn).not.toHaveBeenCalled();
+    });
+
+    it('should truncate long values in warning messages', () => {
+      const config = {
+        serperApiKey: 'this-is-a-very-long-api-key-that-should-be-truncated-in-the-warning-message',
+      };
+
+      extractVariableName.mockReturnValue(null);
+
+      checkWebSearchConfig(config);
+
+      expect(logger.warn).toHaveBeenCalledWith(
+        expect.stringContaining('Current value: "this-is-a-..."'),
+      );
+    });
+  });
+});

api/server/utils/import/importConversations.js

@@ -1,6 +1,5 @@
 const fs = require('fs').promises;
 const { getImporter } = require('./importers');
-const { indexSync } = require('~/lib/db');
 const { logger } = require('~/config');
 
 /**
@@ -15,8 +14,6 @@ const importConversations = async (job) => {
     const jsonData = JSON.parse(fileData);
     const importer = getImporter(jsonData);
     await importer(jsonData, requestUserId);
-    // Sync Meilisearch index
-    await indexSync();
     logger.debug(`user: ${requestUserId} | Finished importing conversations`);
   } catch (error) {
     logger.error(`user: ${requestUserId} | Failed to import conversation: `, error);