feat(llm): create endpoints for starting/stopping embeddings

apps/client/src/widgets/type_widgets/options/ai_settings/ai_settings_widget.ts

@@ -51,6 +51,35 @@ export default class AiSettingsWidget extends OptionsWidget {
 
             await this.updateOption(optionName, value);
 
+            // Special handling for aiEnabled option
+            if (optionName === 'aiEnabled') {
+                try {
+                    const isEnabled = value === 'true';
+                    
+                    if (isEnabled) {
+                        // Start embedding generation
+                        await server.post('llm/embeddings/start');
+                        toastService.showMessage(t("ai_llm.embeddings_started") || "Embedding generation started");
+                        
+                        // Start polling for stats updates
+                        this.refreshEmbeddingStats();
+                    } else {
+                        // Stop embedding generation
+                        await server.post('llm/embeddings/stop');
+                        toastService.showMessage(t("ai_llm.embeddings_stopped") || "Embedding generation stopped");
+                        
+                        // Clear any active polling intervals
+                        if (this.indexRebuildRefreshInterval) {
+                            clearInterval(this.indexRebuildRefreshInterval);
+                            this.indexRebuildRefreshInterval = null;
+                        }
+                    }
+                } catch (error) {
+                    console.error('Error toggling embeddings:', error);
+                    toastService.showError(t("ai_llm.embeddings_toggle_error") || "Error toggling embeddings");
+                }
+            }
+
             if (validateAfter) {
                 await this.displayValidationWarnings();
             }

apps/server/src/routes/api/embeddings.ts

@@ -782,6 +782,49 @@ async function getIndexRebuildStatus(req: Request, res: Response) {
     };
 }
 
+/**
+ * Start embedding generation when AI is enabled
+ */
+async function startEmbeddings(req: Request, res: Response) {
+    try {
+        log.info("Starting embedding generation system");
+        
+        // Initialize the index service if not already initialized
+        await indexService.initialize();
+        
+        // Start automatic indexing
+        await indexService.startEmbeddingGeneration();
+        
+        return {
+            success: true,
+            message: "Embedding generation started"
+        };
+    } catch (error: any) {
+        log.error(`Error starting embeddings: ${error.message || 'Unknown error'}`);
+        throw new Error(`Failed to start embeddings: ${error.message || 'Unknown error'}`);
+    }
+}
+
+/**
+ * Stop embedding generation when AI is disabled
+ */
+async function stopEmbeddings(req: Request, res: Response) {
+    try {
+        log.info("Stopping embedding generation system");
+        
+        // Stop automatic indexing
+        await indexService.stopEmbeddingGeneration();
+        
+        return {
+            success: true,
+            message: "Embedding generation stopped"
+        };
+    } catch (error: any) {
+        log.error(`Error stopping embeddings: ${error.message || 'Unknown error'}`);
+        throw new Error(`Failed to stop embeddings: ${error.message || 'Unknown error'}`);
+    }
+}
+
 export default {
     findSimilarNotes,
     searchByText,
@@ -794,5 +837,7 @@ export default {
     retryFailedNote,
     retryAllFailedNotes,
     rebuildIndex,
-    getIndexRebuildStatus
+    getIndexRebuildStatus,
+    startEmbeddings,
+    stopEmbeddings
 };

apps/server/src/routes/routes.ts

@@ -400,6 +400,8 @@ function register(app: express.Application) {
     asyncApiRoute(PST, "/api/llm/embeddings/retry-all-failed", embeddingsRoute.retryAllFailedNotes);
     asyncApiRoute(PST, "/api/llm/embeddings/rebuild-index", embeddingsRoute.rebuildIndex);
     asyncApiRoute(GET, "/api/llm/embeddings/index-rebuild-status", embeddingsRoute.getIndexRebuildStatus);
+    asyncApiRoute(PST, "/api/llm/embeddings/start", embeddingsRoute.startEmbeddings);
+    asyncApiRoute(PST, "/api/llm/embeddings/stop", embeddingsRoute.stopEmbeddings);
 
     // LLM provider endpoints - moved under /api/llm/providers hierarchy
     asyncApiRoute(GET, "/api/llm/providers/ollama/models", ollamaRoute.listModels);

apps/server/src/services/llm/ai_service_manager.ts

@@ -605,6 +605,7 @@ export class AIServiceManager implements IAIServiceManager {
     private setupProviderChangeListener(): void {
         // List of AI-related options that should trigger service recreation
         const aiRelatedOptions = [
+            'aiEnabled',
             'aiSelectedProvider',
             'embeddingSelectedProvider',
             'openaiApiKey',
@@ -618,11 +619,30 @@ export class AIServiceManager implements IAIServiceManager {
             'voyageApiKey'
         ];
 
-        eventService.subscribe(['entityChanged'], ({ entityName, entity }) => {
+        eventService.subscribe(['entityChanged'], async ({ entityName, entity }) => {
             if (entityName === 'options' && entity && aiRelatedOptions.includes(entity.name)) {
                 log.info(`AI-related option '${entity.name}' changed, recreating LLM services`);
+                
+                // Special handling for aiEnabled toggle
+                if (entity.name === 'aiEnabled') {
+                    const isEnabled = entity.value === 'true';
+                    
+                    if (isEnabled) {
+                        log.info('AI features enabled, initializing AI service and embeddings');
+                        // Initialize the AI service
+                        await this.initialize();
+                        // Initialize embeddings through index service
+                        await indexService.startEmbeddingGeneration();
+                    } else {
+                        log.info('AI features disabled, stopping embeddings');
+                        // Stop embeddings through index service
+                        await indexService.stopEmbeddingGeneration();
+                    }
+                } else {
+                    // For other AI-related options, just recreate services
                     this.recreateServices();
                 }
+            }
         });
     }
 

apps/server/src/services/llm/embeddings/events.ts

@@ -9,6 +9,9 @@ import becca from "../../../becca/becca.js";
 // Add mutex to prevent concurrent processing
 let isProcessingEmbeddings = false;
 
+// Store interval reference for cleanup
+let backgroundProcessingInterval: NodeJS.Timeout | null = null;
+
 /**
  * Setup event listeners for embedding-related events
  */
@@ -53,9 +56,15 @@ export function setupEmbeddingEventListeners() {
  * Setup background processing of the embedding queue
  */
 export async function setupEmbeddingBackgroundProcessing() {
+    // Clear any existing interval
+    if (backgroundProcessingInterval) {
+        clearInterval(backgroundProcessingInterval);
+        backgroundProcessingInterval = null;
+    }
+
     const interval = parseInt(await options.getOption('embeddingUpdateInterval') || '200', 10);
 
-    setInterval(async () => {
+    backgroundProcessingInterval = setInterval(async () => {
         try {
             // Skip if already processing
             if (isProcessingEmbeddings) {
@@ -78,6 +87,17 @@ export async function setupEmbeddingBackgroundProcessing() {
     }, interval);
 }
 
+/**
+ * Stop background processing of the embedding queue
+ */
+export function stopEmbeddingBackgroundProcessing() {
+    if (backgroundProcessingInterval) {
+        clearInterval(backgroundProcessingInterval);
+        backgroundProcessingInterval = null;
+        log.info("Embedding background processing stopped");
+    }
+}
+
 /**
  * Initialize embeddings system
  */

apps/server/src/services/llm/embeddings/index.ts

@@ -58,6 +58,7 @@ export const processNoteWithChunking = async (
 export const {
     setupEmbeddingEventListeners,
     setupEmbeddingBackgroundProcessing,
+    stopEmbeddingBackgroundProcessing,
     initEmbeddings
 } = events;
 
@@ -100,6 +101,7 @@ export default {
     // Event handling
     setupEmbeddingEventListeners: events.setupEmbeddingEventListeners,
     setupEmbeddingBackgroundProcessing: events.setupEmbeddingBackgroundProcessing,
+    stopEmbeddingBackgroundProcessing: events.stopEmbeddingBackgroundProcessing,
     initEmbeddings: events.initEmbeddings,
 
     // Stats and maintenance

apps/server/src/services/llm/index_service.ts

@@ -837,6 +837,81 @@ export class IndexService {
             return false;
         }
     }
+
+    /**
+     * Start embedding generation (called when AI is enabled)
+     */
+    async startEmbeddingGeneration() {
+        try {
+            log.info("Starting embedding generation system");
+            
+            // Re-initialize if needed
+            if (!this.initialized) {
+                await this.initialize();
+            }
+            
+            const aiEnabled = options.getOptionOrNull('aiEnabled') === "true";
+            if (!aiEnabled) {
+                log.error("Cannot start embedding generation - AI features are disabled");
+                throw new Error("AI features must be enabled first");
+            }
+
+            // Check if this instance should process embeddings
+            const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
+            const isSyncServer = await this.isSyncServerForEmbeddings();
+            const shouldProcessEmbeddings = embeddingLocation === 'client' || isSyncServer;
+
+            if (!shouldProcessEmbeddings) {
+                log.info("This instance is not configured to process embeddings");
+                return;
+            }
+
+            // Setup automatic indexing if enabled
+            if (await options.getOptionBool('embeddingAutoUpdateEnabled')) {
+                this.setupAutomaticIndexing();
+                log.info(`Automatic embedding indexing started ${isSyncServer ? 'as sync server' : 'as client'}`);
+            }
+
+            // Re-initialize event listeners
+            this.setupEventListeners();
+
+            // Start processing the queue immediately
+            await this.runBatchIndexing(20);
+            
+            log.info("Embedding generation started successfully");
+        } catch (error: any) {
+            log.error(`Error starting embedding generation: ${error.message || "Unknown error"}`);
+            throw error;
+        }
+    }
+
+    /**
+     * Stop embedding generation (called when AI is disabled)
+     */
+    async stopEmbeddingGeneration() {
+        try {
+            log.info("Stopping embedding generation system");
+            
+            // Clear automatic indexing interval
+            if (this.automaticIndexingInterval) {
+                clearInterval(this.automaticIndexingInterval);
+                this.automaticIndexingInterval = undefined;
+                log.info("Automatic indexing stopped");
+            }
+
+            // Stop the background processing from embeddings/events.ts
+            vectorStore.stopEmbeddingBackgroundProcessing();
+
+            // Mark as not indexing
+            this.indexingInProgress = false;
+            this.indexRebuildInProgress = false;
+            
+            log.info("Embedding generation stopped successfully");
+        } catch (error: any) {
+            log.error(`Error stopping embedding generation: ${error.message || "Unknown error"}`);
+            throw error;
+        }
+    }
 }
 
 // Create singleton instance