fix: remove Ollama default fallbacks in factory and Docker

ROOT CAUSE: The factory was defaulting to 'ollama' when no provider
was configured, and docker-compose.yml was always setting OLLAMA_BASE_URL
even when using OpenAI. This caused the app to try connecting to Ollama
even when OpenAI was configured in the admin.

CRITICAL CHANGES:
1. lib/ai/factory.ts - Removed 'ollama' default fallback
   - getTagsProvider() now throws error if AI_PROVIDER_TAGS not set
   - getEmbeddingsProvider() now throws error if AI_PROVIDER_EMBEDDING not set
   - Forces explicit configuration instead of silent fallback to Ollama

2. docker-compose.yml - Removed default OLLAMA_BASE_URL
   - Changed: OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-http://ollama:11434}
   - To: OLLAMA_BASE_URL=${OLLAMA_BASE_URL}
   - Only set if explicitly defined in .env.docker

3. Application name: Mento → Memento (correct spelling)
   - Updated in: sidebar, README, deploy.sh, DOCKER_DEPLOYMENT.md

4. app/api/ai/config/route.ts - Return 'not set' instead of 'ollama'
   - Makes it clear when provider is not configured

IMPACT: The app will now properly use OpenAI when configured in the
admin interface, instead of silently falling back to Ollama.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

docker-compose.yml

@@ -25,9 +25,10 @@ services:
       - SMTP_FROM=${SMTP_FROM:-noreply@memento.app}
 
       # AI Providers
+      # Only define these if you're using the corresponding provider
       - OPENAI_API_KEY=${OPENAI_API_KEY}
-      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-http://ollama:11434}
+      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL}
-      - OLLAMA_MODEL=${OLLAMA_MODEL:-granite4:latest}
+      - OLLAMA_MODEL=${OLLAMA_MODEL}
     volumes:
       - db-data:/app/prisma
       - uploads-data:/app/public/uploads

keep-notes/DOCKER_DEPLOYMENT.md

@@ -1,6 +1,6 @@
 # 🐳 Docker Deployment Guide for Proxmox
 
-Complete guide to deploy Mento on Proxmox using Docker Compose.
+Complete guide to deploy Memento on Proxmox using Docker Compose.
 
 ## 📋 Prerequisites
 
@@ -375,7 +375,7 @@ usermod -aG docker ubuntu
 # Add: features: nesting=1,keyctl=1
 ```
 
-Then deploy Mento as described above.
+Then deploy Memento as described above.
 
 ## 📚 Additional Resources
 

keep-notes/README.md

@@ -1,8 +1,8 @@
-# Mento - Google Keep Clone
+# Memento - Google Keep Clone
 
 A beautiful and feature-rich Google Keep clone built with modern web technologies.
 
-![Mento](https://img.shields.io/badge/Next.js-16-black)
+![Memento](https://img.shields.io/badge/Next.js-16-black)
 ![TypeScript](https://img.shields.io/badge/TypeScript-5.0-blue)
 ![Tailwind CSS](https://img.shields.io/badge/Tailwind-4.0-38bdf8)
 ![Prisma](https://img.shields.io/badge/Prisma-7.0-2d3748)

keep-notes/app/api/ai/config/route.ts

@@ -6,14 +6,14 @@ export async function GET(request: NextRequest) {
     const config = await getSystemConfig()
 
     return NextResponse.json({
-      AI_PROVIDER_TAGS: config.AI_PROVIDER_TAGS || 'ollama',
+      AI_PROVIDER_TAGS: config.AI_PROVIDER_TAGS || 'not set',
-      AI_MODEL_TAGS: config.AI_MODEL_TAGS || 'granite4:latest',
+      AI_MODEL_TAGS: config.AI_MODEL_TAGS || 'not set',
-      AI_PROVIDER_EMBEDDING: config.AI_PROVIDER_EMBEDDING || 'ollama',
+      AI_PROVIDER_EMBEDDING: config.AI_PROVIDER_EMBEDDING || 'not set',
-      AI_MODEL_EMBEDDING: config.AI_MODEL_EMBEDDING || 'embeddinggemma:latest',
+      AI_MODEL_EMBEDDING: config.AI_MODEL_EMBEDDING || 'not set',
       OPENAI_API_KEY: config.OPENAI_API_KEY ? '***configured***' : '',
       CUSTOM_OPENAI_API_KEY: config.CUSTOM_OPENAI_API_KEY ? '***configured***' : '',
       CUSTOM_OPENAI_BASE_URL: config.CUSTOM_OPENAI_BASE_URL || '',
-      OLLAMA_BASE_URL: config.OLLAMA_BASE_URL || 'http://localhost:11434'
+      OLLAMA_BASE_URL: config.OLLAMA_BASE_URL || 'not set'
     })
   } catch (error: any) {
     return NextResponse.json(

keep-notes/components/sidebar.tsx

@@ -79,7 +79,7 @@ export function Sidebar({ className, user }: { className?: string, user?: any })
             <StickyNote className="h-5 w-5" />
           </div>
           <div className="flex flex-col">
-            <span className="text-lg font-bold tracking-tight text-slate-900 dark:text-white leading-none">Mento</span>
+            <span className="text-lg font-bold tracking-tight text-slate-900 dark:text-white leading-none">Memento</span>
             <span className="text-[10px] font-medium text-slate-400 dark:text-slate-500 uppercase tracking-widest mt-1">{t('nav.workspace')}</span>
           </div>
         </div>

keep-notes/deploy.sh

@@ -1,11 +1,11 @@
 #!/bin/bash
 
-# Mento Docker Deployment Script
+# Memento Docker Deployment Script
-# This script helps you build and deploy Mento on Proxmox/Docker
+# This script helps you build and deploy Memento on Proxmox/Docker
 
 set -e
 
-echo "🚀 Mento Docker Deployment"
+echo "🚀 Memento Docker Deployment"
 echo "================================"
 echo ""
 

keep-notes/lib/ai/factory.ts

@@ -64,19 +64,41 @@ function getProviderInstance(providerType: ProviderType, config: Record<string,
 }
 
 export function getTagsProvider(config?: Record<string, string>): AIProvider {
-  const providerType = (config?.AI_PROVIDER_TAGS || process.env.AI_PROVIDER_TAGS || 'ollama').toLowerCase() as ProviderType;
+  // Check database config first, then environment variables
+  const providerType = (config?.AI_PROVIDER_TAGS || process.env.AI_PROVIDER_TAGS);
+
+  // If no provider is configured, throw a clear error
+  if (!providerType) {
+    throw new Error(
+      'AI_PROVIDER_TAGS is not configured. Please set it in the admin settings or environment variables. ' +
+      'Options: ollama, openai, custom'
+    );
+  }
+
+  const provider = providerType.toLowerCase() as ProviderType;
   const modelName = config?.AI_MODEL_TAGS || process.env.AI_MODEL_TAGS || 'granite4:latest';
   const embeddingModelName = config?.AI_MODEL_EMBEDDING || process.env.AI_MODEL_EMBEDDING || 'embeddinggemma:latest';
 
-  return getProviderInstance(providerType, config || {}, modelName, embeddingModelName);
+  return getProviderInstance(provider, config || {}, modelName, embeddingModelName);
 }
 
 export function getEmbeddingsProvider(config?: Record<string, string>): AIProvider {
-  const providerType = (config?.AI_PROVIDER_EMBEDDING || process.env.AI_PROVIDER_EMBEDDING || 'ollama').toLowerCase() as ProviderType;
+  // Check database config first, then environment variables
+  const providerType = (config?.AI_PROVIDER_EMBEDDING || process.env.AI_PROVIDER_EMBEDDING);
+
+  // If no provider is configured, throw a clear error
+  if (!providerType) {
+    throw new Error(
+      'AI_PROVIDER_EMBEDDING is not configured. Please set it in the admin settings or environment variables. ' +
+      'Options: ollama, openai, custom'
+    );
+  }
+
+  const provider = providerType.toLowerCase() as ProviderType;
   const modelName = config?.AI_MODEL_TAGS || process.env.AI_MODEL_TAGS || 'granite4:latest';
   const embeddingModelName = config?.AI_MODEL_EMBEDDING || process.env.AI_MODEL_EMBEDDING || 'embeddinggemma:latest';
 
-  return getProviderInstance(providerType, config || {}, modelName, embeddingModelName);
+  return getProviderInstance(provider, config || {}, modelName, embeddingModelName);
 }
 
 // Legacy function for backward compatibility