diff --git a/admin/app/controllers/ollama_controller.ts b/admin/app/controllers/ollama_controller.ts
index e58d249..edd6f36 100644
--- a/admin/app/controllers/ollama_controller.ts
+++ b/admin/app/controllers/ollama_controller.ts
@@ -8,7 +8,7 @@ import { modelNameSchema } from '#validators/download'
 import { chatSchema, getAvailableModelsSchema } from '#validators/ollama'
 import { inject } from '@adonisjs/core'
 import type { HttpContext } from '@adonisjs/core/http'
-import { DEFAULT_QUERY_REWRITE_MODEL, RAG_CONTEXT_LIMITS, SYSTEM_PROMPTS } from '../../constants/ollama.js'
+import { RAG_CONTEXT_LIMITS, SYSTEM_PROMPTS } from '../../constants/ollama.js'
 import { SERVICE_NAMES } from '../../constants/service_names.js'
 import logger from '@adonisjs/core/services/logger'
 type Message = { role: 'system' | 'user' | 'assistant'; content: string }
@@ -59,7 +59,7 @@ export default class OllamaController {
 
       // Query rewriting for better RAG retrieval with manageable context
       // Will return user's latest message if no rewriting is needed
-      const rewrittenQuery = await this.rewriteQueryWithContext(reqData.messages)
+      const rewrittenQuery = await this.rewriteQueryWithContext(reqData.messages, reqData.model)
 
       logger.debug(`[OllamaController] Rewritten query for RAG: "${rewrittenQuery}"`)
       if (rewrittenQuery) {
@@ -157,7 +157,7 @@ export default class OllamaController {
           await this.chatService.addMessage(sessionId, 'assistant', fullContent)
           const messageCount = await this.chatService.getMessageCount(sessionId)
           if (messageCount <= 2 && userContent) {
-            this.chatService.generateTitle(sessionId, userContent, fullContent).catch((err) => {
+            this.chatService.generateTitle(sessionId, userContent, fullContent, reqData.model).catch((err) => {
               logger.error(`[OllamaController] Title generation failed: ${err instanceof Error ? err.message : err}`)
             })
           }
@@ -172,7 +172,7 @@ export default class OllamaController {
         await this.chatService.addMessage(sessionId, 'assistant', result.message.content)
         const messageCount = await this.chatService.getMessageCount(sessionId)
         if (messageCount <= 2 && userContent) {
-          this.chatService.generateTitle(sessionId, userContent, result.message.content).catch((err) => {
+          this.chatService.generateTitle(sessionId, userContent, result.message.content, reqData.model).catch((err) => {
             logger.error(`[OllamaController] Title generation failed: ${err instanceof Error ? err.message : err}`)
           })
         }
@@ -312,9 +312,18 @@ export default class OllamaController {
   }
 
   private async rewriteQueryWithContext(
-    messages: Message[]
+    messages: Message[],
+    model: string
   ): Promise<string | null> {
+    const lastUserMessage = [...messages].reverse().find(msg => msg.role === 'user')
+
     try {
+      // Skip the entire RAG pipeline if there are no documents to search
+      const hasDocuments = await this.ragService.hasDocuments()
+      if (!hasDocuments) {
+        return null
+      }
+
       // Get recent conversation history (last 6 messages for 3 turns)
       const recentMessages = messages.slice(-6)
 
@@ -322,7 +331,7 @@ export default class OllamaController {
       // little RAG benefit until there is enough context to matter.
       const userMessages = recentMessages.filter(msg => msg.role === 'user')
       if (userMessages.length <= 2) {
-        return userMessages[userMessages.length - 1]?.content || null
+        return lastUserMessage?.content || null
       }
 
       const conversationContext = recentMessages
@@ -336,17 +345,8 @@ export default class OllamaController {
         })
         .join('\n')
 
-      const installedModels = await this.ollamaService.getModels(true)
-      const rewriteModelAvailable = installedModels?.some(model => model.name === DEFAULT_QUERY_REWRITE_MODEL)
-      if (!rewriteModelAvailable) {
-        logger.warn(`[RAG] Query rewrite model "${DEFAULT_QUERY_REWRITE_MODEL}" not available. Skipping query rewriting.`)
-        const lastUserMessage = [...messages].reverse().find(msg => msg.role === 'user')
-        return lastUserMessage?.content || null
-      }
-
-      // FUTURE ENHANCEMENT: allow the user to specify which model to use for rewriting
       const response = await this.ollamaService.chat({
-        model: DEFAULT_QUERY_REWRITE_MODEL,
+        model,
         messages: [
           {
             role: 'system',
@@ -367,7 +367,6 @@ export default class OllamaController {
         `[RAG] Query rewriting failed: ${error instanceof Error ? error.message : error}`
       )
       // Fallback to last user message if rewriting fails
-      const lastUserMessage = [...messages].reverse().find(msg => msg.role === 'user')
       return lastUserMessage?.content || null
     }
   }
diff --git a/admin/app/services/chat_service.ts b/admin/app/services/chat_service.ts
index 18b0108..2d97ad7 100644
--- a/admin/app/services/chat_service.ts
+++ b/admin/app/services/chat_service.ts
@@ -4,7 +4,7 @@ import logger from '@adonisjs/core/services/logger'
 import { DateTime } from 'luxon'
 import { inject } from '@adonisjs/core'
 import { OllamaService } from './ollama_service.js'
-import { DEFAULT_QUERY_REWRITE_MODEL, SYSTEM_PROMPTS } from '../../constants/ollama.js'
+import { SYSTEM_PROMPTS } from '../../constants/ollama.js'
 import { toTitleCase } from '../utils/misc.js'
 
 @inject()
@@ -232,29 +232,22 @@ export class ChatService {
     }
   }
 
-  async generateTitle(sessionId: number, userMessage: string, assistantMessage: string) {
+  async generateTitle(sessionId: number, userMessage: string, assistantMessage: string, model: string) {
     try {
-      const models = await this.ollamaService.getModels()
-      const titleModelAvailable = models?.some((m) => m.name === DEFAULT_QUERY_REWRITE_MODEL)
-
       let title: string
 
-      if (!titleModelAvailable) {
-        title = userMessage.slice(0, 57) + (userMessage.length > 57 ? '...' : '')
-      } else {
-        const response = await this.ollamaService.chat({
-          model: DEFAULT_QUERY_REWRITE_MODEL,
-          messages: [
-            { role: 'system', content: SYSTEM_PROMPTS.title_generation },
-            { role: 'user', content: userMessage },
-            { role: 'assistant', content: assistantMessage },
-          ],
-        })
+      const response = await this.ollamaService.chat({
+        model,
+        messages: [
+          { role: 'system', content: SYSTEM_PROMPTS.title_generation },
+          { role: 'user', content: userMessage },
+          { role: 'assistant', content: assistantMessage },
+        ],
+      })
 
-        title = response?.message?.content?.trim()
-        if (!title) {
-          title = userMessage.slice(0, 57) + (userMessage.length > 57 ? '...' : '')
-        }
+      title = response?.message?.content?.trim()
+      if (!title) {
+        title = userMessage.slice(0, 57) + (userMessage.length > 57 ? '...' : '')
       }
 
       await this.updateSession(sessionId, { title })
diff --git a/admin/app/services/rag_service.ts b/admin/app/services/rag_service.ts
index 0e9550e..67e8627 100644
--- a/admin/app/services/rag_service.ts
+++ b/admin/app/services/rag_service.ts
@@ -1013,6 +1013,16 @@ export class RagService {
    * Retrieve all unique source files that have been stored in the knowledge base.
    * @returns Array of unique full source paths
    */
+  public async hasDocuments(): Promise<boolean> {
+    try {
+      await this._ensureCollection(RagService.CONTENT_COLLECTION_NAME, RagService.EMBEDDING_DIMENSION)
+      const collectionInfo = await this.qdrant!.getCollection(RagService.CONTENT_COLLECTION_NAME)
+      return (collectionInfo.points_count ?? 0) > 0
+    } catch {
+      return false
+    }
+  }
+
   public async getStoredFiles(): Promise<string[]> {
     try {
       await this._ensureCollection(