fix(RAG): add start button in kb modal and ensure restart policy exists (#700)

Adds a check to RAG health to make sure nomad_qdrant is online, if not
then the user will be blocked from clicking any buttons in the KB modal
until they click the start qdrant button and let the container start

There is a new file qdrant_restart_policy_provider.ts, which tries to
ensure that the restart policy always exists for the nomad_qdrant
container even though the policy should have been there when the
container is created.

admin/adonisrc.ts

@@ -55,6 +55,7 @@ export default defineConfig({
     () => import('@adonisjs/transmit/transmit_provider'),
     () => import('#providers/map_static_provider'),
     () => import('#providers/kiwix_migration_provider'),
+    () => import('#providers/qdrant_restart_policy_provider'),
   ],
 
   /*

admin/app/controllers/rag_controller.ts

@@ -97,4 +97,9 @@ export default class RagController {
       return response.status(500).json({ error: 'Error scanning and syncing storage' })
     }
   }
+
+  public async health({ response }: HttpContext) {
+    const result = await this.ragService.checkQdrantHealth()
+    return response.status(200).json(result)
+  }
 }

admin/app/services/rag_service.ts

@@ -52,14 +52,33 @@ export class RagService {
       this.qdrantInitPromise = (async () => {
         const qdrantUrl = await this.dockerService.getServiceURL(SERVICE_NAMES.QDRANT)
         if (!qdrantUrl) {
-          throw new Error('Qdrant service is not installed or running.')
+          throw new Error('Qdrant vector database is offline. Restart the AI Assistant service in Settings to restore the Knowledge Base.')
         }
         this.qdrant = new QdrantClient({ url: qdrantUrl })
-      })()
+      })().catch((err) => {
+        this.qdrantInitPromise = null
+        this.qdrant = null
+        throw err
+      })
     }
     return this.qdrantInitPromise
   }
 
+  public async checkQdrantHealth(): Promise<{ online: boolean; message?: string }> {
+    try {
+      await this._ensureDependencies()
+      await this.qdrant!.getCollections()
+      return { online: true }
+    } catch {
+      this.qdrant = null
+      this.qdrantInitPromise = null
+      return {
+        online: false,
+        message: 'Qdrant vector database is offline. Restart the AI Assistant service in Settings to restore the Knowledge Base.',
+      }
+    }
+  }
+
   private async _ensureDependencies() {
     if (!this.qdrant) {
       await this._initializeQdrantClient()

admin/inertia/components/chat/KnowledgeBaseModal.tsx

@@ -1,5 +1,5 @@
 import { useMutation, useQuery, useQueryClient } from '@tanstack/react-query'
-import { useRef, useState } from 'react'
+import { useEffect, useRef, useState } from 'react'
 import FileUploader from '~/components/file-uploader'
 import StyledButton from '~/components/StyledButton'
 import StyledSectionHeader from '~/components/StyledSectionHeader'
@@ -10,6 +10,7 @@ import { IconX } from '@tabler/icons-react'
 import { useModals } from '~/context/ModalContext'
 import StyledModal from '../StyledModal'
 import ActiveEmbedJobs from '~/components/ActiveEmbedJobs'
+import { SERVICE_NAMES } from '../../../constants/service_names'
 
 interface KnowledgeBaseModalProps {
   aiAssistantName?: string
@@ -30,6 +31,19 @@ export default function KnowledgeBaseModal({ aiAssistantName = "AI Assistant", o
   const { openModal, closeModal } = useModals()
   const queryClient = useQueryClient()
 
+  const [isStartingQdrant, setIsStartingQdrant] = useState(false)
+
+  const { data: healthStatus } = useQuery({
+    queryKey: ['qdrantHealth'],
+    queryFn: () => api.checkRAGHealth(),
+    refetchInterval: isStartingQdrant ? 3_000 : 30_000,
+  })
+  const qdrantOffline = healthStatus?.online === false
+
+  useEffect(() => {
+    if (!qdrantOffline) setIsStartingQdrant(false)
+  }, [qdrantOffline])
+
   const { data: storedFiles = [], isLoading: isLoadingFiles } = useQuery({
     queryKey: ['storedFiles'],
     queryFn: () => api.getStoredRAGFiles(),
@@ -64,6 +78,17 @@ export default function KnowledgeBaseModal({ aiAssistantName = "AI Assistant", o
     },
   })
 
+  const startQdrantMutation = useMutation({
+    mutationFn: () => api.affectService(SERVICE_NAMES.QDRANT, 'start'),
+    onSuccess: () => {
+      setIsStartingQdrant(true)
+      queryClient.invalidateQueries({ queryKey: ['qdrantHealth'] })
+    },
+    onError: (error: any) => {
+      addNotification({ type: 'error', message: error?.message || 'Failed to start Qdrant.' })
+    },
+  })
+
   const syncMutation = useMutation({
     mutationFn: () => api.syncRAGStorage(),
     onSuccess: (data) => {
@@ -149,6 +174,22 @@ export default function KnowledgeBaseModal({ aiAssistantName = "AI Assistant", o
           </button>
         </div>
         <div className="overflow-y-auto flex-1 p-6">
+          {qdrantOffline && (
+            <div className="mb-4 p-4 bg-red-50 border border-red-200 rounded-lg text-red-700 text-sm dark:bg-red-950 dark:border-red-800 dark:text-red-300 flex items-center justify-between gap-4">
+              <span>
+                <strong>Knowledge Base unavailable:</strong> The Qdrant vector database is offline.
+              </span>
+              <StyledButton
+                variant="danger"
+                size="sm"
+                onClick={() => startQdrantMutation.mutate()}
+                loading={startQdrantMutation.isPending || isStartingQdrant}
+                disabled={startQdrantMutation.isPending || isStartingQdrant}
+              >
+                {isStartingQdrant ? 'Starting…' : 'Start Qdrant'}
+              </StyledButton>
+            </div>
+          )}
           <div className="bg-surface-primary rounded-lg border shadow-md overflow-hidden">
             <div className="p-6">
               <FileUploader
@@ -165,7 +206,7 @@ export default function KnowledgeBaseModal({ aiAssistantName = "AI Assistant", o
                   size="lg"
                   icon="IconUpload"
                   onClick={handleUpload}
-                  disabled={files.length === 0 || isUploading}
+                  disabled={files.length === 0 || isUploading || qdrantOffline}
                   loading={isUploading}
                 >
                   Upload
@@ -236,7 +277,7 @@ export default function KnowledgeBaseModal({ aiAssistantName = "AI Assistant", o
                 icon="IconTrash"
                 onClick={() => cleanupFailedMutation.mutate()}
                 loading={cleanupFailedMutation.isPending}
-                disabled={cleanupFailedMutation.isPending}
+                disabled={cleanupFailedMutation.isPending || qdrantOffline}
               >
                 Clean Up Failed
               </StyledButton>
@@ -252,7 +293,7 @@ export default function KnowledgeBaseModal({ aiAssistantName = "AI Assistant", o
                 size="md"
                 icon='IconRefresh'
                 onClick={handleConfirmSync}
-                disabled={syncMutation.isPending || isUploading}
+                disabled={syncMutation.isPending || isUploading || qdrantOffline}
                 loading={syncMutation.isPending || isUploading}
               >
                 Sync Storage

admin/inertia/lib/api.ts

@@ -451,6 +451,13 @@ class API {
     })()
   }
 
+  async checkRAGHealth() {
+    return catchInternal(async () => {
+      const response = await this.client.get<{ online: boolean; message?: string }>('/rag/health')
+      return response.data
+    })()
+  }
+
   async getStoredRAGFiles() {
     return catchInternal(async () => {
       const response = await this.client.get<{ files: string[] }>('/rag/files')

admin/providers/qdrant_restart_policy_provider.ts

@@ -0,0 +1,62 @@
+import logger from '@adonisjs/core/services/logger'
+import type { ApplicationService } from '@adonisjs/core/types'
+
+/**
+ * Ensures the nomad_qdrant container has the `unless-stopped` restart policy.
+ *
+ * Existing installations may have been created before this policy was enforced
+ * in the service seeder. Docker allows updating a container's restart policy
+ * without recreating it via the container.update() API.
+ *
+ * This provider runs once on every admin startup. If the policy is already
+ * correct, the check is a no-op.
+ */
+export default class QdrantRestartPolicyProvider {
+  constructor(protected app: ApplicationService) {}
+
+  async boot() {
+    if (this.app.getEnvironment() !== 'web') return
+
+    setImmediate(async () => {
+      try {
+        const Service = (await import('#models/service')).default
+        const { SERVICE_NAMES } = await import('../constants/service_names.js')
+        const Docker = (await import('dockerode')).default
+
+        const qdrantService = await Service.query()
+          .where('service_name', SERVICE_NAMES.QDRANT)
+          .first()
+
+        if (!qdrantService?.installed) {
+          logger.info('[QdrantRestartPolicyProvider] Qdrant not installed — skipping restart policy check.')
+          return
+        }
+
+        const docker = new Docker({ socketPath: '/var/run/docker.sock' })
+        const containers = await docker.listContainers({ all: true })
+        const containerInfo = containers.find((c) => c.Names.includes(`/${SERVICE_NAMES.QDRANT}`))
+
+        if (!containerInfo) {
+          logger.warn('[QdrantRestartPolicyProvider] Qdrant container not found — skipping restart policy check.')
+          return
+        }
+
+        const container = docker.getContainer(containerInfo.Id)
+        const inspected = await container.inspect()
+        const currentPolicy = inspected.HostConfig?.RestartPolicy?.Name
+
+        if (currentPolicy === 'unless-stopped') {
+          logger.info('[QdrantRestartPolicyProvider] Qdrant already has unless-stopped restart policy — no update needed.')
+          return
+        }
+
+        logger.info(`[QdrantRestartPolicyProvider] Qdrant restart policy is "${currentPolicy ?? 'none'}" — updating to unless-stopped.`)
+        await container.update({ RestartPolicy: { Name: 'unless-stopped', MaximumRetryCount: 0 } })
+        logger.info('[QdrantRestartPolicyProvider] Qdrant restart policy updated successfully.')
+      } catch (err: any) {
+        logger.error(`[QdrantRestartPolicyProvider] Failed to update Qdrant restart policy: ${err.message}`)
+        // Non-fatal: the container will still run, just without auto-restart on crash.
+      }
+    })
+  }
+}

admin/start/routes.ts

@@ -143,6 +143,7 @@ router
     router.delete('/failed-jobs', [RagController, 'cleanupFailedJobs'])
     router.get('/job-status', [RagController, 'getJobStatus'])
     router.post('/sync', [RagController, 'scanAndSync'])
+    router.get('/health', [RagController, 'health'])
   })
   .prefix('/api/rag')