feat(rag): add knowledge base migration from v4.9.0 to plugin architecture

Rewrite dbm020 to backup old knowledge_bases data and preserve
external_knowledge_bases table. Add migration API endpoints and
frontend dialog so users can opt-in to auto-install LangRAG plugin
and restore their knowledge bases with original UUIDs preserved.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/langbot/pkg/api/http/controller/groups/knowledge/migration.py

@@ -0,0 +1,290 @@
+import asyncio
+import json
+
+import sqlalchemy
+
+from ... import group
+from ......core import taskmgr
+from ......entity.persistence import metadata as persistence_metadata
+from langbot_plugin.runtime.plugin.mgr import PluginInstallSource
+
+LANGRAG_PLUGIN_AUTHOR = 'langbot-team'
+LANGRAG_PLUGIN_NAME = 'LangRAG'
+LANGRAG_PLUGIN_ID = f'{LANGRAG_PLUGIN_AUTHOR}/{LANGRAG_PLUGIN_NAME}'
+
+
+@group.group_class('knowledge/migration', '/api/v1/knowledge/migration')
+class KnowledgeMigrationRouterGroup(group.RouterGroup):
+    async def _get_migration_flag(self) -> bool:
+        """Check if rag_plugin_migration_needed flag is set."""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_metadata.Metadata).where(
+                persistence_metadata.Metadata.key == 'rag_plugin_migration_needed'
+            )
+        )
+        row = result.first()
+        return row is not None and row.value == 'true'
+
+    async def _set_migration_flag(self, value: str):
+        """Set rag_plugin_migration_needed flag."""
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_metadata.Metadata)
+            .where(persistence_metadata.Metadata.key == 'rag_plugin_migration_needed')
+            .values(value=value)
+        )
+
+    async def _table_exists(self, table_name: str) -> bool:
+        """Check if a table exists."""
+        if self.ap.persistence_mgr.db.name == 'postgresql':
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text(
+                    'SELECT EXISTS (SELECT FROM information_schema.tables WHERE table_name = :table_name);'
+                ).bindparams(table_name=table_name)
+            )
+            return result.scalar()
+        else:
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text(
+                    "SELECT name FROM sqlite_master WHERE type='table' AND name=:table_name;"
+                ).bindparams(table_name=table_name)
+            )
+            return result.first() is not None
+
+    async def _execute_rag_migration(self, task_context: taskmgr.TaskContext):
+        """Execute RAG migration: install langrag plugin and restore backup data."""
+        warnings = []
+
+        # Step 1: Install langrag plugin from marketplace
+        task_context.trace('Installing LangRAG plugin from marketplace...', action='install-plugin')
+        try:
+            install_info = {
+                'plugin_author': LANGRAG_PLUGIN_AUTHOR,
+                'plugin_name': LANGRAG_PLUGIN_NAME,
+                'plugin_version': 'latest',
+            }
+            await self.ap.plugin_connector.install_plugin(
+                PluginInstallSource.MARKETPLACE, install_info, task_context=task_context
+            )
+        except Exception as e:
+            # Plugin may already be installed
+            self.ap.logger.warning(f'LangRAG plugin install returned: {e}')
+            task_context.trace(f'Plugin install note: {e}')
+
+        # Step 2: Wait for the plugin to be available
+        task_context.trace('Waiting for LangRAG plugin to become available...', action='wait-plugin')
+        max_retries = 30
+        for i in range(max_retries):
+            try:
+                engines = await self.ap.plugin_connector.list_knowledge_engines()
+                engine_ids = [e.get('plugin_id') for e in engines]
+                if LANGRAG_PLUGIN_ID in engine_ids:
+                    task_context.trace('LangRAG plugin is ready.')
+                    break
+            except Exception:
+                pass
+            if i == max_retries - 1:
+                raise Exception(
+                    f'LangRAG plugin ({LANGRAG_PLUGIN_ID}) did not become available after {max_retries} retries'
+                )
+            await asyncio.sleep(2)
+
+        # Step 3: Restore internal knowledge bases from backup
+        task_context.trace('Restoring internal knowledge bases...', action='restore-internal')
+        if await self._table_exists('knowledge_bases_backup'):
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('SELECT * FROM knowledge_bases_backup;')
+            )
+            rows = result.fetchall()
+            columns = result.keys()
+
+            for row in rows:
+                row_dict = dict(zip(columns, row))
+                kb_uuid = row_dict.get('uuid')
+                name = row_dict.get('name', 'Untitled')
+                description = row_dict.get('description', '')
+                emoji = row_dict.get('emoji', '\U0001f4da')
+                embedding_model_uuid = row_dict.get('embedding_model_uuid', '')
+                top_k = row_dict.get('top_k', 5)
+                created_at = row_dict.get('created_at')
+                updated_at = row_dict.get('updated_at')
+
+                creation_settings = json.dumps({'embedding_model_uuid': embedding_model_uuid})
+                retrieval_settings = json.dumps({'top_k': top_k})
+
+                # Insert into knowledge_bases with the same UUID
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'INSERT INTO knowledge_bases '
+                        '(uuid, name, description, emoji, created_at, updated_at, '
+                        'knowledge_engine_plugin_id, collection_id, creation_settings, retrieval_settings) '
+                        'VALUES (:uuid, :name, :description, :emoji, :created_at, :updated_at, '
+                        ':plugin_id, :collection_id, :creation_settings, :retrieval_settings);'
+                    ).bindparams(
+                        uuid=kb_uuid,
+                        name=name,
+                        description=description,
+                        emoji=emoji,
+                        created_at=created_at,
+                        updated_at=updated_at,
+                        plugin_id=LANGRAG_PLUGIN_ID,
+                        collection_id=kb_uuid,
+                        creation_settings=creation_settings,
+                        retrieval_settings=retrieval_settings,
+                    )
+                )
+
+                # Notify langrag plugin to recognize this KB
+                try:
+                    config = {'embedding_model_uuid': embedding_model_uuid}
+                    await self.ap.plugin_connector.rag_on_kb_create(LANGRAG_PLUGIN_ID, kb_uuid, config)
+                    task_context.trace(f'Restored internal KB: {name} ({kb_uuid})')
+                except Exception as e:
+                    warning = f'Failed to notify plugin for KB {name} ({kb_uuid}): {e}'
+                    warnings.append(warning)
+                    task_context.trace(warning)
+
+            # Reload all knowledge bases into runtime
+            await self.ap.rag_mgr.load_knowledge_bases_from_db()
+
+        # Step 4: Restore external knowledge bases (read from preserved original table)
+        task_context.trace('Restoring external knowledge bases...', action='restore-external')
+        if await self._table_exists('external_knowledge_bases'):
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('SELECT * FROM external_knowledge_bases;')
+            )
+            rows = result.fetchall()
+            columns = result.keys()
+
+            # Get current available engines for matching
+            try:
+                engines = await self.ap.plugin_connector.list_knowledge_engines()
+                engine_id_set = {e.get('plugin_id') for e in engines}
+            except Exception:
+                engine_id_set = set()
+
+            for row in rows:
+                row_dict = dict(zip(columns, row))
+                kb_uuid = row_dict.get('uuid')
+                name = row_dict.get('name', 'Untitled')
+                description = row_dict.get('description', '')
+                emoji = row_dict.get('emoji', '\U0001f517')
+                plugin_author = row_dict.get('plugin_author', '')
+                plugin_name = row_dict.get('plugin_name', '')
+                retriever_config = row_dict.get('retriever_config', {})
+                created_at = row_dict.get('created_at')
+
+                external_plugin_id = f'{plugin_author}/{plugin_name}'
+
+                if external_plugin_id not in engine_id_set:
+                    warning = (
+                        f'External KB "{name}" ({kb_uuid}) uses plugin {external_plugin_id} '
+                        f'which is not available as a Knowledge Engine. Skipped.'
+                    )
+                    warnings.append(warning)
+                    task_context.trace(warning)
+                    continue
+
+                # Parse retriever_config
+                if isinstance(retriever_config, str):
+                    try:
+                        retriever_config = json.loads(retriever_config)
+                    except (json.JSONDecodeError, TypeError):
+                        retriever_config = {}
+
+                creation_settings = json.dumps(retriever_config)
+
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'INSERT INTO knowledge_bases '
+                        '(uuid, name, description, emoji, created_at, updated_at, '
+                        'knowledge_engine_plugin_id, collection_id, creation_settings, retrieval_settings) '
+                        'VALUES (:uuid, :name, :description, :emoji, :created_at, :updated_at, '
+                        ':plugin_id, :collection_id, :creation_settings, :retrieval_settings);'
+                    ).bindparams(
+                        uuid=kb_uuid,
+                        name=name,
+                        description=description,
+                        emoji=emoji,
+                        created_at=created_at,
+                        updated_at=created_at,
+                        plugin_id=external_plugin_id,
+                        collection_id=kb_uuid,
+                        creation_settings=creation_settings,
+                        retrieval_settings=json.dumps({}),
+                    )
+                )
+
+                try:
+                    await self.ap.plugin_connector.rag_on_kb_create(
+                        external_plugin_id, kb_uuid, retriever_config
+                    )
+                    task_context.trace(f'Restored external KB: {name} ({kb_uuid})')
+                except Exception as e:
+                    warning = f'Failed to notify plugin for external KB {name} ({kb_uuid}): {e}'
+                    warnings.append(warning)
+                    task_context.trace(warning)
+
+            # Reload again after external KBs
+            await self.ap.rag_mgr.load_knowledge_bases_from_db()
+
+        # Step 5: Clear migration flag
+        await self._set_migration_flag('false')
+        task_context.trace('RAG migration completed.', action='done')
+
+        if warnings:
+            task_context.trace(f'Completed with {len(warnings)} warning(s).')
+
+    async def initialize(self) -> None:
+        @self.route('/status', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            needed = await self._get_migration_flag()
+
+            internal_kb_count = 0
+            external_kb_count = 0
+
+            if needed:
+                if await self._table_exists('knowledge_bases_backup'):
+                    result = await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text('SELECT COUNT(*) FROM knowledge_bases_backup;')
+                    )
+                    internal_kb_count = result.scalar() or 0
+
+                if await self._table_exists('external_knowledge_bases'):
+                    result = await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text('SELECT COUNT(*) FROM external_knowledge_bases;')
+                    )
+                    external_kb_count = result.scalar() or 0
+
+            return self.success(
+                data={
+                    'needed': needed,
+                    'internal_kb_count': internal_kb_count,
+                    'external_kb_count': external_kb_count,
+                }
+            )
+
+        @self.route('/execute', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            needed = await self._get_migration_flag()
+            if not needed:
+                return self.http_status(400, -1, 'RAG migration is not needed')
+
+            ctx = taskmgr.TaskContext.new()
+            wrapper = self.ap.task_mgr.create_user_task(
+                self._execute_rag_migration(task_context=ctx),
+                kind='rag-migration',
+                name='rag-migration-execute',
+                label='Migrating knowledge bases to plugin architecture',
+                context=ctx,
+            )
+
+            return self.success(data={'task_id': wrapper.id})
+
+        @self.route('/dismiss', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            needed = await self._get_migration_flag()
+            if not needed:
+                return self.http_status(400, -1, 'RAG migration is not needed')
+
+            await self._set_migration_flag('false')
+            return self.success()

src/langbot/pkg/persistence/migrations/dbm020_knowledge_engine_plugin_architecture.py

@@ -9,20 +9,22 @@ class DBMigrateKnowledgeEnginePluginArchitecture(migration.DBMigration):
     """Migrate to unified Knowledge Engine plugin architecture.
 
     Changes:
-    - Add knowledge_engine_plugin_id, collection_id, creation_settings, retrieval_settings columns to knowledge_bases
+    - Backup existing knowledge_bases data to knowledge_bases_backup
-    - Migrate existing top_k values into retrieval_settings JSON
+    - Clear knowledge_bases table and add new plugin architecture columns
-    - Migrate existing embedding_model_uuid into creation_settings JSON
+    - Drop old columns (PostgreSQL only; SQLite leaves them unmapped)
-    - Drop embedding_model_uuid and top_k columns (PostgreSQL only; SQLite leaves them unmapped)
+    - Preserve external_knowledge_bases table as-is for future migration
-    - Drop external_knowledge_bases table (no longer needed; external KB data is not migrated)
+    - Set rag_plugin_migration_needed flag in metadata if old data exists
     """
 
     async def upgrade(self):
         """Upgrade"""
+        has_internal_data = await self._backup_knowledge_bases()
+        has_external_data = await self._check_external_knowledge_bases()
+        await self._clear_knowledge_bases()
         await self._add_columns_to_knowledge_bases()
-        await self._migrate_top_k_to_retrieval_settings()
-        await self._migrate_embedding_model_uuid_to_creation_settings()
         await self._drop_old_columns()
-        await self._drop_external_knowledge_bases_table()
+        if has_internal_data or has_external_data:
+            await self._set_migration_flag()
 
     async def _get_table_columns(self, table_name: str) -> list[str]:
         """Get column names from a table (works for both SQLite and PostgreSQL)."""
@@ -57,6 +59,56 @@ class DBMigrateKnowledgeEnginePluginArchitecture(migration.DBMigration):
             )
             return result.first() is not None
 
+    async def _backup_knowledge_bases(self) -> bool:
+        """Backup knowledge_bases data. Returns True if data was backed up."""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT COUNT(*) FROM knowledge_bases;')
+        )
+        count = result.scalar()
+        if count == 0:
+            return False
+
+        # Drop backup table if it already exists (from a previous failed migration)
+        if await self._table_exists('knowledge_bases_backup'):
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('DROP TABLE knowledge_bases_backup;')
+            )
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('CREATE TABLE knowledge_bases_backup AS SELECT * FROM knowledge_bases;')
+        )
+        self.ap.logger.info(
+            'Backed up %d knowledge base(s) to knowledge_bases_backup table.',
+            count,
+        )
+        return True
+
+    async def _check_external_knowledge_bases(self) -> bool:
+        """Check if external_knowledge_bases table exists and has data.
+
+        The table is preserved as-is (not dropped) for future migration.
+        """
+        if not await self._table_exists('external_knowledge_bases'):
+            return False
+
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT COUNT(*) FROM external_knowledge_bases;')
+        )
+        count = result.scalar()
+        if count > 0:
+            self.ap.logger.info(
+                'Found %d external knowledge base(s) in external_knowledge_bases table. '
+                'Table preserved for future migration.',
+                count,
+            )
+        return count > 0
+
+    async def _clear_knowledge_bases(self):
+        """Clear all rows from knowledge_bases table (preserve table structure)."""
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('DELETE FROM knowledge_bases;')
+        )
+
     async def _add_columns_to_knowledge_bases(self):
         """Add new RAG plugin architecture columns to knowledge_bases table."""
         columns = await self._get_table_columns('knowledge_bases')
@@ -74,73 +126,6 @@ class DBMigrateKnowledgeEnginePluginArchitecture(migration.DBMigration):
                     sqlalchemy.text(f'ALTER TABLE knowledge_bases ADD COLUMN {col_name} {col_type};')
                 )
 
-        # For existing knowledge bases without knowledge_engine_plugin_id,
-        # set collection_id = uuid (same default as new KBs)
-        await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.text('UPDATE knowledge_bases SET collection_id = uuid WHERE collection_id IS NULL;')
-        )
-
-    async def _migrate_top_k_to_retrieval_settings(self):
-        """Migrate existing top_k values into retrieval_settings JSON."""
-        columns = await self._get_table_columns('knowledge_bases')
-        if 'top_k' not in columns:
-            return
-
-        result = await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.text(
-                'SELECT uuid, top_k FROM knowledge_bases WHERE top_k IS NOT NULL AND retrieval_settings IS NULL;'
-            )
-        )
-        rows = result.fetchall()
-
-        for row in rows:
-            kb_uuid = row[0]
-            top_k = row[1]
-            retrieval_settings = json.dumps({'top_k': top_k})
-            await self.ap.persistence_mgr.execute_async(
-                sqlalchemy.text('UPDATE knowledge_bases SET retrieval_settings = :rs WHERE uuid = :uuid;').bindparams(
-                    rs=retrieval_settings, uuid=kb_uuid
-                )
-            )
-
-    async def _migrate_embedding_model_uuid_to_creation_settings(self):
-        """Migrate existing embedding_model_uuid into creation_settings JSON."""
-        columns = await self._get_table_columns('knowledge_bases')
-        if 'embedding_model_uuid' not in columns:
-            return
-
-        result = await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.text(
-                'SELECT uuid, embedding_model_uuid, creation_settings FROM knowledge_bases '
-                "WHERE embedding_model_uuid IS NOT NULL AND embedding_model_uuid != '';"
-            )
-        )
-        rows = result.fetchall()
-
-        for row in rows:
-            kb_uuid = row[0]
-            emb_uuid = row[1]
-            existing_settings = row[2]
-
-            if existing_settings and isinstance(existing_settings, str):
-                try:
-                    settings = json.loads(existing_settings)
-                except (json.JSONDecodeError, TypeError):
-                    settings = {}
-            elif isinstance(existing_settings, dict):
-                settings = existing_settings
-            else:
-                settings = {}
-
-            if 'embedding_model_uuid' not in settings:
-                settings['embedding_model_uuid'] = emb_uuid
-                new_settings = json.dumps(settings)
-                await self.ap.persistence_mgr.execute_async(
-                    sqlalchemy.text(
-                        'UPDATE knowledge_bases SET creation_settings = :cs WHERE uuid = :uuid;'
-                    ).bindparams(cs=new_settings, uuid=kb_uuid)
-                )
-
     async def _drop_old_columns(self):
         """Drop embedding_model_uuid and top_k columns (PostgreSQL only).
 
@@ -162,22 +147,26 @@ class DBMigrateKnowledgeEnginePluginArchitecture(migration.DBMigration):
                 sqlalchemy.text('ALTER TABLE knowledge_bases DROP COLUMN top_k;')
             )
 
-    async def _drop_external_knowledge_bases_table(self):
+    async def _set_migration_flag(self):
-        """Drop the external_knowledge_bases table if it exists."""
+        """Set rag_plugin_migration_needed flag in metadata table."""
-        if await self._table_exists('external_knowledge_bases'):
+        # Check if the key already exists
-            # Log existing external KBs before dropping, so users are aware of data loss
+        result = await self.ap.persistence_mgr.execute_async(
-            rows = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text("SELECT value FROM metadata WHERE key = 'rag_plugin_migration_needed';")
-                sqlalchemy.text('SELECT * FROM external_knowledge_bases;')
+        )
-            )
+        row = result.first()
-            existing = rows.fetchall()
+        if row is not None:
-            if existing:
+            await self.ap.persistence_mgr.execute_async(
-                self.ap.logger.warning(
+                sqlalchemy.text(
-                    'Dropping external_knowledge_bases table with %d existing record(s). '
+                    "UPDATE metadata SET value = 'true' WHERE key = 'rag_plugin_migration_needed';"
-                    'These external KB configurations will be removed: %s',
-                    len(existing),
-                    [dict(row._mapping) for row in existing],
                 )
-            await self.ap.persistence_mgr.execute_async(sqlalchemy.text('DROP TABLE external_knowledge_bases;'))
+            )
+        else:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text(
+                    "INSERT INTO metadata (key, value) VALUES ('rag_plugin_migration_needed', 'true');"
+                )
+            )
+        self.ap.logger.info('Set rag_plugin_migration_needed=true in metadata.')
 
     async def downgrade(self):
         """Downgrade"""

src/langbot/pkg/utils/constants.py

@@ -2,7 +2,7 @@ import langbot
 
 semantic_version = f'v{langbot.__version__}'
 
-required_database_version = 19
+required_database_version = 20
 """Tag the version of the database schema, used to check if the database needs to be migrated"""
 
 debug_mode = False

web/src/app/home/knowledge/components/kb-migration-dialog/KBMigrationDialog.tsx

@@ -0,0 +1,149 @@
+'use client';
+
+import { useState } from 'react';
+import {
+  Dialog,
+  DialogContent,
+  DialogHeader,
+  DialogTitle,
+  DialogDescription,
+  DialogFooter,
+} from '@/components/ui/dialog';
+import { Button } from '@/components/ui/button';
+import { useTranslation } from 'react-i18next';
+import { httpClient } from '@/app/infra/http/HttpClient';
+import { useAsyncTask, AsyncTaskStatus } from '@/hooks/useAsyncTask';
+import { toast } from 'sonner';
+import { Loader2 } from 'lucide-react';
+
+interface KBMigrationDialogProps {
+  open: boolean;
+  onOpenChange: (open: boolean) => void;
+  internalKbCount: number;
+  externalKbCount: number;
+  onMigrationComplete: () => void;
+}
+
+export default function KBMigrationDialog({
+  open,
+  onOpenChange,
+  internalKbCount,
+  externalKbCount,
+  onMigrationComplete,
+}: KBMigrationDialogProps) {
+  const { t } = useTranslation();
+  const [dismissing, setDismissing] = useState(false);
+
+  const asyncTask = useAsyncTask({
+    onSuccess: () => {
+      toast.success(t('knowledge.migration.success'));
+      onOpenChange(false);
+      onMigrationComplete();
+    },
+    onError: (error) => {
+      toast.error(`${t('knowledge.migration.error')}${error}`);
+    },
+  });
+
+  const handleStartMigration = async () => {
+    try {
+      const resp = await httpClient.executeRagMigration();
+      asyncTask.startTask(resp.task_id);
+    } catch {
+      toast.error(t('knowledge.migration.error'));
+    }
+  };
+
+  const handleDismiss = async () => {
+    setDismissing(true);
+    try {
+      await httpClient.dismissRagMigration();
+      onOpenChange(false);
+    } catch {
+      toast.error(t('knowledge.migration.dismissError'));
+    } finally {
+      setDismissing(false);
+    }
+  };
+
+  const isRunning = asyncTask.status === AsyncTaskStatus.RUNNING;
+  const isError = asyncTask.status === AsyncTaskStatus.ERROR;
+  const totalCount = internalKbCount + externalKbCount;
+
+  return (
+    <Dialog
+      open={open}
+      onOpenChange={(v) => {
+        if (!isRunning) onOpenChange(v);
+      }}
+    >
+      <DialogContent className="sm:max-w-[500px]">
+        <DialogHeader>
+          <DialogTitle>{t('knowledge.migration.title')}</DialogTitle>
+          <DialogDescription>
+            {t('knowledge.migration.description')}
+          </DialogDescription>
+        </DialogHeader>
+
+        <div className="py-4 space-y-3">
+          {!isRunning && !isError && (
+            <>
+              <p className="text-sm text-muted-foreground">
+                {t('knowledge.migration.detected', {
+                  total: totalCount,
+                  internal: internalKbCount,
+                  external: externalKbCount,
+                })}
+              </p>
+              <p className="text-sm text-muted-foreground">
+                {t('knowledge.migration.installHint')}
+              </p>
+            </>
+          )}
+
+          {isRunning && (
+            <div className="flex items-center gap-3">
+              <Loader2 className="h-5 w-5 animate-spin text-primary" />
+              <p className="text-sm">{t('knowledge.migration.running')}</p>
+            </div>
+          )}
+
+          {isError && (
+            <div className="space-y-2">
+              <p className="text-sm text-destructive">
+                {t('knowledge.migration.error')}
+              </p>
+              {asyncTask.error && (
+                <p className="text-xs text-muted-foreground bg-muted p-2 rounded">
+                  {asyncTask.error}
+                </p>
+              )}
+            </div>
+          )}
+        </div>
+
+        <DialogFooter>
+          {!isRunning && (
+            <Button
+              variant="outline"
+              onClick={handleDismiss}
+              disabled={dismissing}
+            >
+              {t('knowledge.migration.dismiss')}
+            </Button>
+          )}
+          {!isRunning && !isError && (
+            <Button onClick={handleStartMigration}>
+              {t('knowledge.migration.start')}
+            </Button>
+          )}
+          {isError && (
+            <Button onClick={handleStartMigration}>
+              {t('knowledge.migration.retry')}
+            </Button>
+          )}
+        </DialogFooter>
+      </DialogContent>
+    </Dialog>
+  );
+}

web/src/app/home/knowledge/page.tsx

@@ -7,6 +7,7 @@ import { useEffect, useState } from 'react';
 import { KnowledgeBaseVO } from '@/app/home/knowledge/components/kb-card/KBCardVO';
 import KBCard from '@/app/home/knowledge/components/kb-card/KBCard';
 import KBDetailDialog from '@/app/home/knowledge/KBDetailDialog';
+import KBMigrationDialog from '@/app/home/knowledge/components/kb-migration-dialog/KBMigrationDialog';
 import { httpClient } from '@/app/infra/http/HttpClient';
 import { KnowledgeBase } from '@/app/infra/entities/api';
 
@@ -18,10 +19,29 @@ export default function KnowledgePage() {
   const [selectedKbId, setSelectedKbId] = useState<string>('');
   const [detailDialogOpen, setDetailDialogOpen] = useState(false);
 
+  // Migration dialog state
+  const [migrationDialogOpen, setMigrationDialogOpen] = useState(false);
+  const [migrationInternalCount, setMigrationInternalCount] = useState(0);
+  const [migrationExternalCount, setMigrationExternalCount] = useState(0);
+
   useEffect(() => {
     getKnowledgeBaseList();
+    checkMigrationStatus();
   }, []);
 
+  async function checkMigrationStatus() {
+    try {
+      const resp = await httpClient.getRagMigrationStatus();
+      if (resp.needed) {
+        setMigrationInternalCount(resp.internal_kb_count);
+        setMigrationExternalCount(resp.external_kb_count);
+        setMigrationDialogOpen(true);
+      }
+    } catch {
+      // Silently ignore - migration check is non-critical
+    }
+  }
+
   async function getKnowledgeBaseList() {
     const resp = await httpClient.getKnowledgeBases();
 
@@ -85,8 +105,20 @@ export default function KnowledgePage() {
     getKnowledgeBaseList();
   };
 
+  const handleMigrationComplete = () => {
+    getKnowledgeBaseList();
+  };
+
   return (
     <div>
+      <KBMigrationDialog
+        open={migrationDialogOpen}
+        onOpenChange={setMigrationDialogOpen}
+        internalKbCount={migrationInternalCount}
+        externalKbCount={migrationExternalCount}
+        onMigrationComplete={handleMigrationComplete}
+      />
+
       <KBDetailDialog
         open={detailDialogOpen}
         onOpenChange={setDetailDialogOpen}

web/src/app/infra/entities/api/index.ts

@@ -262,6 +262,12 @@ export interface ApiRespSystemInfo {
   limitation: SystemLimitation;
 }
 
+export interface RagMigrationStatusResp {
+  needed: boolean;
+  internal_kb_count: number;
+  external_kb_count: number;
+}
+
 export interface ApiRespPluginSystemStatus {
   is_enable: boolean;
   is_connected: boolean;

web/src/app/infra/http/BackendClient.ts

@@ -40,6 +40,7 @@ import {
   ModelProvider,
   ApiRespKnowledgeEngines,
   ApiRespParsers,
+  RagMigrationStatusResp,
 } from '@/app/infra/entities/api';
 import { Plugin } from '@/app/infra/entities/plugin';
 import { GetBotLogsRequest } from '@/app/infra/http/requestParam/bots/GetBotLogsRequest';
@@ -710,6 +711,19 @@ export class BackendClient extends BaseHttpClient {
     return this.get('/api/v1/system/status/plugin-system');
   }
 
+  // ============ RAG Migration API ============
+  public getRagMigrationStatus(): Promise<RagMigrationStatusResp> {
+    return this.get('/api/v1/knowledge/migration/status');
+  }
+
+  public executeRagMigration(): Promise<AsyncTaskCreatedResp> {
+    return this.post('/api/v1/knowledge/migration/execute');
+  }
+
+  public dismissRagMigration(): Promise<object> {
+    return this.post('/api/v1/knowledge/migration/dismiss');
+  }
+
   public getPluginDebugInfo(): Promise<{
     debug_url: string;
     plugin_debug_key: string;

web/src/i18n/locales/en-US.ts

@@ -773,6 +773,22 @@ const enUS = {
     retrieverConfiguration: 'Retriever Configuration',
     retrieverInstallInfo: 'You can install Knowledge Retriever plugins from',
     retrieverMarketLink: 'here',
+    migration: {
+      title: 'Knowledge Base Migration',
+      description:
+        'Legacy knowledge base data detected. Migration to the new plugin-based RAG architecture is required.',
+      detected:
+        'Found {{total}} knowledge base(s) to migrate ({{internal}} internal, {{external}} external).',
+      installHint:
+        'Migration will automatically install the LangRAG plugin and restore your knowledge base data. Documents and vector data will be preserved.',
+      start: 'Migrate Now',
+      dismiss: 'Skip for Now',
+      running: 'Migrating knowledge bases, please wait...',
+      success: 'Knowledge base migration completed',
+      error: 'Knowledge base migration failed: ',
+      dismissError: 'Operation failed',
+      retry: 'Retry',
+    },
   },
   register: {
     title: 'Initialize LangBot 👋',

web/src/i18n/locales/ja-JP.ts

@@ -762,6 +762,22 @@ const jaJP = {
     retrieverConfiguration: '検索器設定',
     retrieverInstallInfo: 'ナレッジ検索器プラグインは',
     retrieverMarketLink: 'こちらからインストールできます',
+    migration: {
+      title: 'ナレッジベースの移行',
+      description:
+        '旧バージョンのナレッジベースデータが検出されました。新しいプラグインベースのRAGアーキテクチャへの移行が必要です。',
+      detected:
+        '移行が必要なナレッジベースが{{total}}件見つかりました（内部{{internal}}件、外部{{external}}件）。',
+      installHint:
+        '移行により LangRAG プラグインが自動的にインストールされ、ナレッジベースデータが復元されます。ドキュメントとベクトルデータは保持されます。',
+      start: '今すぐ移行',
+      dismiss: '後で',
+      running: 'ナレッジベースを移行中です。しばらくお待ちください...',
+      success: 'ナレッジベースの移行が完了しました',
+      error: 'ナレッジベースの移行に失敗しました：',
+      dismissError: '操作に失敗しました',
+      retry: 'リトライ',
+    },
   },
   register: {
     title: 'LangBot を初期化 👋',

web/src/i18n/locales/zh-Hans.ts

@@ -742,6 +742,21 @@ const zhHans = {
     retrieverConfiguration: '检索器配置',
     retrieverInstallInfo: '您可以从',
     retrieverMarketLink: '此处安装知识检索器插件',
+    migration: {
+      title: '知识库迁移',
+      description: '检测到旧版知识库数据，需要迁移到新的插件化 RAG 架构。',
+      detected:
+        '共检测到 {{total}} 个知识库需要迁移（{{internal}} 个内置知识库，{{external}} 个外部知识库）。',
+      installHint:
+        '迁移将自动安装 LangRAG 插件并恢复您的知识库数据，文档和向量数据将被保留。',
+      start: '立即迁移',
+      dismiss: '暂不迁移',
+      running: '正在迁移知识库，请稍候...',
+      success: '知识库迁移完成',
+      error: '知识库迁移失败：',
+      dismissError: '操作失败',
+      retry: '重试',
+    },
   },
   register: {
     title: '初始化 LangBot 👋',

web/src/i18n/locales/zh-Hant.ts

@@ -722,6 +722,21 @@ const zhHant = {
     retrieverConfiguration: '檢索器配置',
     retrieverInstallInfo: '您可以從',
     retrieverMarketLink: '此處安裝知識檢索器插件',
+    migration: {
+      title: '知識庫遷移',
+      description: '檢測到舊版知識庫資料，需要遷移到新的插件化 RAG 架構。',
+      detected:
+        '共檢測到 {{total}} 個知識庫需要遷移（{{internal}} 個內建知識庫，{{external}} 個外部知識庫）。',
+      installHint:
+        '遷移將自動安裝 LangRAG 插件並恢復您的知識庫資料，文件和向量資料將被保留。',
+      start: '立即遷移',
+      dismiss: '暫不遷移',
+      running: '正在遷移知識庫，請稍候...',
+      success: '知識庫遷移完成',
+      error: '知識庫遷移失敗：',
+      dismissError: '操作失敗',
+      retry: '重試',
+    },
   },
   register: {
     title: '初始化 LangBot 👋',