feat(ee): turbopuffer ai vector search driver (#2402)

* feat(ai): add AI_VECTOR_DRIVER and turbopuffer configuration

* feat(ai): carry workspace and target space ids on vector lifecycle events

* feat(ai): add vector driver interface and turbopuffer request helpers

* feat(ai): add pgvector driver behind the vector driver interface

* refactor(ai): route vector reads and writes through the vector driver

* feat(ai): add turbopuffer vector driver

* feat(ai): rebuild turbopuffer namespaces when the embedding model changes

* feat(ai): warm the vector namespace cache on session start

* fix(ai): harden turbopuffer misconfiguration and reset failure paths

* fix(ai): collapse blank-line runs in extracted page text

* fix(ai): skip full re-embed when ai search is re-enabled within the delete grace window

* sync

* fix(ai): store real embedding dimensions instead of serialized vector length

* fix(ai): filter search hits by the page's current space at query time

* fix(ai): retry the page moved-to-space vector patch job

* sync

* feat(ai): pre-warm the vector namespace

* fix(ai): pass AI_VECTOR_DRIVER through the client build config

apps/server/package.json

@@ -66,6 +66,7 @@
     "@nestjs/websockets": "11.1.28",
     "@node-saml/passport-saml": "5.1.0",
     "@socket.io/redis-adapter": "8.3.0",
+    "@turbopuffer/turbopuffer": "^2.8.0",
     "ai": "6.0.134",
     "ai-sdk-ollama": "3.8.1",
     "bcrypt": "6.0.0",

apps/server/src/collaboration/collaboration.util.ts

@@ -57,6 +57,7 @@ import {
   JSONContent,
 } from '@tiptap/core';
 import { generateHTML, generateJSON } from '../common/helpers/prosemirror/html';
+import { collapseBlankLines } from '../common/helpers';
 // @tiptap/html library works best for generating prosemirror json state but not HTML
 // see: https://github.com/ueberdosis/tiptap/issues/5352
 // see:https://github.com/ueberdosis/tiptap/issues/4089
@@ -146,7 +147,7 @@ export function htmlToJson(html: string) {
 }
 
 export function jsonToText(tiptapJson: JSONContent) {
-  return generateText(tiptapJson, tiptapExtensions);
+  return collapseBlankLines(generateText(tiptapJson, tiptapExtensions));
 }
 
 export function jsonToNode(tiptapJson: JSONContent) {

apps/server/src/common/helpers/index.ts

@@ -1,4 +1,5 @@
 export * from './utils';
+export * from './text.utils';
 export * from './nanoid.utils';
 export * from './file.helper';
 export * from './constants';

apps/server/src/common/helpers/text.utils.spec.ts

@@ -0,0 +1,14 @@
+import { collapseBlankLines } from './text.utils';
+
+describe('collapseBlankLines', () => {
+  it.each([
+    ['a\n\n\n\nb', 'a\n\nb'],
+    ['a\n\nb', 'a\n\nb'],
+    ['a\nb', 'a\nb'],
+    ['\n\n\n\na\n\n\n', '\n\na\n\n'],
+    ['no newlines', 'no newlines'],
+    ['', ''],
+  ])('collapses %j to %j', (input, expected) => {
+    expect(collapseBlankLines(input)).toBe(expected);
+  });
+});

apps/server/src/common/helpers/text.utils.ts

@@ -0,0 +1,3 @@
+export function collapseBlankLines(text: string): string {
+  return text.replace(/\n{2,}/g, '\n\n');
+}

apps/server/src/core/page/services/page.service.ts

@@ -496,10 +496,21 @@ export class PageService {
           },
         );
 
-        await this.aiQueue.add(QueueJob.PAGE_MOVED_TO_SPACE, {
-          pageIds: pageIdsToMove,
-          workspaceId: rootPage.workspaceId,
-        });
+        await this.aiQueue.add(
+          QueueJob.PAGE_MOVED_TO_SPACE,
+          {
+            pageIds: pageIdsToMove,
+            spaceId,
+            workspaceId: rootPage.workspaceId,
+          },
+          {
+            attempts: 2,
+            backoff: {
+              type: 'fixed',
+              delay: 2 * 60 * 1000,
+            },
+          },
+        );
       }
     });
 

apps/server/src/database/listeners/space.listener.ts

@@ -8,6 +8,7 @@ import { EnvironmentService } from '../../integrations/environment/environment.s
 
 export class SpaceEvent {
   spaceId: string;
+  workspaceId: string;
 }
 
 @Injectable()
@@ -22,12 +23,12 @@ export class SpaceListener {
 
   @OnEvent(EventName.SPACE_DELETED)
   async handleSpaceDeleted(event: SpaceEvent) {
-    const { spaceId } = event;
+    const { spaceId, workspaceId } = event;
     if (this.isTypesense()) {
       await this.searchQueue.add(QueueJob.SPACE_DELETED, { spaceId });
     }
 
-    await this.aiQueue.add(QueueJob.SPACE_DELETED, { spaceId });
+    await this.aiQueue.add(QueueJob.SPACE_DELETED, { spaceId, workspaceId });
   }
 
   isTypesense(): boolean {

apps/server/src/database/repos/space/space.repo.ts

@@ -230,6 +230,7 @@ export class SpaceRepo {
 
     this.eventEmitter.emit(EventName.SPACE_DELETED, {
       spaceId,
+      workspaceId,
     });
   }
 }

apps/server/src/database/repos/workspace/workspace.repo.ts

@@ -211,6 +211,24 @@ export class WorkspaceRepo {
       .executeTakeFirst();
   }
 
+  async updateAiEmbeddingFingerprint(
+    workspaceId: string,
+    fingerprint: { driver: string; model: string; dimensions: number },
+    trx?: KyselyTransaction,
+  ) {
+    const db = dbOrTx(this.db, trx);
+    return db
+      .updateTable('workspaces')
+      .set({
+        settings: sql`COALESCE(settings, '{}'::jsonb)
+                || jsonb_build_object('ai', COALESCE(settings->'ai', '{}'::jsonb)
+                || jsonb_build_object('embedding', ${JSON.stringify(fingerprint)}::text::jsonb))`,
+        updatedAt: new Date(),
+      })
+      .where('id', '=', workspaceId)
+      .execute();
+  }
+
   async updateSharingSettings(
     workspaceId: string,
     prefKey: string,

apps/server/src/integrations/environment/environment.service.ts

@@ -310,6 +310,31 @@ export class EnvironmentService {
     return val === 'true';
   }
 
+  getAiVectorDriver(): string {
+    return this.configService
+      .get<string>('AI_VECTOR_DRIVER', 'pgvector')
+      .toLowerCase();
+  }
+
+  getTurbopufferApiKey(): string {
+    return this.configService.get<string>('TURBOPUFFER_API_KEY');
+  }
+
+  getTurbopufferRegion(): string {
+    return this.configService.get<string>('TURBOPUFFER_REGION');
+  }
+
+  getTurbopufferBaseUrl(): string {
+    return this.configService.get<string>('TURBOPUFFER_BASE_URL');
+  }
+
+  getTurbopufferNamespacePrefix(): string {
+    return this.configService.get<string>(
+      'TURBOPUFFER_NAMESPACE_PREFIX',
+      'docmost',
+    );
+  }
+
   getOpenAiApiKey(): string {
     return this.configService.get<string>('OPENAI_API_KEY');
   }

apps/server/src/integrations/environment/environment.validation.ts

@@ -5,6 +5,7 @@ import {
   IsOptional,
   IsString,
   IsUrl,
+  Matches,
   MinLength,
   ValidateIf,
   validateSync,
@@ -108,6 +109,41 @@ export class EnvironmentVariables {
   @IsString()
   AI_DRIVER: string;
 
+  @IsOptional()
+  @ValidateIf((obj) => obj.AI_VECTOR_DRIVER)
+  @IsIn(['pgvector', 'turbopuffer'])
+  @IsString()
+  AI_VECTOR_DRIVER: string;
+
+  @ValidateIf((obj) => obj.AI_VECTOR_DRIVER === 'turbopuffer')
+  @IsNotEmpty()
+  @IsString()
+  TURBOPUFFER_API_KEY: string;
+
+  @ValidateIf(
+    (obj) =>
+      obj.AI_VECTOR_DRIVER === 'turbopuffer' && !obj.TURBOPUFFER_BASE_URL,
+  )
+  @IsNotEmpty({
+    message:
+      'TURBOPUFFER_REGION is required when AI_VECTOR_DRIVER is turbopuffer, unless TURBOPUFFER_BASE_URL is set',
+  })
+  @IsString()
+  TURBOPUFFER_REGION: string;
+
+  @IsOptional()
+  @ValidateIf((obj) => obj.TURBOPUFFER_BASE_URL != '' && obj.TURBOPUFFER_BASE_URL != null)
+  @IsUrl({ protocols: ['http', 'https'], require_tld: false })
+  TURBOPUFFER_BASE_URL: string;
+
+  @IsOptional()
+  @IsString()
+  @Matches(/^[A-Za-z0-9\-_.]{1,90}$/, {
+    message:
+      'TURBOPUFFER_NAMESPACE_PREFIX may only contain letters, digits, dot, dash, underscore (max 90 chars)',
+  })
+  TURBOPUFFER_NAMESPACE_PREFIX: string;
+
   @IsOptional()
   @IsString()
   AI_EMBEDDING_MODEL: string;

apps/server/src/integrations/queue/constants/queue.constants.ts

@@ -61,6 +61,7 @@ export enum QueueJob {
   WORKSPACE_DELETED = 'workspace-deleted',
   WORKSPACE_CREATE_EMBEDDINGS = 'workspace-create-embeddings',
   WORKSPACE_DELETE_EMBEDDINGS = 'workspace-delete-embeddings',
+  WORKSPACE_RESET_EMBEDDINGS = 'workspace-reset-embeddings',
 
   GENERATE_PAGE_EMBEDDINGS = 'generate-page-embeddings',
   DELETE_PAGE_EMBEDDINGS = 'delete-page-embeddings',

apps/server/src/integrations/static/static.module.ts

@@ -49,6 +49,10 @@ export class StaticModule implements OnModuleInit {
           : undefined,
         POSTHOG_HOST: this.environmentService.getPostHogHost(),
         POSTHOG_KEY: this.environmentService.getPostHogKey(),
+        AI_VECTOR_DRIVER:
+          this.environmentService.getAiVectorDriver() === 'turbopuffer'
+            ? 'turbopuffer'
+            : undefined,
       };
 
       const windowScriptContent = `<script>window.CONFIG=${JSON.stringify(configString)};</script>`;