feat: Store large html content in the asset db

17 files changed, 2383 insertions, 18 deletions

diff --git a/apps/web/lib/attachments.tsx b/apps/web/lib/attachments.tsx
index 62848d33..ce34b295 100644
--- a/apps/web/lib/attachments.tsx
+++ b/apps/web/lib/attachments.tsx
@@ -1,4 +1,11 @@
-import { Archive, Camera, Image, Paperclip, Video } from "lucide-react";
+import {
+  Archive,
+  Camera,
+  FileCode,
+  Image,
+  Paperclip,
+  Video,
+} from "lucide-react";
 
 import { ZAssetType } from "@karakeep/shared/types/bookmarks";
 
@@ -10,5 +17,6 @@ export const ASSET_TYPE_TO_ICON: Record<ZAssetType, React.ReactNode> = {
   bannerImage: <Image className="size-4" />,
   video: <Video className="size-4" />,
   bookmarkAsset: <Paperclip className="size-4" />,
+  linkHtmlContent: <FileCode className="size-4" />,
   unknown: <Paperclip className="size-4" />,
 };
diff --git a/apps/workers/workerUtils.ts b/apps/workers/workerUtils.ts
index d41df578..3eaf5b4b 100644
--- a/apps/workers/workerUtils.ts
+++ b/apps/workers/workerUtils.ts
@@ -46,5 +46,8 @@ export async function getBookmarkDetails(bookmarkId: string) {
     precrawledArchiveAssetId: bookmark.assets

       .filter((a) => a.assetType == AssetTypes.LINK_PRECRAWLED_ARCHIVE)

       .at(-1)?.id,

+    contentAssetId: bookmark.assets.find(

+      (a) => a.assetType == AssetTypes.LINK_HTML_CONTENT,

+    )?.id,

   };

 }

diff --git a/apps/workers/workers/crawlerWorker.ts b/apps/workers/workers/crawlerWorker.ts
index 10106a3b..428ec0f5 100644
--- a/apps/workers/workers/crawlerWorker.ts
+++ b/apps/workers/workers/crawlerWorker.ts
@@ -696,6 +696,75 @@ async function handleAsAssetBookmark(
   });
 }
 
+const HTML_CONTENT_SIZE_THRESHOLD = 50 * 1024; // 50KB
+
+type StoreHtmlResult =
+  | { result: "stored"; assetId: string; size: number }
+  | { result: "store_inline" }
+  | { result: "not_stored" };
+
+async function storeHtmlContent(
+  htmlContent: string | undefined,
+  userId: string,
+  jobId: string,
+): Promise<StoreHtmlResult> {
+  if (!htmlContent) {
+    return { result: "not_stored" };
+  }
+
+  const contentBuffer = Buffer.from(htmlContent, "utf8");
+  const contentSize = contentBuffer.byteLength;
+
+  // Only store in assets if content is >= 50KB
+  if (contentSize < HTML_CONTENT_SIZE_THRESHOLD) {
+    logger.info(
+      `[Crawler][${jobId}] HTML content size (${contentSize} bytes) is below threshold, storing inline`,
+    );
+    return { result: "store_inline" };
+  }
+
+  try {
+    const quotaApproved = await checkStorageQuota(
+      db,
+      userId,
+      contentBuffer.byteLength,
+    );
+    const assetId = newAssetId();
+
+    await saveAsset({
+      userId,
+      assetId,
+      asset: contentBuffer,
+      metadata: {
+        contentType: ASSET_TYPES.TEXT_HTML,
+        fileName: null,
+      },
+      quotaApproved,
+    });
+
+    logger.info(
+      `[Crawler][${jobId}] Stored large HTML content (${contentSize} bytes) as asset: ${assetId}`,
+    );
+
+    return {
+      result: "stored",
+      assetId,
+      size: contentSize,
+    };
+  } catch (error) {
+    if (error instanceof StorageQuotaError) {
+      logger.warn(
+        `[Crawler][${jobId}] Skipping HTML content storage due to quota exceeded: ${error.message}`,
+      );
+      return { result: "not_stored" };
+    }
+    logger.error(
+      `[Crawler][${jobId}] Failed to store HTML content as asset: ${error}`,
+    );
+    throw error;
+  }
+}
+
 async function crawlAndParseUrl(
   url: string,
   userId: string,
@@ -704,6 +773,7 @@ async function crawlAndParseUrl(
   oldScreenshotAssetId: string | undefined,
   oldImageAssetId: string | undefined,
   oldFullPageArchiveAssetId: string | undefined,
+  oldContentAssetId: string | undefined,
   precrawledArchiveAssetId: string | undefined,
   archiveFullPage: boolean,
   abortSignal: AbortSignal,
@@ -741,6 +811,12 @@ async function crawlAndParseUrl(
     extractReadableContent(htmlContent, browserUrl, jobId),
     storeScreenshot(screenshot, userId, jobId),
   ]);
+
+  const htmlContentAssetInfo = await storeHtmlContent(
+    readableContent?.content,
+    userId,
+    jobId,
+  );
   abortSignal.throwIfAborted();
   let imageAssetInfo: DBAssetType | null = null;
   if (meta.image) {
@@ -784,8 +860,14 @@ async function crawlAndParseUrl(
         // Don't store data URIs as they're not valid URLs and are usually quite large
         imageUrl: meta.image?.startsWith("data:") ? null : meta.image,
         favicon: meta.logo,
-        content: readableContent?.textContent,
-        htmlContent: readableContent?.content,
+        htmlContent:
+          htmlContentAssetInfo.result === "store_inline"
+            ? readableContent?.content
+            : null,
+        contentAssetId:
+          htmlContentAssetInfo.result === "stored"
+            ? htmlContentAssetInfo.assetId
+            : null,
         crawledAt: new Date(),
         crawlStatusCode: statusCode,
         author: meta.author,
@@ -813,12 +895,31 @@ async function crawlAndParseUrl(
     if (imageAssetInfo) {
       await updateAsset(oldImageAssetId, imageAssetInfo, txn);
     }
+    if (htmlContentAssetInfo.result === "stored") {
+      await updateAsset(
+        oldContentAssetId,
+        {
+          id: htmlContentAssetInfo.assetId,
+          bookmarkId,
+          userId,
+          assetType: AssetTypes.LINK_HTML_CONTENT,
+          contentType: ASSET_TYPES.TEXT_HTML,
+          size: htmlContentAssetInfo.size,
+          fileName: null,
+        },
+        txn,
+      );
+    } else if (oldContentAssetId) {
+      // Unlink the old content asset
+      await txn.delete(assets).where(eq(assets.id, oldContentAssetId));
+    }
   });
 
   // Delete the old assets if any
   await Promise.all([
     silentDeleteAsset(userId, oldScreenshotAssetId),
     silentDeleteAsset(userId, oldImageAssetId),
+    silentDeleteAsset(userId, oldContentAssetId),
   ]);
 
   return async () => {
@@ -857,7 +958,7 @@ async function crawlAndParseUrl(
           );
         });
         if (oldFullPageArchiveAssetId) {
-          silentDeleteAsset(userId, oldFullPageArchiveAssetId);
+          await silentDeleteAsset(userId, oldFullPageArchiveAssetId);
         }
       }
     }
@@ -882,6 +983,7 @@ async function runCrawler(job: DequeuedJob<ZCrawlLinkRequest>) {
     screenshotAssetId: oldScreenshotAssetId,
     imageAssetId: oldImageAssetId,
     fullPageArchiveAssetId: oldFullPageArchiveAssetId,
+    contentAssetId: oldContentAssetId,
     precrawledArchiveAssetId,
   } = await getBookmarkDetails(bookmarkId);
 
@@ -926,6 +1028,7 @@ async function runCrawler(job: DequeuedJob<ZCrawlLinkRequest>) {
       oldScreenshotAssetId,
       oldImageAssetId,
       oldFullPageArchiveAssetId,
+      oldContentAssetId,
       precrawledArchiveAssetId,
       archiveFullPage,
       job.abortSignal,
diff --git a/apps/workers/workers/inference/summarize.ts b/apps/workers/workers/inference/summarize.ts
index a832fe0a..2d9c8ef7 100644
--- a/apps/workers/workers/inference/summarize.ts
+++ b/apps/workers/workers/inference/summarize.ts
@@ -9,6 +9,7 @@ import logger from "@karakeep/shared/logger";
 import { buildSummaryPrompt } from "@karakeep/shared/prompts";
 import { triggerSearchReindex, ZOpenAIRequest } from "@karakeep/shared/queues";
 import { BookmarkTypes } from "@karakeep/shared/types/bookmarks";
+import { Bookmark } from "@karakeep/trpc/models/bookmarks";
 
 async function fetchBookmarkDetailsForSummary(bookmarkId: string) {
   const bookmark = await db.query.bookmarks.findFirst({
@@ -19,7 +20,8 @@ async function fetchBookmarkDetailsForSummary(bookmarkId: string) {
         columns: {
           title: true,
           description: true,
-          content: true,
+          htmlContent: true,
+          contentAssetId: true,
           publisher: true,
           author: true,
           url: true,
@@ -57,10 +59,16 @@ export async function runSummarization(
   let textToSummarize = "";
   if (bookmarkData.type === BookmarkTypes.LINK && bookmarkData.link) {
     const link = bookmarkData.link;
+
+    // Extract plain text content from HTML for summarization
+    let content =
+      (await Bookmark.getBookmarkPlainTextContent(link, bookmarkData.userId)) ??
+      "";
+
     textToSummarize = `
 Title: ${link.title ?? ""}
 Description: ${link.description ?? ""}
-Content: ${link.content ?? ""}
+Content: ${content}
 Publisher: ${link.publisher ?? ""}
 Author: ${link.author ?? ""}
 URL: ${link.url ?? ""}
diff --git a/apps/workers/workers/inference/tagging.ts b/apps/workers/workers/inference/tagging.ts
index d666b3d9..271eea4b 100644
--- a/apps/workers/workers/inference/tagging.ts
+++ b/apps/workers/workers/inference/tagging.ts
@@ -21,6 +21,7 @@ import {
   triggerSearchReindex,
   triggerWebhook,
 } from "@karakeep/shared/queues";
+import { Bookmark } from "@karakeep/trpc/models/bookmarks";
 
 const openAIResponseSchema = z.object({
   tags: z.array(z.string()),
@@ -77,13 +78,17 @@ async function buildPrompt(
 ) {
   const prompts = await fetchCustomPrompts(bookmark.userId, "text");
   if (bookmark.link) {
-    if (!bookmark.link.description && !bookmark.link.content) {
+    let content =
+      (await Bookmark.getBookmarkPlainTextContent(
+        bookmark.link,
+        bookmark.userId,
+      )) ?? "";
+
+    if (!bookmark.link.description && !content) {
       throw new Error(
         `No content found for link "${bookmark.id}". Skipping ...`,
       );
     }
-
-    const content = bookmark.link.content;
     return buildTextPrompt(
       serverConfig.inference.inferredTagLang,
       prompts,
diff --git a/apps/workers/workers/searchWorker.ts b/apps/workers/workers/searchWorker.ts
index 13243152..177ca0db 100644
--- a/apps/workers/workers/searchWorker.ts
+++ b/apps/workers/workers/searchWorker.ts
@@ -11,6 +11,7 @@ import {
   zSearchIndexingRequestSchema,
 } from "@karakeep/shared/queues";
 import { getSearchIdxClient } from "@karakeep/shared/search";
+import { Bookmark } from "@karakeep/trpc/models/bookmarks";
 
 export class SearchIndexingWorker {
   static build() {
@@ -75,6 +76,12 @@ async function runIndex(
     throw new Error(`Bookmark ${bookmarkId} not found`);
   }
 
+  // Extract plain text content from HTML for search indexing
+  const content = await Bookmark.getBookmarkPlainTextContent(
+    bookmark.link,
+    bookmark.userId,
+  );
+
   const task = await searchClient.addDocuments(
     [
       {
@@ -85,7 +92,7 @@ async function runIndex(
               url: bookmark.link.url,
               linkTitle: bookmark.link.title,
               description: bookmark.link.description,
-              content: bookmark.link.content,
+              content,
               publisher: bookmark.link.publisher,
               author: bookmark.link.author,
               datePublished: bookmark.link.datePublished,
diff --git a/packages/db/drizzle/0055_content_asset_id.sql b/packages/db/drizzle/0055_content_asset_id.sql
new file mode 100644
index 00000000..533792d3
--- /dev/null
+++ b/packages/db/drizzle/0055_content_asset_id.sql
@@ -0,0 +1,2 @@
+ALTER TABLE `bookmarkLinks` ADD `contentAssetId` text;--> statement-breakpoint
+ALTER TABLE `bookmarkLinks` DROP COLUMN `content`;
\ No newline at end of file
diff --git a/packages/db/drizzle/meta/0055_snapshot.json b/packages/db/drizzle/meta/0055_snapshot.json
new file mode 100644
index 00000000..024aba47
--- /dev/null
+++ b/packages/db/drizzle/meta/0055_snapshot.json
@@ -0,0 +1,2051 @@
+{
+  "version": "6",
+  "dialect": "sqlite",
+  "id": "a7674152-1484-4144-9faa-2f4597ba619e",
+  "prevId": "ac5b67e5-b9a8-413b-bba7-80280d8ebfc8",
+  "tables": {
+    "account": {
+      "name": "account",
+      "columns": {
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "type": {
+          "name": "type",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "provider": {
+          "name": "provider",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "providerAccountId": {
+          "name": "providerAccountId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "refresh_token": {
+          "name": "refresh_token",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "access_token": {
+          "name": "access_token",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "expires_at": {
+          "name": "expires_at",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "token_type": {
+          "name": "token_type",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "scope": {
+          "name": "scope",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "id_token": {
+          "name": "id_token",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "session_state": {
+          "name": "session_state",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {
+        "account_userId_user_id_fk": {
+          "name": "account_userId_user_id_fk",
+          "tableFrom": "account",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {
+        "account_provider_providerAccountId_pk": {
+          "columns": [
+            "provider",
+            "providerAccountId"
+          ],
+          "name": "account_provider_providerAccountId_pk"
+        }
+      },
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "apiKey": {
+      "name": "apiKey",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "keyId": {
+          "name": "keyId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "keyHash": {
+          "name": "keyHash",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "apiKey_keyId_unique": {
+          "name": "apiKey_keyId_unique",
+          "columns": [
+            "keyId"
+          ],
+          "isUnique": true
+        },
+        "apiKey_name_userId_unique": {
+          "name": "apiKey_name_userId_unique",
+          "columns": [
+            "name",
+            "userId"
+          ],
+          "isUnique": true
+        }
+      },
+      "foreignKeys": {
+        "apiKey_userId_user_id_fk": {
+          "name": "apiKey_userId_user_id_fk",
+          "tableFrom": "apiKey",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "assets": {
+      "name": "assets",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "assetType": {
+          "name": "assetType",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "size": {
+          "name": "size",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": 0
+        },
+        "contentType": {
+          "name": "contentType",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "fileName": {
+          "name": "fileName",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "bookmarkId": {
+          "name": "bookmarkId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "assets_bookmarkId_idx": {
+          "name": "assets_bookmarkId_idx",
+          "columns": [
+            "bookmarkId"
+          ],
+          "isUnique": false
+        },
+        "assets_assetType_idx": {
+          "name": "assets_assetType_idx",
+          "columns": [
+            "assetType"
+          ],
+          "isUnique": false
+        },
+        "assets_userId_idx": {
+          "name": "assets_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "assets_bookmarkId_bookmarks_id_fk": {
+          "name": "assets_bookmarkId_bookmarks_id_fk",
+          "tableFrom": "assets",
+          "tableTo": "bookmarks",
+          "columnsFrom": [
+            "bookmarkId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "assets_userId_user_id_fk": {
+          "name": "assets_userId_user_id_fk",
+          "tableFrom": "assets",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "bookmarkAssets": {
+      "name": "bookmarkAssets",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "assetType": {
+          "name": "assetType",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "assetId": {
+          "name": "assetId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "content": {
+          "name": "content",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "metadata": {
+          "name": "metadata",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "fileName": {
+          "name": "fileName",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "sourceUrl": {
+          "name": "sourceUrl",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {
+        "bookmarkAssets_id_bookmarks_id_fk": {
+          "name": "bookmarkAssets_id_bookmarks_id_fk",
+          "tableFrom": "bookmarkAssets",
+          "tableTo": "bookmarks",
+          "columnsFrom": [
+            "id"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "bookmarkLinks": {
+      "name": "bookmarkLinks",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "url": {
+          "name": "url",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "title": {
+          "name": "title",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "description": {
+          "name": "description",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "author": {
+          "name": "author",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "publisher": {
+          "name": "publisher",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "datePublished": {
+          "name": "datePublished",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "dateModified": {
+          "name": "dateModified",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "imageUrl": {
+          "name": "imageUrl",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "favicon": {
+          "name": "favicon",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "htmlContent": {
+          "name": "htmlContent",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "contentAssetId": {
+          "name": "contentAssetId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "crawledAt": {
+          "name": "crawledAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "crawlStatus": {
+          "name": "crawlStatus",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false,
+          "default": "'pending'"
+        },
+        "crawlStatusCode": {
+          "name": "crawlStatusCode",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false,
+          "default": 200
+        }
+      },
+      "indexes": {
+        "bookmarkLinks_url_idx": {
+          "name": "bookmarkLinks_url_idx",
+          "columns": [
+            "url"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "bookmarkLinks_id_bookmarks_id_fk": {
+          "name": "bookmarkLinks_id_bookmarks_id_fk",
+          "tableFrom": "bookmarkLinks",
+          "tableTo": "bookmarks",
+          "columnsFrom": [
+            "id"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "bookmarkLists": {
+      "name": "bookmarkLists",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "description": {
+          "name": "description",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "icon": {
+          "name": "icon",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "type": {
+          "name": "type",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "query": {
+          "name": "query",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "parentId": {
+          "name": "parentId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "rssToken": {
+          "name": "rssToken",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "public": {
+          "name": "public",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": false
+        }
+      },
+      "indexes": {
+        "bookmarkLists_userId_idx": {
+          "name": "bookmarkLists_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        },
+        "bookmarkLists_userId_id_idx": {
+          "name": "bookmarkLists_userId_id_idx",
+          "columns": [
+            "userId",
+            "id"
+          ],
+          "isUnique": true
+        }
+      },
+      "foreignKeys": {
+        "bookmarkLists_userId_user_id_fk": {
+          "name": "bookmarkLists_userId_user_id_fk",
+          "tableFrom": "bookmarkLists",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "bookmarkLists_parentId_bookmarkLists_id_fk": {
+          "name": "bookmarkLists_parentId_bookmarkLists_id_fk",
+          "tableFrom": "bookmarkLists",
+          "tableTo": "bookmarkLists",
+          "columnsFrom": [
+            "parentId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "set null",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "bookmarkTags": {
+      "name": "bookmarkTags",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "bookmarkTags_name_idx": {
+          "name": "bookmarkTags_name_idx",
+          "columns": [
+            "name"
+          ],
+          "isUnique": false
+        },
+        "bookmarkTags_userId_idx": {
+          "name": "bookmarkTags_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        },
+        "bookmarkTags_userId_name_unique": {
+          "name": "bookmarkTags_userId_name_unique",
+          "columns": [
+            "userId",
+            "name"
+          ],
+          "isUnique": true
+        },
+        "bookmarkTags_userId_id_idx": {
+          "name": "bookmarkTags_userId_id_idx",
+          "columns": [
+            "userId",
+            "id"
+          ],
+          "isUnique": true
+        }
+      },
+      "foreignKeys": {
+        "bookmarkTags_userId_user_id_fk": {
+          "name": "bookmarkTags_userId_user_id_fk",
+          "tableFrom": "bookmarkTags",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "bookmarkTexts": {
+      "name": "bookmarkTexts",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "text": {
+          "name": "text",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "sourceUrl": {
+          "name": "sourceUrl",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {
+        "bookmarkTexts_id_bookmarks_id_fk": {
+          "name": "bookmarkTexts_id_bookmarks_id_fk",
+          "tableFrom": "bookmarkTexts",
+          "tableTo": "bookmarks",
+          "columnsFrom": [
+            "id"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "bookmarks": {
+      "name": "bookmarks",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "modifiedAt": {
+          "name": "modifiedAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "title": {
+          "name": "title",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "archived": {
+          "name": "archived",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": false
+        },
+        "favourited": {
+          "name": "favourited",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "taggingStatus": {
+          "name": "taggingStatus",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false,
+          "default": "'pending'"
+        },
+        "summarizationStatus": {
+          "name": "summarizationStatus",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false,
+          "default": "'pending'"
+        },
+        "summary": {
+          "name": "summary",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "note": {
+          "name": "note",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "type": {
+          "name": "type",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "bookmarks_userId_idx": {
+          "name": "bookmarks_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        },
+        "bookmarks_archived_idx": {
+          "name": "bookmarks_archived_idx",
+          "columns": [
+            "archived"
+          ],
+          "isUnique": false
+        },
+        "bookmarks_favourited_idx": {
+          "name": "bookmarks_favourited_idx",
+          "columns": [
+            "favourited"
+          ],
+          "isUnique": false
+        },
+        "bookmarks_createdAt_idx": {
+          "name": "bookmarks_createdAt_idx",
+          "columns": [
+            "createdAt"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "bookmarks_userId_user_id_fk": {
+          "name": "bookmarks_userId_user_id_fk",
+          "tableFrom": "bookmarks",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "bookmarksInLists": {
+      "name": "bookmarksInLists",
+      "columns": {
+        "bookmarkId": {
+          "name": "bookmarkId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "listId": {
+          "name": "listId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "addedAt": {
+          "name": "addedAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "bookmarksInLists_bookmarkId_idx": {
+          "name": "bookmarksInLists_bookmarkId_idx",
+          "columns": [
+            "bookmarkId"
+          ],
+          "isUnique": false
+        },
+        "bookmarksInLists_listId_idx": {
+          "name": "bookmarksInLists_listId_idx",
+          "columns": [
+            "listId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "bookmarksInLists_bookmarkId_bookmarks_id_fk": {
+          "name": "bookmarksInLists_bookmarkId_bookmarks_id_fk",
+          "tableFrom": "bookmarksInLists",
+          "tableTo": "bookmarks",
+          "columnsFrom": [
+            "bookmarkId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "bookmarksInLists_listId_bookmarkLists_id_fk": {
+          "name": "bookmarksInLists_listId_bookmarkLists_id_fk",
+          "tableFrom": "bookmarksInLists",
+          "tableTo": "bookmarkLists",
+          "columnsFrom": [
+            "listId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {
+        "bookmarksInLists_bookmarkId_listId_pk": {
+          "columns": [
+            "bookmarkId",
+            "listId"
+          ],
+          "name": "bookmarksInLists_bookmarkId_listId_pk"
+        }
+      },
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "config": {
+      "name": "config",
+      "columns": {
+        "key": {
+          "name": "key",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "value": {
+          "name": "value",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "customPrompts": {
+      "name": "customPrompts",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "text": {
+          "name": "text",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "enabled": {
+          "name": "enabled",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "appliesTo": {
+          "name": "appliesTo",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "customPrompts_userId_idx": {
+          "name": "customPrompts_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "customPrompts_userId_user_id_fk": {
+          "name": "customPrompts_userId_user_id_fk",
+          "tableFrom": "customPrompts",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "highlights": {
+      "name": "highlights",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "bookmarkId": {
+          "name": "bookmarkId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "startOffset": {
+          "name": "startOffset",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "endOffset": {
+          "name": "endOffset",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "color": {
+          "name": "color",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": "'yellow'"
+        },
+        "text": {
+          "name": "text",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "note": {
+          "name": "note",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "highlights_bookmarkId_idx": {
+          "name": "highlights_bookmarkId_idx",
+          "columns": [
+            "bookmarkId"
+          ],
+          "isUnique": false
+        },
+        "highlights_userId_idx": {
+          "name": "highlights_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "highlights_bookmarkId_bookmarks_id_fk": {
+          "name": "highlights_bookmarkId_bookmarks_id_fk",
+          "tableFrom": "highlights",
+          "tableTo": "bookmarks",
+          "columnsFrom": [
+            "bookmarkId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "highlights_userId_user_id_fk": {
+          "name": "highlights_userId_user_id_fk",
+          "tableFrom": "highlights",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "rssFeedImports": {
+      "name": "rssFeedImports",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "entryId": {
+          "name": "entryId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "rssFeedId": {
+          "name": "rssFeedId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "bookmarkId": {
+          "name": "bookmarkId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "rssFeedImports_feedIdIdx_idx": {
+          "name": "rssFeedImports_feedIdIdx_idx",
+          "columns": [
+            "rssFeedId"
+          ],
+          "isUnique": false
+        },
+        "rssFeedImports_entryIdIdx_idx": {
+          "name": "rssFeedImports_entryIdIdx_idx",
+          "columns": [
+            "entryId"
+          ],
+          "isUnique": false
+        },
+        "rssFeedImports_rssFeedId_entryId_unique": {
+          "name": "rssFeedImports_rssFeedId_entryId_unique",
+          "columns": [
+            "rssFeedId",
+            "entryId"
+          ],
+          "isUnique": true
+        }
+      },
+      "foreignKeys": {
+        "rssFeedImports_rssFeedId_rssFeeds_id_fk": {
+          "name": "rssFeedImports_rssFeedId_rssFeeds_id_fk",
+          "tableFrom": "rssFeedImports",
+          "tableTo": "rssFeeds",
+          "columnsFrom": [
+            "rssFeedId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "rssFeedImports_bookmarkId_bookmarks_id_fk": {
+          "name": "rssFeedImports_bookmarkId_bookmarks_id_fk",
+          "tableFrom": "rssFeedImports",
+          "tableTo": "bookmarks",
+          "columnsFrom": [
+            "bookmarkId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "set null",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "rssFeeds": {
+      "name": "rssFeeds",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "url": {
+          "name": "url",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "enabled": {
+          "name": "enabled",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": true
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "lastFetchedAt": {
+          "name": "lastFetchedAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "lastFetchedStatus": {
+          "name": "lastFetchedStatus",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false,
+          "default": "'pending'"
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "rssFeeds_userId_idx": {
+          "name": "rssFeeds_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "rssFeeds_userId_user_id_fk": {
+          "name": "rssFeeds_userId_user_id_fk",
+          "tableFrom": "rssFeeds",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "ruleEngineActions": {
+      "name": "ruleEngineActions",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "ruleId": {
+          "name": "ruleId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "action": {
+          "name": "action",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "listId": {
+          "name": "listId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "tagId": {
+          "name": "tagId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "ruleEngineActions_userId_idx": {
+          "name": "ruleEngineActions_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        },
+        "ruleEngineActions_ruleId_idx": {
+          "name": "ruleEngineActions_ruleId_idx",
+          "columns": [
+            "ruleId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "ruleEngineActions_userId_user_id_fk": {
+          "name": "ruleEngineActions_userId_user_id_fk",
+          "tableFrom": "ruleEngineActions",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "ruleEngineActions_ruleId_ruleEngineRules_id_fk": {
+          "name": "ruleEngineActions_ruleId_ruleEngineRules_id_fk",
+          "tableFrom": "ruleEngineActions",
+          "tableTo": "ruleEngineRules",
+          "columnsFrom": [
+            "ruleId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "ruleEngineActions_userId_tagId_fk": {
+          "name": "ruleEngineActions_userId_tagId_fk",
+          "tableFrom": "ruleEngineActions",
+          "tableTo": "bookmarkTags",
+          "columnsFrom": [
+            "userId",
+            "tagId"
+          ],
+          "columnsTo": [
+            "userId",
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "ruleEngineActions_userId_listId_fk": {
+          "name": "ruleEngineActions_userId_listId_fk",
+          "tableFrom": "ruleEngineActions",
+          "tableTo": "bookmarkLists",
+          "columnsFrom": [
+            "userId",
+            "listId"
+          ],
+          "columnsTo": [
+            "userId",
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "ruleEngineRules": {
+      "name": "ruleEngineRules",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "enabled": {
+          "name": "enabled",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": true
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "description": {
+          "name": "description",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "event": {
+          "name": "event",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "condition": {
+          "name": "condition",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "listId": {
+          "name": "listId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "tagId": {
+          "name": "tagId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "ruleEngine_userId_idx": {
+          "name": "ruleEngine_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "ruleEngineRules_userId_user_id_fk": {
+          "name": "ruleEngineRules_userId_user_id_fk",
+          "tableFrom": "ruleEngineRules",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "ruleEngineRules_userId_tagId_fk": {
+          "name": "ruleEngineRules_userId_tagId_fk",
+          "tableFrom": "ruleEngineRules",
+          "tableTo": "bookmarkTags",
+          "columnsFrom": [
+            "userId",
+            "tagId"
+          ],
+          "columnsTo": [
+            "userId",
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "ruleEngineRules_userId_listId_fk": {
+          "name": "ruleEngineRules_userId_listId_fk",
+          "tableFrom": "ruleEngineRules",
+          "tableTo": "bookmarkLists",
+          "columnsFrom": [
+            "userId",
+            "listId"
+          ],
+          "columnsTo": [
+            "userId",
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "session": {
+      "name": "session",
+      "columns": {
+        "sessionToken": {
+          "name": "sessionToken",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "expires": {
+          "name": "expires",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {
+        "session_userId_user_id_fk": {
+          "name": "session_userId_user_id_fk",
+          "tableFrom": "session",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "tagsOnBookmarks": {
+      "name": "tagsOnBookmarks",
+      "columns": {
+        "bookmarkId": {
+          "name": "bookmarkId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "tagId": {
+          "name": "tagId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "attachedAt": {
+          "name": "attachedAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "attachedBy": {
+          "name": "attachedBy",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "tagsOnBookmarks_tagId_idx": {
+          "name": "tagsOnBookmarks_tagId_idx",
+          "columns": [
+            "tagId"
+          ],
+          "isUnique": false
+        },
+        "tagsOnBookmarks_bookmarkId_idx": {
+          "name": "tagsOnBookmarks_bookmarkId_idx",
+          "columns": [
+            "bookmarkId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "tagsOnBookmarks_bookmarkId_bookmarks_id_fk": {
+          "name": "tagsOnBookmarks_bookmarkId_bookmarks_id_fk",
+          "tableFrom": "tagsOnBookmarks",
+          "tableTo": "bookmarks",
+          "columnsFrom": [
+            "bookmarkId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        },
+        "tagsOnBookmarks_tagId_bookmarkTags_id_fk": {
+          "name": "tagsOnBookmarks_tagId_bookmarkTags_id_fk",
+          "tableFrom": "tagsOnBookmarks",
+          "tableTo": "bookmarkTags",
+          "columnsFrom": [
+            "tagId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {
+        "tagsOnBookmarks_bookmarkId_tagId_pk": {
+          "columns": [
+            "bookmarkId",
+            "tagId"
+          ],
+          "name": "tagsOnBookmarks_bookmarkId_tagId_pk"
+        }
+      },
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "userSettings": {
+      "name": "userSettings",
+      "columns": {
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "bookmarkClickAction": {
+          "name": "bookmarkClickAction",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": "'open_original_link'"
+        },
+        "archiveDisplayBehaviour": {
+          "name": "archiveDisplayBehaviour",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": "'show'"
+        },
+        "timezone": {
+          "name": "timezone",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false,
+          "default": "'UTC'"
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {
+        "userSettings_userId_user_id_fk": {
+          "name": "userSettings_userId_user_id_fk",
+          "tableFrom": "userSettings",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "user": {
+      "name": "user",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "email": {
+          "name": "email",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "emailVerified": {
+          "name": "emailVerified",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "image": {
+          "name": "image",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "password": {
+          "name": "password",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "salt": {
+          "name": "salt",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false,
+          "default": "''"
+        },
+        "role": {
+          "name": "role",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false,
+          "default": "'user'"
+        },
+        "bookmarkQuota": {
+          "name": "bookmarkQuota",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "storageQuota": {
+          "name": "storageQuota",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "user_email_unique": {
+          "name": "user_email_unique",
+          "columns": [
+            "email"
+          ],
+          "isUnique": true
+        }
+      },
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "verificationToken": {
+      "name": "verificationToken",
+      "columns": {
+        "identifier": {
+          "name": "identifier",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "token": {
+          "name": "token",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "expires": {
+          "name": "expires",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {
+        "verificationToken_identifier_token_pk": {
+          "columns": [
+            "identifier",
+            "token"
+          ],
+          "name": "verificationToken_identifier_token_pk"
+        }
+      },
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "webhooks": {
+      "name": "webhooks",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "createdAt": {
+          "name": "createdAt",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "url": {
+          "name": "url",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "userId": {
+          "name": "userId",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "events": {
+          "name": "events",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "token": {
+          "name": "token",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        }
+      },
+      "indexes": {
+        "webhooks_userId_idx": {
+          "name": "webhooks_userId_idx",
+          "columns": [
+            "userId"
+          ],
+          "isUnique": false
+        }
+      },
+      "foreignKeys": {
+        "webhooks_userId_user_id_fk": {
+          "name": "webhooks_userId_user_id_fk",
+          "tableFrom": "webhooks",
+          "tableTo": "user",
+          "columnsFrom": [
+            "userId"
+          ],
+          "columnsTo": [
+            "id"
+          ],
+          "onDelete": "cascade",
+          "onUpdate": "no action"
+        }
+      },
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    }
+  },
+  "views": {},
+  "enums": {},
+  "_meta": {
+    "schemas": {},
+    "tables": {},
+    "columns": {}
+  },
+  "internal": {
+    "indexes": {}
+  }
+}
\ No newline at end of file
diff --git a/packages/db/drizzle/meta/_journal.json b/packages/db/drizzle/meta/_journal.json
index ea4e30b1..6c509b15 100644
--- a/packages/db/drizzle/meta/_journal.json
+++ b/packages/db/drizzle/meta/_journal.json
@@ -386,6 +386,13 @@
       "when": 1751826417328,
       "tag": "0054_add_timezone",
       "breakpoints": true
+    },
+    {
+      "idx": 55,
+      "version": "6",
+      "when": 1751839469055,
+      "tag": "0055_content_asset_id",
+      "breakpoints": true
     }
   ]
 }
\ No newline at end of file
diff --git a/packages/db/schema.ts b/packages/db/schema.ts
index ed9d586c..4375b201 100644
--- a/packages/db/schema.ts
+++ b/packages/db/schema.ts
@@ -161,8 +161,8 @@ export const bookmarkLinks = sqliteTable(
     dateModified: integer("dateModified", { mode: "timestamp" }),
     imageUrl: text("imageUrl"),
     favicon: text("favicon"),
-    content: text("content"),
     htmlContent: text("htmlContent"),
+    contentAssetId: text("contentAssetId"),
     crawledAt: integer("crawledAt", { mode: "timestamp" }),
     crawlStatus: text("crawlStatus", {
       enum: ["pending", "failure", "success"],
@@ -179,6 +179,7 @@ export const enum AssetTypes {
   LINK_FULL_PAGE_ARCHIVE = "linkFullPageArchive",
   LINK_PRECRAWLED_ARCHIVE = "linkPrecrawledArchive",
   LINK_VIDEO = "linkVideo",
+  LINK_HTML_CONTENT = "linkHtmlContent",
   BOOKMARK_ASSET = "bookmarkAsset",
   UNKNOWN = "unknown",
 }
@@ -196,6 +197,7 @@ export const assets = sqliteTable(
         AssetTypes.LINK_FULL_PAGE_ARCHIVE,
         AssetTypes.LINK_PRECRAWLED_ARCHIVE,
         AssetTypes.LINK_VIDEO,
+        AssetTypes.LINK_HTML_CONTENT,
         AssetTypes.BOOKMARK_ASSET,
         AssetTypes.UNKNOWN,
       ],
diff --git a/packages/shared/package.json b/packages/shared/package.json
index f4e521b6..6f22865f 100644
--- a/packages/shared/package.json
+++ b/packages/shared/package.json
@@ -7,6 +7,7 @@
   "dependencies": {
     "@aws-sdk/client-s3": "^3.842.0",
     "glob": "^11.0.0",
+    "html-to-text": "^9.0.5",
     "js-tiktoken": "^1.0.20",
     "liteque": "^0.3.2",
     "meilisearch": "^0.37.0",
@@ -20,6 +21,7 @@
   "devDependencies": {
     "@karakeep/prettier-config": "workspace:^0.1.0",
     "@karakeep/tsconfig": "workspace:^0.1.0",
+    "@types/html-to-text": "^9.0.4",
     "vitest": "^1.6.1"
   },
   "scripts": {
diff --git a/packages/shared/types/bookmarks.ts b/packages/shared/types/bookmarks.ts
index ea1ab717..f648bce5 100644
--- a/packages/shared/types/bookmarks.ts
+++ b/packages/shared/types/bookmarks.ts
@@ -16,6 +16,7 @@ export const zSortOrder = z.enum(["asc", "desc", "relevance"]);
 export type ZSortOrder = z.infer<typeof zSortOrder>;
 
 export const zAssetTypesSchema = z.enum([
+  "linkHtmlContent",
   "screenshot",
   "assetScreenshot",
   "bannerImage",
@@ -45,6 +46,7 @@ export const zBookmarkedLinkSchema = z.object({
   videoAssetId: z.string().nullish(),
   favicon: z.string().nullish(),
   htmlContent: z.string().nullish(),
+  contentAssetId: z.string().nullish(),
   crawledAt: z.date().nullish(),
   author: z.string().nullish(),
   publisher: z.string().nullish(),
diff --git a/packages/shared/utils/htmlUtils.ts b/packages/shared/utils/htmlUtils.ts
new file mode 100644
index 00000000..60272899
--- /dev/null
+++ b/packages/shared/utils/htmlUtils.ts
@@ -0,0 +1,17 @@
+import { compile } from "html-to-text";
+
+const compiledConvert = compile({
+  selectors: [{ selector: "img", format: "skip" }],
+});
+
+/**
+ * Converts HTML content to plain text
+ */
+export function htmlToPlainText(htmlContent: string): string {
+  if (!htmlContent) {
+    return "";
+  }
+
+  // TODO, we probably should also remove singlefile inline images from the content
+  return compiledConvert(htmlContent);
+}
diff --git a/packages/trpc/lib/attachments.ts b/packages/trpc/lib/attachments.ts
index 739aa8f5..e886b821 100644
--- a/packages/trpc/lib/attachments.ts
+++ b/packages/trpc/lib/attachments.ts
@@ -14,6 +14,7 @@ export function mapDBAssetTypeToUserType(assetType: AssetTypes): ZAssetType {
     [AssetTypes.LINK_PRECRAWLED_ARCHIVE]: "precrawledArchive",
     [AssetTypes.LINK_BANNER_IMAGE]: "bannerImage",
     [AssetTypes.LINK_VIDEO]: "video",
+    [AssetTypes.LINK_HTML_CONTENT]: "linkHtmlContent",
     [AssetTypes.BOOKMARK_ASSET]: "bookmarkAsset",
     [AssetTypes.UNKNOWN]: "bannerImage",
   };
@@ -31,6 +32,7 @@ export function mapSchemaAssetTypeToDB(
     bannerImage: AssetTypes.LINK_BANNER_IMAGE,
     video: AssetTypes.LINK_VIDEO,
     bookmarkAsset: AssetTypes.BOOKMARK_ASSET,
+    linkHtmlContent: AssetTypes.LINK_HTML_CONTENT,
     unknown: AssetTypes.UNKNOWN,
   };
   return map[assetType];
@@ -45,6 +47,7 @@ export function humanFriendlyNameForAssertType(type: ZAssetType) {
     bannerImage: "Banner Image",
     video: "Video",
     bookmarkAsset: "Bookmark Asset",
+    linkHtmlContent: "HTML Content",
     unknown: "Unknown",
   };
   return map[type];
@@ -59,6 +62,7 @@ export function isAllowedToAttachAsset(type: ZAssetType) {
     bannerImage: true,
     video: false,
     bookmarkAsset: false,
+    linkHtmlContent: false,
     unknown: false,
   };
   return map[type];
@@ -73,6 +77,7 @@ export function isAllowedToDetachAsset(type: ZAssetType) {
     bannerImage: true,
     video: true,
     bookmarkAsset: false,
+    linkHtmlContent: false,
     unknown: false,
   };
   return map[type];
diff --git a/packages/trpc/models/bookmarks.ts b/packages/trpc/models/bookmarks.ts
index 986fca58..07b3832d 100644
--- a/packages/trpc/models/bookmarks.ts
+++ b/packages/trpc/models/bookmarks.ts
@@ -27,6 +27,7 @@ import {
   rssFeedImportsTable,
   tagsOnBookmarks,
 } from "@karakeep/db/schema";
+import { readAsset } from "@karakeep/shared/assetdb";
 import serverConfig from "@karakeep/shared/config";
 import {
   createSignedToken,
@@ -46,6 +47,7 @@ import {
   getBookmarkLinkAssetIdOrUrl,
   getBookmarkTitle,
 } from "@karakeep/shared/utils/bookmarkUtils";
+import { htmlToPlainText } from "@karakeep/shared/utils/htmlUtils";
 
 import { AuthedContext } from "..";
 import { mapDBAssetTypeToUserType } from "../lib/attachments";
@@ -202,8 +204,11 @@ export class Bookmark implements PrivacyAware {
               imageUrl: row.bookmarkLinks.imageUrl,
               favicon: row.bookmarkLinks.favicon,
               htmlContent: input.includeContent
-                ? row.bookmarkLinks.htmlContent
+                ? row.bookmarkLinks.contentAssetId
+                  ? null // Will be populated later from asset
+                  : row.bookmarkLinks.htmlContent
                 : null,
+              contentAssetId: row.bookmarkLinks.contentAssetId,
               crawledAt: row.bookmarkLinks.crawledAt,
               author: row.bookmarkLinks.author,
               publisher: row.bookmarkLinks.publisher,
@@ -300,6 +305,33 @@ export class Bookmark implements PrivacyAware {
 
     const bookmarksArr = Object.values(bookmarksRes);
 
+    // Fetch HTML content from assets for bookmarks that have contentAssetId (large content)
+    if (input.includeContent) {
+      await Promise.all(
+        bookmarksArr.map(async (bookmark) => {
+          if (
+            bookmark.content.type === BookmarkTypes.LINK &&
+            bookmark.content.contentAssetId &&
+            !bookmark.content.htmlContent // Only fetch if not already inline
+          ) {
+            try {
+              const asset = await readAsset({
+                userId: ctx.user.id,
+                assetId: bookmark.content.contentAssetId,
+              });
+              bookmark.content.htmlContent = asset.asset.toString("utf8");
+            } catch (error) {
+              // If asset reading fails, keep htmlContent as null
+              console.warn(
+                `Failed to read HTML content asset ${bookmark.content.contentAssetId}:`,
+                error,
+              );
+            }
+          }
+        }),
+      );
+    }
+
     bookmarksArr.sort((a, b) => {
       if (a.createdAt != b.createdAt) {
         return input.sortOrder === "asc"
@@ -427,4 +459,50 @@ export class Bookmark implements PrivacyAware {
       bannerImageUrl: getBannerImageUrl(this.bookmark.content),
     };
   }
+
+  static async getBookmarkHtmlContent(
+    {
+      contentAssetId,
+      htmlContent,
+    }: {
+      contentAssetId: string | null;
+      htmlContent: string | null;
+    },
+    userId: string,
+  ): Promise<string | null> {
+    if (contentAssetId) {
+      // Read large HTML content from asset
+      const asset = await readAsset({
+        userId,
+        assetId: contentAssetId,
+      });
+      return asset.asset.toString("utf8");
+    } else if (htmlContent) {
+      return htmlContent;
+    }
+    return null;
+  }
+
+  static async getBookmarkPlainTextContent(
+    {
+      contentAssetId,
+      htmlContent,
+    }: {
+      contentAssetId: string | null;
+      htmlContent: string | null;
+    },
+    userId: string,
+  ): Promise<string | null> {
+    const content = await this.getBookmarkHtmlContent(
+      {
+        contentAssetId,
+        htmlContent,
+      },
+      userId,
+    );
+    if (!content) {
+      return null;
+    }
+    return htmlToPlainText(content);
+  }
 }
diff --git a/packages/trpc/routers/bookmarks.ts b/packages/trpc/routers/bookmarks.ts
index f1fe10d7..77f40878 100644
--- a/packages/trpc/routers/bookmarks.ts
+++ b/packages/trpc/routers/bookmarks.ts
@@ -118,7 +118,7 @@ async function getBookmark(
     });
   }
 
-  return toZodSchema(bookmark, includeContent);
+  return await toZodSchema(bookmark, includeContent);
 }
 
 async function attemptToDedupLink(ctx: AuthedContext, url: string) {
@@ -177,10 +177,10 @@ async function cleanupAssetForBookmark(
   );
 }
 
-function toZodSchema(
+async function toZodSchema(
   bookmark: BookmarkQueryReturnType,
   includeContent: boolean,
-): ZBookmark {
+): Promise<ZBookmark> {
   const { tagsOnBookmarks, link, text, asset, assets, ...rest } = bookmark;
 
   let content: ZBookmarkContent = {
@@ -208,7 +208,9 @@ function toZodSchema(
       description: link.description,
       imageUrl: link.imageUrl,
       favicon: link.favicon,
-      htmlContent: includeContent ? link.htmlContent : null,
+      htmlContent: includeContent
+        ? await Bookmark.getBookmarkHtmlContent(link, bookmark.userId)
+        : null,
       crawledAt: link.crawledAt,
       author: link.author,
       publisher: link.publisher,
@@ -806,7 +808,9 @@ export const bookmarksAppRouter = router({
       }
 
       return {
-        bookmarks: results.map((b) => toZodSchema(b, input.includeContent)),
+        bookmarks: await Promise.all(
+          results.map((b) => toZodSchema(b, input.includeContent)),
+        ),
         nextCursor:
           resp.hits.length + resp.offset >= resp.estimatedTotalHits
             ? null
@@ -1052,10 +1056,15 @@ export const bookmarksAppRouter = router({
         });
       }
 
+      const content = await Bookmark.getBookmarkPlainTextContent(
+        bookmark,
+        ctx.user.id,
+      );
+
       const bookmarkDetails = `
 Title: ${bookmark.title ?? ""}
 Description: ${bookmark.description ?? ""}
-Content: ${bookmark.content ?? ""}
+Content: ${content}
 Publisher: ${bookmark.publisher ?? ""}
 Author: ${bookmark.author ?? ""}
 `;
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 08fe922c..3649d5b7 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -1109,6 +1109,9 @@ importers:
       glob:
         specifier: ^11.0.0
         version: 11.0.2
+      html-to-text:
+        specifier: ^9.0.5
+        version: 9.0.5
       js-tiktoken:
         specifier: ^1.0.20
         version: 1.0.20
@@ -1143,6 +1146,9 @@ importers:
       '@karakeep/tsconfig':
         specifier: workspace:^0.1.0
         version: link:../../tooling/typescript
+      '@types/html-to-text':
+        specifier: ^9.0.4
+        version: 9.0.4
       vitest:
         specifier: ^1.6.1
         version: 1.6.1(@types/node@22.15.30)(happy-dom@17.4.9)(jsdom@26.1.0)(lightningcss@1.30.1)(sass@1.89.1)(terser@5.41.0)
@@ -4782,6 +4788,9 @@ packages:
   '@segment/loosely-validate-event@2.0.0':
     resolution: {integrity: sha512-ZMCSfztDBqwotkl848ODgVcAmN4OItEWDCkshcKz0/W6gGSQayuuCtWV/MlodFivAZD793d6UgANd6wCXUfrIw==}
 
+  '@selderee/plugin-htmlparser2@0.11.0':
+    resolution: {integrity: sha512-P33hHGdldxGabLFjPPpaTxVolMrzrcegejx+0GxjrIb9Zv48D8yAIA/QTDR2dFl7Uz7urX8aX6+5bCZslr+gWQ==}
+
   '@sideway/address@4.1.5':
     resolution: {integrity: sha512-IqO/DUQHUkPeixNQ8n0JA6102hT9CmaljNTPmQ1u8MEhBo/R4Q8eKLN/vGZxuebwOroDB4cbpjheD4+/sKFK4Q==}
 
@@ -5385,6 +5394,9 @@ packages:
   '@types/html-minifier-terser@6.1.0':
     resolution: {integrity: sha512-oh/6byDPnL1zeNXFrDXFLyZjkr1MsBG667IM792caf1L2UPOOMf65NFzjUH/ltyfwjAGfs1rsX1eftK0jC/KIg==}
 
+  '@types/html-to-text@9.0.4':
+    resolution: {integrity: sha512-pUY3cKH/Nm2yYrEmDlPR1mR7yszjGx4DrwPjQ702C4/D5CwHuZTgZdIdwPkRbcuhs7BAh2L5rg3CL5cbRiGTCQ==}
+
   '@types/http-cache-semantics@4.0.4':
     resolution: {integrity: sha512-1m0bIFVc7eJWyve9S0RnuRgcQqF/Xd5QsUZAZeQFr1Q3/p9JWoQQEqmVy+DPTNpGXwhgIetAoYF8JSc33q29QA==}
 
@@ -8604,6 +8616,10 @@ packages:
     resolution: {integrity: sha512-ztqyC3kLto0e9WbNp0aeP+M3kTt+nbaIveGmUxAtZa+8iFgKLUOD4YKM5j+f3QD89bra7UeumolZHKuOXnTmeQ==}
     engines: {node: '>=8'}
 
+  html-to-text@9.0.5:
+    resolution: {integrity: sha512-qY60FjREgVZL03vJU6IfMV4GDjGBIoOyvuFdpBDIX9yTlDw0TjxVBQp+P8NvpdIXNJvfWBTNul7fsAQJq2FNpg==}
+    engines: {node: '>=14'}
+
   html-url-attributes@3.0.1:
     resolution: {integrity: sha512-ol6UPyBWqsrO6EJySPz2O7ZSr856WDrEzM5zMqp+FJJLGMW35cLYmmZnl0vztAZxRUoNZJFTCohfjuIJ8I4QBQ==}
 
@@ -9407,6 +9423,9 @@ packages:
     resolution: {integrity: sha512-RE2g0b5VGZsOCFOCgP7omTRYFqydmZkBwl5oNnQ1lDYC57uyO9KqNnNVxT7COSHTxrRCWVcAVOcbjk+tvh/rgQ==}
     engines: {node: '>=0.10.0'}
 
+  leac@0.6.0:
+    resolution: {integrity: sha512-y+SqErxb8h7nE/fiEX07jsbuhrpO9lL8eca7/Y1nuWV2moNlXhyd59iDGcRf6moVyDMbmTNzL40SUyrFU/yDpg==}
+
   leven@3.1.0:
     resolution: {integrity: sha512-qsda+H8jTaUaN/x5vzW2rzc+8Rw4TAQ/4KjB46IwK5VH+IlVeeeje/EoZRpiXvIqjFgK84QffqPztGI3VBLG1A==}
     engines: {node: '>=6'}
@@ -10959,6 +10978,9 @@ packages:
   parse5@7.3.0:
     resolution: {integrity: sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw==}
 
+  parseley@0.12.1:
+    resolution: {integrity: sha512-e6qHKe3a9HWr0oMRVDTRhKce+bRO8VGQR3NyVwcjwrbhMmFCX9KszEV35+rn4AdilFAq9VPxP/Fe1wC9Qjd2lw==}
+
   parseurl@1.3.3:
     resolution: {integrity: sha512-CiyeOxFT/JZyN5m0z9PfXw4SCBJ6Sygz1Dpl0wqjlhDEGGBP1GnsUVEL0p63hoG1fcj3fHynXi9NYO4nWOL+qQ==}
     engines: {node: '>= 0.8'}
@@ -11055,6 +11077,9 @@ packages:
     resolution: {integrity: sha512-/Y3fcFrXEAsMjJXeL9J8+ZG9U01LbuWaYypvDW2ycW1jL269L3js3DVBjDJ0Up9Np1uqDXsDrRihHANhZOlwdQ==}
     engines: {node: '>=20'}
 
+  peberminta@0.9.0:
+    resolution: {integrity: sha512-XIxfHpEuSJbITd1H3EeQwpcZbTLHc+VVr8ANI9t5sit565tsI4/xK3KWTUFE2e6QiangUkh3B0jihzmGnNrRsQ==}
+
   picocolors@1.1.1:
     resolution: {integrity: sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==}
 
@@ -12655,6 +12680,9 @@ packages:
     resolution: {integrity: sha512-vfD3pmTzGpufjScBh50YHKzEu2lxBWhVEHsNGoEXmCmn2hKGfeNLYMzCJpe8cD7gqX7TJluOVpBkAequ6dgMmA==}
     engines: {node: '>=4'}
 
+  selderee@0.11.0:
+    resolution: {integrity: sha512-5TF+l7p4+OsnP8BCCvSyZiSPc4x4//p5uPwK8TCnVPJYRmU2aYKMpOXvw8zM5a5JvuuCGN1jmsMwuU2W02ukfA==}
+
   select-hose@2.0.0:
     resolution: {integrity: sha512-mEugaLK+YfkijB4fx0e6kImuJdCIt2LxCRcbEYPqRGCs4F2ogyfZU5IAZRdjCP8JPq2AtdNoC/Dux63d9Kiryg==}
 
@@ -20180,6 +20208,11 @@ snapshots:
       component-type: 1.2.2
       join-component: 1.1.0
 
+  '@selderee/plugin-htmlparser2@0.11.0':
+    dependencies:
+      domhandler: 5.0.3
+      selderee: 0.11.0
+
   '@sideway/address@4.1.5':
     dependencies:
       '@hapi/hoek': 9.3.0
@@ -20929,6 +20962,8 @@ snapshots:
 
   '@types/html-minifier-terser@6.1.0': {}
 
+  '@types/html-to-text@9.0.4': {}
+
   '@types/http-cache-semantics@4.0.4': {}
 
   '@types/http-errors@2.0.4': {}
@@ -24800,6 +24835,14 @@ snapshots:
 
   html-tags@3.3.1: {}
 
+  html-to-text@9.0.5:
+    dependencies:
+      '@selderee/plugin-htmlparser2': 0.11.0
+      deepmerge: 4.3.1
+      dom-serializer: 2.0.0
+      htmlparser2: 8.0.2
+      selderee: 0.11.0
+
   html-url-attributes@3.0.1: {}
 
   html-void-elements@2.0.1: {}
@@ -25630,6 +25673,8 @@ snapshots:
 
   lazy-cache@1.0.4: {}
 
+  leac@0.6.0: {}
+
   leven@3.1.0: {}
 
   levn@0.4.1:
@@ -27891,6 +27936,11 @@ snapshots:
     dependencies:
       entities: 6.0.0
 
+  parseley@0.12.1:
+    dependencies:
+      leac: 0.6.0
+      peberminta: 0.9.0
+
   parseurl@1.3.3: {}
 
   pascal-case@3.1.2:
@@ -27963,6 +28013,8 @@ snapshots:
     optionalDependencies:
       '@napi-rs/canvas': 0.1.70
 
+  peberminta@0.9.0: {}
+
   picocolors@1.1.1: {}
 
   picomatch@2.3.1: {}
@@ -29903,6 +29955,10 @@ snapshots:
       extend-shallow: 2.0.1
       kind-of: 6.0.3
 
+  selderee@0.11.0:
+    dependencies:
+      parseley: 0.12.1
+
   select-hose@2.0.0: {}
 
   selfsigned@2.4.1: