Keep searchable text only in knowledgebases

Every bot file was chunked into bot_file_chunks and embedded into
bot_file_vectors, and uploads kept their extracted text in
media.text_content, which together took most of the database. Bot
files are no longer indexed: bots find them by name or path with
list_files and read them with read_file, and search_files, ingest_file
and the files modal's re-read button are gone. Attachments keep no
text; a reply reads a document from the file. Only knowledgebase
documents keep text.

The schema drops both tables and the ingest columns. At boot,
dropStoredFileText removes what older versions stored (file jobs,
upload text) and vacuums once much of the database is free. The
media:prune-text script it replaces is removed.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

src/pages/api/admin/bots/files.ts

@@ -132,8 +132,6 @@ function toPublicFile({ file }: { file: BotFileWithMediaLite }) {
         purpose: file.purpose || "writing",
         scope: file.scope || "bot",
         owner_id: Number(file.owner_id) || 0,
-        ingested_at: file.ingested_at ? Number(file.ingested_at) : undefined,
-        ingest_error: file.ingest_error || undefined,
         created_at: Number(file.created_at) || 0,
         url: media_url || "",
     };
@@ -149,8 +147,6 @@ type BotFileWithMediaLite = {
     purpose?: string;
     scope?: string;
     owner_id?: number | "";
-    ingested_at?: number | "";
-    ingest_error?: string;
     created_at?: number | "";
     media?: Record<string, unknown> | null;
 };

src/pages/api/admin/bots/ingest-file.ts

@@ -1,82 +0,0 @@
-import userAuth from "@/src/functions/backend/auth/user-auth";
-import grabBotFile from "@/src/functions/backend/db/bot-files/grab-bot-file";
-import grabUserBot from "@/src/functions/backend/db/bots/grab-user-bot";
-import grabUserWorkspace from "@/src/functions/backend/db/workspaces/grab-user-workspace";
-import { IngestBotFileRequestSchema } from "@/src/schemas/bot-file-schema";
-import enqueueFileIngest from "@/src/file-ingest/enqueue-file-ingest";
-import AppError from "@/src/utils/app-error";
-import parseWithSchema from "@/src/utils/parse-with-schema";
-import canManageCrew from "@/src/utils/rbac/can-manage-crew";
-import isReadOnlyUser from "@/src/utils/rbac/is-read-only-user";
-import safeErrorMessage from "@/src/utils/safe-error-message";
-import type { StorageScope } from "@/src/utils/storage-access";
-import type { APIResponseObject, BunextAPIRouteHandler } from "@moduletrace/bunext/types";
-
-/**
- * Queues a conversation's file to be read again and re-embedded, for when
- * a search misses something the user knows is in it.
- */
-export const handler: BunextAPIRouteHandler<APIResponseObject> = async ({ req, body }) => {
-    try {
-        if (req.method != "POST") throw new AppError(`Method not allowed`);
-
-        const { user, user_types } = await userAuth({ req });
-
-        if (!user?.id) return { success: false, msg: `Unauthorized`, logoutUser: true };
-        if (isReadOnlyUser({ user_types: user_types || [] })) {
-            throw new AppError(`This user can only read records.`);
-        }
-        if (!canManageCrew({ user_types: user_types || [] })) {
-            throw new AppError(`Only a crew manager can re-read files.`);
-        }
-
-        const { file_id, read_media } = parseWithSchema({
-            schema: IngestBotFileRequestSchema,
-            data: body,
-        });
-
-        const scopes = await reachableScopes({ user_id: user.id, file_id });
-
-        const file = await grabBotFile({ scopes, file_id });
-
-        if (!file?.id) throw new AppError(`That file isn't here.`);
-
-        await enqueueFileIngest({ file_id: file.id });
-
-        return { success: true, msg: `${file.name || "The file"} will be read again shortly.` };
-    } catch (error: unknown) {
-        return { success: false, msg: safeErrorMessage({ error }) };
-    }
-};
-
-/**
- * The directories the user reaches for this file.
- */
-async function reachableScopes({
-    user_id,
-    file_id,
-}: {
-    user_id: number;
-    file_id: number;
-}): Promise<StorageScope[]> {
-    const { default: BunSQLite } = await import("@moduletrace/bun-sqlite");
-
-    const res = await BunSQLite.sql<{ scope: string; owner_id: number }>({
-        sql: `SELECT scope, owner_id FROM bot_files WHERE id = ? LIMIT 1`,
-        values: [file_id],
-    });
-
-    const file = res.payload?.[0];
-
-    if (!file?.owner_id) return [];
-
-    if (file.scope == "workspace") {
-        const workspace = await grabUserWorkspace({ workspace_id: file.owner_id, user_id });
-
-        return workspace?.id ? [{ scope: "workspace", owner_id: Number(file.owner_id) }] : [];
-    }
-
-    const bot = await grabUserBot({ bot_id: file.owner_id, user_id });
-
-    return bot?.id ? [{ scope: "bot", owner_id: Number(file.owner_id) }] : [];
-}

src/pages/api/admin/bots/upload-attachment.ts

@@ -8,7 +8,6 @@ import type { BotMessageAttachment } from "@/src/types";
 import AppError from "@/src/utils/app-error";
 import attachmentFileKind from "@/src/utils/attachment-file-kind";
 import bufferFromBase64 from "@/src/utils/buffer-from-base-64";
-import canExtractText from "@/src/utils/can-extract-text";
 import parseWithSchema from "@/src/utils/parse-with-schema";
 import isReadOnlyUser from "@/src/utils/rbac/is-read-only-user";
 import safeErrorMessage from "@/src/utils/safe-error-message";
@@ -19,8 +18,8 @@ import type {
 
 /**
  * Stores one file for a chat message, private to the session user, before
- * the message is sent with its id. Images are resized; documents have
- * their text pulled out now, so bots can read them later.
+ * the message is sent with its id. Images are resized; a document keeps
+ * no extracted text (a reply reads it from the file).
  */
 export const handler: BunextAPIRouteHandler<
     APIResponseObject<BotMessageAttachment>
@@ -65,7 +64,6 @@ export const handler: BunextAPIRouteHandler<
             media_mime_type: ext,
             media_paradigms: ["bot-attachment"],
             media: { title: name },
-            extract_media_text_content: canExtractText({ name, mime_type: mime }),
             user: { id: Number(user.id) },
         }).catch(async (error) => {
             await logError({ title: `Attachment ${name} couldn't be saved`, error }).catch(() => {});

src/pages/api/admin/tasks/attach-file.ts

@@ -9,7 +9,6 @@ import type { TaskDetail } from "@/src/types";
 import AppError from "@/src/utils/app-error";
 import attachmentFileKind from "@/src/utils/attachment-file-kind";
 import bufferFromBase64 from "@/src/utils/buffer-from-base-64";
-import canExtractText from "@/src/utils/can-extract-text";
 import parseWithSchema from "@/src/utils/parse-with-schema";
 import isReadOnlyUser from "@/src/utils/rbac/is-read-only-user";
 import safeErrorMessage from "@/src/utils/safe-error-message";
@@ -66,7 +65,6 @@ export const handler: BunextAPIRouteHandler<APIResponseObject<TaskDetail>> = asy
                 media_mime_type: ext,
                 media_paradigms: ["task-media"],
                 media: { title: name },
-                extract_media_text_content: canExtractText({ name, mime_type: mime }),
                 user: { id: Number(user.id) },
             });
 

src/pages/api/admin/upload-media.ts

@@ -44,7 +44,6 @@ export const handler: BunextAPIRouteHandler<APIResponseObject> = async (
             is_media_primary,
             update_on_duplicate,
             reauth,
-            return_media_text_content,
             media,
             media_name,
         } = body;
@@ -100,7 +99,6 @@ export const handler: BunextAPIRouteHandler<APIResponseObject> = async (
             media_type,
             is_primary: is_media_primary,
             update_on_duplicate,
-            extract_media_text_content: return_media_text_content,
             media,
             media_mime_type: ext,
             user: { id: target_user_id },