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]>
This commit is contained in:
Claude Opus 5.5
@@ -29,10 +29,9 @@ type Props = {
|
||||
|
||||
/**
|
||||
* The files a conversation works with: a bot's own folder, or the
|
||||
* workspace's shared one. Each can be opened, read again so it can be
|
||||
* searched, or deleted (a crew manager only). The list loads when the
|
||||
* modal opens, and search goes through the same endpoint, so the page
|
||||
* props stay small.
|
||||
* workspace's shared one. Each can be opened or deleted (a crew manager
|
||||
* only). The list loads when the modal opens, and search (by name or path)
|
||||
* goes through the same endpoint, so the page props stay small.
|
||||
*/
|
||||
export default function BotFilesModal({ bot, workspace, menu, on_open }: Props) {
|
||||
const { pageProps } = useContext(AppContext);
|
||||
@@ -105,7 +104,7 @@ export default function BotFilesModal({ bot, workspace, menu, on_open }: Props)
|
||||
<H2 className="text-lg! leading-6! tracking-normal! font-bold text-ink">{title}</H2>
|
||||
<Span className="text-[13px] leading-[18px] text-ink-secondary">
|
||||
{workspace?.id
|
||||
? `Files every bot here can read and search. They're kept with the app, not on a computer.`
|
||||
? `Files every bot here can find and read. They're kept with the app, not on a computer.`
|
||||
: `What ${name} has saved: documents you sent, files it wrote and images it made. They're kept with the app, not on a computer.${can_manage ? " Deleting one removes it for good." : ""}`}
|
||||
</Span>
|
||||
{usage ? (
|
||||
@@ -128,7 +127,7 @@ export default function BotFilesModal({ bot, workspace, menu, on_open }: Props)
|
||||
|
||||
<Stack className="w-full mt-4 gap-2! items-stretch">
|
||||
<Input
|
||||
placeholder="Search files"
|
||||
placeholder="Search by name or path"
|
||||
value={search}
|
||||
onChange={(event) => setSearch(event.target.value)}
|
||||
onKeyDown={(event) => {
|
||||
@@ -146,14 +145,6 @@ export default function BotFilesModal({ bot, workspace, menu, on_open }: Props)
|
||||
file={file}
|
||||
can_manage={can_manage}
|
||||
busy={busy_id == file.id}
|
||||
onIngest={() =>
|
||||
run({
|
||||
url: `/api/admin/bots/ingest-file`,
|
||||
payload: { file_id: file.id },
|
||||
file_id: file.id,
|
||||
done: `${file.name} will be read again shortly.`,
|
||||
})
|
||||
}
|
||||
onDelete={() =>
|
||||
run({
|
||||
url: `/api/admin/bots/delete-file`,
|
||||
|
||||
@@ -3,7 +3,7 @@ import Row from "@moduletrace/twui/layout/Row";
|
||||
import Span from "@moduletrace/twui/layout/Span";
|
||||
import Stack from "@moduletrace/twui/layout/Stack";
|
||||
import Button from "@moduletrace/twui/layout/Button";
|
||||
import { RefreshCw, Trash2 } from "lucide-react";
|
||||
import { Trash2 } from "lucide-react";
|
||||
import type { MediaType, PublicBotFile } from "@/src/types";
|
||||
import relativeTime from "@/src/utils/relative-time";
|
||||
import AttachmentIcon from "./attachment-icon";
|
||||
@@ -11,19 +11,18 @@ import AttachmentIcon from "./attachment-icon";
|
||||
type Props = {
|
||||
file: PublicBotFile;
|
||||
/**
|
||||
* A crew manager may delete and re-ingest.
|
||||
* A crew manager may delete it.
|
||||
*/
|
||||
can_manage: boolean;
|
||||
busy?: boolean;
|
||||
onIngest: () => void;
|
||||
onDelete: () => void;
|
||||
};
|
||||
|
||||
/**
|
||||
* One file in the files modal: its type, path, size and age, and what can
|
||||
* be done with it. A file that isn't searchable says why.
|
||||
* be done with it.
|
||||
*/
|
||||
export default function FileRow({ file, can_manage, busy, onIngest, onDelete }: Props) {
|
||||
export default function FileRow({ file, can_manage, busy, onDelete }: Props) {
|
||||
return (
|
||||
<Row className="w-full gap-3! flex-nowrap items-start py-2 border-0 border-b border-solid border-hairline last:border-b-0">
|
||||
<Row className="mt-0.5 text-ink-secondary">
|
||||
@@ -44,11 +43,6 @@ export default function FileRow({ file, can_manage, busy, onIngest, onDelete }:
|
||||
file.scope == "workspace" ? "Workspace" : "Bot files",
|
||||
`${Math.max(1, Math.round(file.size / 1024))} KB`,
|
||||
file.created_at ? relativeTime({ at: file.created_at }) : "",
|
||||
file.ingest_error
|
||||
? file.ingest_error
|
||||
: file.ingested_at
|
||||
? "searchable"
|
||||
: "not searchable yet",
|
||||
]
|
||||
.filter(Boolean)
|
||||
.join(" · ")}
|
||||
@@ -56,19 +50,6 @@ export default function FileRow({ file, can_manage, busy, onIngest, onDelete }:
|
||||
</Stack>
|
||||
{can_manage ? (
|
||||
<Row className="shrink-0 gap-0!">
|
||||
<Button
|
||||
title="Read it again so it can be searched"
|
||||
aria-label="Reingest"
|
||||
type="button"
|
||||
variant="ghost"
|
||||
color="gray"
|
||||
size="small"
|
||||
disabled={busy}
|
||||
onClick={onIngest}
|
||||
className="p-1.5!"
|
||||
>
|
||||
<RefreshCw size={14} aria-hidden />
|
||||
</Button>
|
||||
<Button
|
||||
title="Delete it"
|
||||
aria-label="Delete"
|
||||
|
||||
@@ -14,7 +14,7 @@ type Props = {
|
||||
export default function FilesSearchInput({ value, loading, onChange, onSubmit }: Props) {
|
||||
return (
|
||||
<Input
|
||||
placeholder="Search this folder"
|
||||
placeholder="Search this folder by name"
|
||||
value={value}
|
||||
disabled={loading}
|
||||
onChange={(event) => onChange(event.target.value)}
|
||||
|
||||
@@ -4,7 +4,7 @@ import type { DatabaseTableSummary } from "@/src/types";
|
||||
import DatabaseTableRow from "./database-table-row";
|
||||
|
||||
const table: DatabaseTableSummary = {
|
||||
name: "bot_file_vectors",
|
||||
name: "knowledgebase_vectors",
|
||||
type: "virtual",
|
||||
rows: 12,
|
||||
size_bytes: 2048,
|
||||
@@ -16,7 +16,7 @@ describe("DatabaseTableRow", () => {
|
||||
test("names the table, its record count and its size", () => {
|
||||
const html = renderToString(<DatabaseTableRow table={table} selected={false} onOpen={() => {}} />);
|
||||
|
||||
expect(html).toContain("bot_file_vectors");
|
||||
expect(html).toContain("knowledgebase_vectors");
|
||||
expect(html).toContain("12");
|
||||
expect(html).toContain("2.0 KB");
|
||||
});
|
||||
@@ -24,7 +24,7 @@ describe("DatabaseTableRow", () => {
|
||||
test("links to the table's own address", () => {
|
||||
const html = renderToString(<DatabaseTableRow table={table} selected={false} onOpen={() => {}} />);
|
||||
|
||||
expect(html).toContain(`href="/admin/settings/database?table=bot_file_vectors"`);
|
||||
expect(html).toContain(`href="/admin/settings/database?table=knowledgebase_vectors"`);
|
||||
});
|
||||
|
||||
test("a table with no count yet shows a dash", () => {
|
||||
|
||||
Reference in New Issue
Block a user