Add knowledgebases

Knowledgebases give bots RAG over documents, scoped like extensions: to
particular bots, to a workspace, or to every bot, with their own button
beside Tools in the composer. Documents are chunked and embedded by the
file-ingest worker with the install's embedding model, which is now an
install-wide setting rather than a per-bot one.

- Word search runs on an FTS5 index ranked by BM25, with a scored LIKE
  fallback for scripts written without spaces.
- Changing the embedding model re-indexes documents automatically.
- Ingest jobs wait without spending attempts while every embedding model
  rests, fail at once on errors retrying can't fix, and keep passages
  searchable by words when the model refuses.
- Settings > Knowledgebases shows each knowledgebase's and document's
  index state: spinner, warning, grey check (words only) or green check.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
2026-10-26 16:41:01 +01:00
co-authored by Claude Opus 5.5
parent 2259b6895f
commit e7b23b7454
111 changed files with 4573 additions and 148 deletions
@@ -1,10 +1,12 @@
import BunSQLite from "@moduletrace/bun-sqlite";
import type {
BUN_SQLITE_COBBLE_CUSTOM_TOOLS,
BUN_SQLITE_COBBLE_KNOWLEDGEBASES,
BUN_SQLITE_COBBLE_MCP_SERVERS,
BUN_SQLITE_COBBLE_SKILLS,
} from "@/db/types/db";
import botExtensionsSql from "@/src/utils/bot-extensions-sql";
import parseKnowledgebaseRow from "../knowledgebases/parse-knowledgebase-row";
import parseCustomToolRow from "./parse-custom-tool-row";
import parseMcpServerRow from "./parse-mcp-server-row";
import parseSkillRow from "./parse-skill-row";
@@ -15,19 +17,23 @@ type Params = {
};
/**
* The MCP servers, custom tools and skills a bot gets on one run
* The MCP servers, custom tools, skills and knowledgebases a bot gets on one run
* (`botExtensionsSql`): every bot's, its own, and its workspace's there.
*/
export default async function grabBotExtensions({ bot_id, workspace_id }: Params) {
const [servers, tools, skills] = await Promise.all([
const [servers, tools, skills, knowledgebases] = await Promise.all([
BunSQLite.sql<BUN_SQLITE_COBBLE_MCP_SERVERS>(botExtensionsSql({ kind: "mcp", bot_id, workspace_id })),
BunSQLite.sql<BUN_SQLITE_COBBLE_CUSTOM_TOOLS>(botExtensionsSql({ kind: "tool", bot_id, workspace_id })),
BunSQLite.sql<BUN_SQLITE_COBBLE_SKILLS>(botExtensionsSql({ kind: "skill", bot_id, workspace_id })),
BunSQLite.sql<BUN_SQLITE_COBBLE_KNOWLEDGEBASES>(
botExtensionsSql({ kind: "knowledgebase", bot_id, workspace_id }),
),
]);
return {
servers: (servers.payload || []).map((row) => parseMcpServerRow({ row })),
tools: (tools.payload || []).map((row) => parseCustomToolRow({ row })),
skills: (skills.payload || []).map((row) => parseSkillRow({ row })),
knowledgebases: (knowledgebases.payload || []).map((row) => parseKnowledgebaseRow({ row })),
};
}