External dataset (#1497)

* perf: read rawText and chunk code

* perf: read raw text

* perf: read rawtext

* perf: token count

* log

packages/global/common/system/types/index.d.ts

@@ -66,6 +66,8 @@ export type SystemEnvType = {
   vectorMaxProcess: number;
   qaMaxProcess: number;
   pgHNSWEfSearch: number;
+  tokenWorkers: number; // token count max worker
+
   oneapiUrl?: string;
   chatApiKey?: string;
 };