Add image index and pdf parse (#3956)

* feat: think tag parse

* feat: parse think tag test

* feat: pdf parse ux

* feat: doc2x parse

* perf: rewrite training mode setting

* feat: image parse queue

* perf: image index

* feat: image parse process

* feat: add init sh

* fix: ts

packages/global/common/system/utils.ts

@@ -16,3 +16,24 @@ export const retryFn = async <T>(fn: () => Promise<T>, retryTimes = 3): Promise<
     return Promise.reject(error);
   }
 };
+
+export const batchRun = async <T>(arr: T[], fn: (arr: T) => any, batchSize = 10) => {
+  const batchArr = new Array(batchSize).fill(null);
+  const result: any[] = [];
+
+  const batchFn = async () => {
+    const data = arr.shift();
+    if (data) {
+      result.push(await fn(data));
+      return batchFn();
+    }
+  };
+
+  await Promise.all(
+    batchArr.map(async () => {
+      await batchFn();
+    })
+  );
+
+  return result;
+};