Feat: pptx and xlsx loader (#1118)

* perf: plan tip

* perf: upload size controller

* feat: add image ttl index

* feat: new upload file ux

* remove file

* feat: support read pptx

* feat: support xlsx

* fix: rerank docker flie

packages/service/common/file/read/word.ts

@@ -0,0 +1,35 @@
+import mammoth from 'mammoth';
+import { htmlToMarkdown } from '../../string/markdown';
+import { ReadFileByBufferParams, ReadFileResponse } from './type';
+import { initMarkdownText } from './utils';
+
+/**
+ * read docx to markdown
+ */
+export const readWordFile = async ({
+  teamId,
+  buffer,
+  metadata = {}
+}: ReadFileByBufferParams): Promise<ReadFileResponse> => {
+  try {
+    const { value: html } = await mammoth.convertToHtml({
+      buffer
+    });
+
+    const md = await htmlToMarkdown(html);
+
+    const rawText = await initMarkdownText({
+      teamId,
+      md,
+      metadata
+    });
+
+    return {
+      rawText,
+      metadata: {}
+    };
+  } catch (error) {
+    console.log('error doc read:', error);
+    return Promise.reject('Can not read doc file, please convert to PDF');
+  }
+};