Release 0.4.11 (#1008 )

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
fix: llama parse input spreadsheet (#1007 )
2026-07-10 15:53:42 -04:00 · 2024-07-02 15:07:03 -07:00 · 2024-07-02 14:48:51 -07:00 · 2024-07-02 00:40:45 -07:00
25 changed files with 233 additions and 121 deletions
@@ -0,0 +1,28 @@
+name: Publish Preview
+on: [pull_request]
+
+jobs:
+  pre_release:
+    name: Pre Release
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v3
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: ".nvmrc"
+          cache: "pnpm"
+
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Build
+        run: pnpm run build
+
+      - name: Pre Release
+        run: pnpx pkg-pr-new publish ./packages/*
@@ -1,5 +1,12 @@
 # docs

+## 0.0.37
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.0.36

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "docs",
-  "version": "0.0.36",
+  "version": "0.0.37",
  "private": true,
  "scripts": {
    "docusaurus": "docusaurus",
@@ -1,5 +1,13 @@
 # @llamaindex/autotool-02-next-example

+## 0.1.21
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+  - @llamaindex/autotool@1.0.0
+
 ## 0.1.20

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/autotool-02-next-example",
  "private": true,
-  "version": "0.1.20",
+  "version": "0.1.21",
  "scripts": {
    "dev": "next dev",
    "build": "next build",
@@ -51,7 +51,7 @@
    "unplugin": "^1.10.1"
  },
  "peerDependencies": {
-    "llamaindex": "^0.4.10",
+    "llamaindex": "^0.4.11",
    "openai": "^4",
    "typescript": "^4"
  },
@@ -1,5 +1,12 @@
 # @llamaindex/community

+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.0.14

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/community",
  "description": "Community package for LlamaIndexTS",
-  "version": "0.0.14",
+  "version": "0.0.15",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
@@ -1,5 +1,12 @@
 # @llamaindex/experimental

+## 0.0.46
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.0.45

 ### Patch Changes
@@ -1,7 +1,7 @@
 {
  "name": "@llamaindex/experimental",
  "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.45",
+  "version": "0.0.46",
  "type": "module",
  "types": "dist/type/index.d.ts",
  "main": "dist/cjs/index.js",
@@ -1,5 +1,11 @@
 # llamaindex

+## 0.4.11
+
+### Patch Changes
+
+- 8bf5b4a: fix: llama parse input spreadsheet
+
 ## 0.4.10

 ### Patch Changes
@@ -1,5 +1,12 @@
 # @llamaindex/cloudflare-worker-agent-test

+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.0.29

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.29",
+  "version": "0.0.30",
  "type": "module",
  "private": true,
  "scripts": {
@@ -1,5 +1,12 @@
 # @llamaindex/next-agent-test

+## 0.1.30
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.1.29

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/next-agent-test",
-  "version": "0.1.29",
+  "version": "0.1.30",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,12 @@
 # test-edge-runtime

+## 0.1.29
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.1.28

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.28",
+  "version": "0.1.29",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,12 @@
 # @llamaindex/next-node-runtime

+## 0.0.11
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.0.10

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.0.10",
+  "version": "0.0.11",
  "private": true,
  "scripts": {
    "dev": "next dev",
@@ -1,5 +1,12 @@
 # @llamaindex/waku-query-engine-test

+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [8bf5b4a]
+  - llamaindex@0.4.11
+
 ## 0.0.29

 ### Patch Changes
@@ -1,6 +1,6 @@
 {
  "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.29",
+  "version": "0.0.30",
  "type": "module",
  "private": true,
  "scripts": {
@@ -1,6 +1,6 @@
 {
  "name": "llamaindex",
-  "version": "0.4.10",
+  "version": "0.4.11",
  "license": "MIT",
  "type": "module",
  "keywords": [
@@ -1,105 +1,100 @@
 import { Document } from "@llamaindex/core/schema";
 import { fs, getEnv } from "@llamaindex/env";
-import { filetypemime } from "magic-bytes.js";
+import { filetypeinfo } from "magic-bytes.js";
 import { FileReader, type Language, type ResultType } from "./type.js";

-const SupportedFiles: { [key: string]: string } = {
-  ".pdf": "application/pdf",
-  // Documents and Presentations
-  ".602": "application/x-t602",
-  ".abw": "application/x-abiword",
-  ".cgm": "image/cgm",
-  ".cwk": "application/x-cwk",
-  ".doc": "application/msword",
-  ".docx":
-    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-  ".docm": "application/vnd.ms-word.document.macroEnabled.12",
-  ".dot": "application/msword",
-  ".dotm": "application/vnd.ms-word.template.macroEnabled.12",
-  ".dotx":
-    "application/vnd.openxmlformats-officedocument.wordprocessingml.template",
-  ".hwp": "application/x-hwp",
-  ".key": "application/x-iwork-keynote-sffkey",
-  ".lwp": "application/vnd.lotus-wordpro",
-  ".mw": "application/macwriteii",
-  ".mcw": "application/macwriteii",
-  ".pages": "application/x-iwork-pages-sffpages",
-  ".pbd": "application/x-pagemaker",
-  ".ppt": "application/vnd.ms-powerpoint",
-  ".pptm": "application/vnd.ms-powerpoint.presentation.macroEnabled.12",
-  ".pptx":
-    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
-  ".pot": "application/vnd.ms-powerpoint",
-  ".potm": "application/vnd.ms-powerpoint.template.macroEnabled.12",
-  ".potx":
-    "application/vnd.openxmlformats-officedocument.presentationml.template",
-  ".rtf": "application/rtf",
-  ".sda": "application/vnd.stardivision.draw",
-  ".sdd": "application/vnd.stardivision.impress",
-  ".sdp": "application/sdp",
-  ".sdw": "application/vnd.stardivision.writer",
-  ".sgl": "application/vnd.stardivision.writer",
-  ".sti": "application/vnd.sun.xml.impress.template",
-  ".sxi": "application/vnd.sun.xml.impress",
-  ".sxw": "application/vnd.sun.xml.writer",
-  ".stw": "application/vnd.sun.xml.writer.template",
-  ".sxg": "application/vnd.sun.xml.writer.global",
-  ".txt": "text/plain",
-  ".uof": "application/vnd.uoml+xml",
-  ".uop": "application/vnd.openofficeorg.presentation",
-  ".uot": "application/x-uo",
-  ".vor": "application/vnd.stardivision.writer",
-  ".wpd": "application/wordperfect",
-  ".wps": "application/vnd.ms-works",
-  ".xml": "application/xml",
-  ".zabw": "application/x-abiword",
-  // Images
-  ".epub": "application/epub+zip",
-  ".jpg": "image/jpeg",
-  ".jpeg": "image/jpeg",
-  ".png": "image/png",
-  ".gif": "image/gif",
-  ".bmp": "image/bmp",
-  ".svg": "image/svg+xml",
-  ".tiff": "image/tiff",
-  ".webp": "image/webp",
-  // Web
-  ".htm": "text/html",
-  ".html": "text/html",
-  // Spreadsheets
-  ".xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-  ".xls": "application/vnd.ms-excel",
-  ".xlsm": "application/vnd.ms-excel.sheet.macroEnabled.12",
-  ".xlsb": "application/vnd.ms-excel.sheet.binary.macroEnabled.12",
-  ".xlw": "application/vnd.ms-excel",
-  ".csv": "text/csv",
-  ".dif": "application/x-dif",
-  ".sylk": "text/vnd.sylk",
-  ".slk": "text/vnd.sylk",
-  ".prn": "application/x-prn",
-  ".numbers": "application/x-iwork-numbers-sffnumbers",
-  ".et": "application/vnd.ms-excel",
-  ".ods": "application/vnd.oasis.opendocument.spreadsheet",
-  ".fods": "application/vnd.oasis.opendocument.spreadsheet",
-  ".uos1": "application/vnd.uoml+xml",
-  ".uos2": "application/vnd.uoml+xml",
-  ".dbf": "application/vnd.dbf",
-  ".wk1": "application/vnd.lotus-1-2-3",
-  ".wk2": "application/vnd.lotus-1-2-3",
-  ".wk3": "application/vnd.lotus-1-2-3",
-  ".wk4": "application/vnd.lotus-1-2-3",
-  ".wks": "application/vnd.lotus-1-2-3",
-  ".123": "application/vnd.lotus-1-2-3",
-  ".wq1": "application/x-lotus",
-  ".wq2": "application/x-lotus",
-  ".wb1": "application/x-quattro-pro",
-  ".wb2": "application/x-quattro-pro",
-  ".wb3": "application/x-quattro-pro",
-  ".qpw": "application/x-quattro-pro",
-  ".xlr": "application/vnd.ms-works",
-  ".eth": "application/ethos",
-  ".tsv": "text/tab-separated-values",
-};
+const SUPPORT_FILE_EXT: string[] = [
+  ".pdf",
+  // document and presentations
+  ".602",
+  ".abw",
+  ".cgm",
+  ".cwk",
+  ".doc",
+  ".docx",
+  ".docm",
+  ".dot",
+  ".dotm",
+  ".hwp",
+  ".key",
+  ".lwp",
+  ".mw",
+  ".mcw",
+  ".pages",
+  ".pbd",
+  ".ppt",
+  ".pptm",
+  ".pptx",
+  ".pot",
+  ".potm",
+  ".potx",
+  ".rtf",
+  ".sda",
+  ".sdd",
+  ".sdp",
+  ".sdw",
+  ".sgl",
+  ".sti",
+  ".sxi",
+  ".sxw",
+  ".stw",
+  ".sxg",
+  ".txt",
+  ".uof",
+  ".uop",
+  ".uot",
+  ".vor",
+  ".wpd",
+  ".wps",
+  ".xml",
+  ".zabw",
+  ".epub",
+  // images
+  ".jpg",
+  ".jpeg",
+  ".png",
+  ".gif",
+  ".bmp",
+  ".svg",
+  ".tiff",
+  ".webp",
+  // web
+  ".htm",
+  ".html",
+  // spreadsheets
+  ".xlsx",
+  ".xls",
+  ".xlsm",
+  ".xlsb",
+  ".xlw",
+  ".csv",
+  ".dif",
+  ".sylk",
+  ".slk",
+  ".prn",
+  ".numbers",
+  ".et",
+  ".ods",
+  ".fods",
+  ".uos1",
+  ".uos2",
+  ".dbf",
+  ".wk1",
+  ".wk2",
+  ".wk3",
+  ".wk4",
+  ".wks",
+  ".123",
+  ".wq1",
+  ".wq2",
+  ".wb1",
+  ".wb2",
+  ".wb3",
+  ".qpw",
+  ".xlr",
+  ".eth",
+  ".tsv",
+];

 /**
 * Represents a reader for parsing files using the LlamaParse API.
@@ -165,7 +160,7 @@ export class LlamaParseReader extends FileReader {
    fileName?: string,
  ): Promise<string> {
    // Load data, set the mime type
-    const { mimeType, extension } = await this.getMimeType(data);
+    const { mime, extension } = await LlamaParseReader.getMimeType(data);

    if (this.verbose) {
      const name = fileName ? fileName : extension;
@@ -173,7 +168,7 @@ export class LlamaParseReader extends FileReader {
    }

    const body = new FormData();
-    body.set("file", new Blob([data], { type: mimeType }), fileName);
+    body.set("file", new Blob([data], { type: mime }), fileName);

    const LlamaParseBodyParams = {
      language: this.language,
@@ -378,19 +373,23 @@ export class LlamaParseReader extends FileReader {
    return images;
  }

-  private async getMimeType(
+  static async getMimeType(
    data: Uint8Array,
-  ): Promise<{ mimeType: string; extension: string }> {
-    const mimes = filetypemime(data); // Get an array of possible MIME types
-    const extension = Object.keys(SupportedFiles).find(
-      (ext) => SupportedFiles[ext] === mimes[0],
-    ); // Find the extension for the first MIME type
-    if (!extension) {
-      const supportedExtensions = Object.keys(SupportedFiles).join(", ");
+  ): Promise<{ mime: string; extension: string }> {
+    const typeinfos = filetypeinfo(data);
+    // find the first type info that matches the supported MIME types
+    // It could be happened that docx file is recognized as zip file, so we need to check the mime type
+    const info = typeinfos.find((info) => {
+      if (info.extension && SUPPORT_FILE_EXT.includes(`.${info.extension}`)) {
+        return info;
+      }
+    });
+    if (!info || !info.mime || !info.extension) {
+      const ext = SUPPORT_FILE_EXT.join(", ");
      throw new Error(
-        `File has type "${mimes[0]}" which does not match supported MIME Types. Supported formats include: ${supportedExtensions}`,
+        `File has type which does not match supported MIME Types. Supported formats include: ${ext}`,
      );
    }
-    return { mimeType: mimes[0], extension }; // Return the first MIME type and its corresponding extension
+    return { mime: info.mime, extension: info.extension };
  }
 }
@@ -0,0 +1,15 @@
+import { LlamaParseReader } from "llamaindex";
+import { readFile } from "node:fs/promises";
+import { join } from "node:path";
+import { fileURLToPath } from "node:url";
+import { expect, test } from "vitest";
+
+const fixturesDir = fileURLToPath(new URL("./fixtures", import.meta.url));
+
+test("file type should be detected correctly", async () => {
+  const xlsx = join(fixturesDir, "test.xlsx");
+  const buffer = await readFile(xlsx);
+  const { mime, extension } = await LlamaParseReader.getMimeType(buffer);
+  expect(mime).toBe("application/vnd.oasis.opendocument.spreadsheet");
+  expect(extension).toBe("ods");
+});
Author	SHA1	Message	Date
github-actions[bot]	e0af059221	Release 0.4.11 (#1008 ) Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2024-07-02 15:07:03 -07:00
Alex Yang	8bf5b4acfd	fix: llama parse input spreadsheet (#1007 )	2024-07-02 14:48:51 -07:00
Alex Yang	93a003baa0	ci: pre release (#1005 )	2024-07-02 00:40:45 -07:00