cr

examples-ts/classify/.gitignore

@@ -1,21 +0,0 @@
-node_modules
-package-lock.json
-yarn.lock
-
-.DS_Store
-.cache
-.env
-.vercel
-.output
-.nitro
-/build/
-/api/
-/server/build
-/public/build# Sentry Config File
-.env.sentry-build-plugin
-/test-results/
-/playwright-report/
-/blob-report/
-/playwright/.cache/
-.tanstack
-.vscode

examples-ts/classify/.prettierignore

@@ -1,4 +0,0 @@
-**/build
-**/public
-pnpm-lock.yaml
-routeTree.gen.ts

examples-ts/classify/README.md

@@ -1,88 +0,0 @@
-# LlamaClassify Demo
-
-A TypeScript demo application showcasing the power of **LlamaClassify** - an agentic documents classification service from [LlamaCloud](https://cloud.llamaindex.ai). This demo allows you to classify financial documents among three different types (Cash flow statement, Income Statement and Balance Sheet).
-
-## Table of Contents
-
-- [Features](#features)
-- [Prerequisites](#prerequisites)
-- [Installation](#installation)
-- [Usage](#usage)
-  - [Start the Demo](#start-the-demo)
-- [How It Works](#how-it-works)
-- [Troubleshooting](#troubleshooting)
-  - [Common Issues](#common-issues)
-- [License](#license)
-- [Contributing](#contributing)
-
-## Features
-
-- 📄 **Documemt Classification**: Classify files based on well-defined rules you can customized and play around with.
-- 🤖 **Reasoning-based Actionable Insights**: Get in-depth, reasoning based insights on the document classification, accompanied by confidence scores.
-- 🎨 **Beautiful UI**: [DaisyUI](https://daisyui.com)-based interface powered by [TanStack](https://tanstack.com)
-- ⚡ **Fast Development**: Hot reload support with development mode
-- 🛠️ **TypeScript**: Full TypeScript support with strict type checking
-
-## Prerequisites
-
-- Node.js (version 22 or higher)
-- pnpm package manager
-- LlamaCloud API key
-
-## Installation
-
-1. Clone the repository:
-
-```bash
-git clone https://github.com/run-llama/llama_cloud_services
-cd lama_cloud_services/examples-ts/classify/
-```
-
-2. Install dependencies:
-
-```bash
-npm install
-```
-
-3. Set up your environment variables:
-
-```bash
-# Add your API key to your environment
-export LLAMA_CLOUD_API_KEY="your-llamacloud-api-key"
-```
-
-## Usage
-
-### Start the Demo
-
-```bash
-npm run dev
-```
-
-The application will be up and running on http://localhost:3000
-
-## How It Works
-
-1. **Document Input**: Enter the path to your document when prompted
-2. **Parsing**: LlamaClassify, based on the rules you can find [here](./src/utils/classifier.ts), processes the document and classifies it
-3. **Results**: The classification outcome, as well as the reasoning behind it and the confidence score, are displayed in the UI.
-
-## Troubleshooting
-
-### Common Issues
-
-1. **Module Resolution Errors**: Ensure you're using Node.js 22+ and have all dependencies installed
-2. **API Key Issues**: Verify your LlamaCloud API key is correctly set
-3. **File Path Errors**: Use absolute paths or ensure relative paths are correct from the project root
-
-## License
-
-MIT License - see the [LICENSE](../../LICENSE) file for details.
-
-## Contributing
-
-1. Fork the repository
-2. Create a feature branch
-3. Make your changes
-4. Run `npm run format` and `npm run lint`
-5. Submit a pull request

examples-ts/classify/package.json

@@ -1,34 +0,0 @@
-{
-  "name": "tanstack-start-example-basic",
-  "private": true,
-  "sideEffects": false,
-  "type": "module",
-  "scripts": {
-    "dev": "vite dev",
-    "build": "vite build && tsc --noEmit",
-    "start": "node .output/server/index.mjs"
-  },
-  "dependencies": {
-    "@tanstack/react-router": "^1.133.22",
-    "@tanstack/react-router-devtools": "^1.133.22",
-    "@tanstack/react-start": "^1.133.22",
-    "llama-cloud-services": "^0.3.10",
-    "react": "^19.0.0",
-    "react-dom": "^19.0.0",
-    "tailwind-merge": "^2.6.0",
-    "zod": "^3.24.2"
-  },
-  "devDependencies": {
-    "@tailwindcss/postcss": "^4.1.15",
-    "@types/node": "^22.5.4",
-    "@types/react": "^19.0.8",
-    "@types/react-dom": "^19.0.3",
-    "@vitejs/plugin-react": "^4.6.0",
-    "daisyui": "^5.3.7",
-    "postcss": "^8.5.1",
-    "tailwindcss": "^4.1.15",
-    "typescript": "^5.7.2",
-    "vite": "^7.1.7",
-    "vite-tsconfig-paths": "^5.1.4"
-  }
-}

examples-ts/classify/postcss.config.mjs

@@ -1,5 +0,0 @@
-export default {
-  plugins: {
-    '@tailwindcss/postcss': {},
-  },
-}

examples-ts/classify/public/site.webmanifest

@@ -1,19 +0,0 @@
-{
-  "name": "",
-  "short_name": "",
-  "icons": [
-    {
-      "src": "/android-chrome-192x192.png",
-      "sizes": "192x192",
-      "type": "image/png"
-    },
-    {
-      "src": "/android-chrome-512x512.png",
-      "sizes": "512x512",
-      "type": "image/png"
-    }
-  ],
-  "theme_color": "#ffffff",
-  "background_color": "#ffffff",
-  "display": "standalone"
-}

examples-ts/classify/src/components/DefaultCatchBoundary.tsx

@@ -1,53 +0,0 @@
-import {
-  ErrorComponent,
-  Link,
-  rootRouteId,
-  useMatch,
-  useRouter,
-} from '@tanstack/react-router'
-import type { ErrorComponentProps } from '@tanstack/react-router'
-
-export function DefaultCatchBoundary({ error }: ErrorComponentProps) {
-  const router = useRouter()
-  const isRoot = useMatch({
-    strict: false,
-    select: (state) => state.id === rootRouteId,
-  })
-
-  console.error('DefaultCatchBoundary Error:', error)
-
-  return (
-    <div className="min-w-0 flex-1 p-4 flex flex-col items-center justify-center gap-6">
-      <ErrorComponent error={error} />
-      <div className="flex gap-2 items-center flex-wrap">
-        <button
-          onClick={() => {
-            router.invalidate()
-          }}
-          className={`px-2 py-1 bg-gray-600 dark:bg-gray-700 rounded-sm text-white uppercase font-extrabold`}
-        >
-          Try Again
-        </button>
-        {isRoot ? (
-          <Link
-            to="/"
-            className={`px-2 py-1 bg-gray-600 dark:bg-gray-700 rounded-sm text-white uppercase font-extrabold`}
-          >
-            Home
-          </Link>
-        ) : (
-          <Link
-            to="/"
-            className={`px-2 py-1 bg-gray-600 dark:bg-gray-700 rounded-sm text-white uppercase font-extrabold`}
-            onClick={(e) => {
-              e.preventDefault()
-              window.history.back()
-            }}
-          >
-            Go Back
-          </Link>
-        )}
-      </div>
-    </div>
-  )
-}

examples-ts/classify/src/components/NotFound.tsx

@@ -1,25 +0,0 @@
-import { Link } from '@tanstack/react-router'
-
-export function NotFound({ children }: { children?: any }) {
-  return (
-    <div className="space-y-2 p-2">
-      <div className="text-gray-600 dark:text-gray-400">
-        {children || <p>The page you are looking for does not exist.</p>}
-      </div>
-      <p className="flex items-center gap-2 flex-wrap">
-        <button
-          onClick={() => window.history.back()}
-          className="bg-emerald-500 text-white px-2 py-1 rounded-sm uppercase font-black text-sm"
-        >
-          Go back
-        </button>
-        <Link
-          to="/"
-          className="bg-cyan-600 text-white px-2 py-1 rounded-sm uppercase font-black text-sm"
-        >
-          Start Over
-        </Link>
-      </p>
-    </div>
-  )
-}

examples-ts/classify/src/routeTree.gen.ts

@@ -1,225 +0,0 @@
-/* eslint-disable */
-
-// @ts-nocheck
-
-// noinspection JSUnusedGlobalSymbols
-
-// This file was automatically generated by TanStack Router.
-// You should NOT make any changes in this file as it will be overwritten.
-// Additionally, you should also exclude this file from your linter and/or formatter to prevent it from being checked or modified.
-
-import { Route as rootRouteImport } from './routes/__root'
-import { Route as UsersRouteImport } from './routes/users'
-import { Route as IndexRouteImport } from './routes/index'
-import { Route as UsersIndexRouteImport } from './routes/users.index'
-import { Route as PostsIndexRouteImport } from './routes/posts.index'
-import { Route as UsersUserIdRouteImport } from './routes/users.$userId'
-import { Route as PostsPostIdRouteImport } from './routes/posts.$postId'
-import { Route as ApiClassifyRouteImport } from './routes/api/classify'
-import { Route as PostsPostIdDeepRouteImport } from './routes/posts_.$postId.deep'
-
-const UsersRoute = UsersRouteImport.update({
-  id: '/users',
-  path: '/users',
-  getParentRoute: () => rootRouteImport,
-} as any)
-const IndexRoute = IndexRouteImport.update({
-  id: '/',
-  path: '/',
-  getParentRoute: () => rootRouteImport,
-} as any)
-const UsersIndexRoute = UsersIndexRouteImport.update({
-  id: '/',
-  path: '/',
-  getParentRoute: () => UsersRoute,
-} as any)
-const PostsIndexRoute = PostsIndexRouteImport.update({
-  id: '/posts/',
-  path: '/posts/',
-  getParentRoute: () => rootRouteImport,
-} as any)
-const UsersUserIdRoute = UsersUserIdRouteImport.update({
-  id: '/$userId',
-  path: '/$userId',
-  getParentRoute: () => UsersRoute,
-} as any)
-const PostsPostIdRoute = PostsPostIdRouteImport.update({
-  id: '/posts/$postId',
-  path: '/posts/$postId',
-  getParentRoute: () => rootRouteImport,
-} as any)
-const ApiClassifyRoute = ApiClassifyRouteImport.update({
-  id: '/api/classify',
-  path: '/api/classify',
-  getParentRoute: () => rootRouteImport,
-} as any)
-const PostsPostIdDeepRoute = PostsPostIdDeepRouteImport.update({
-  id: '/posts_/$postId/deep',
-  path: '/posts/$postId/deep',
-  getParentRoute: () => rootRouteImport,
-} as any)
-
-export interface FileRoutesByFullPath {
-  '/': typeof IndexRoute
-  '/users': typeof UsersRouteWithChildren
-  '/api/classify': typeof ApiClassifyRoute
-  '/posts/$postId': typeof PostsPostIdRoute
-  '/users/$userId': typeof UsersUserIdRoute
-  '/posts': typeof PostsIndexRoute
-  '/users/': typeof UsersIndexRoute
-  '/posts/$postId/deep': typeof PostsPostIdDeepRoute
-}
-export interface FileRoutesByTo {
-  '/': typeof IndexRoute
-  '/api/classify': typeof ApiClassifyRoute
-  '/posts/$postId': typeof PostsPostIdRoute
-  '/users/$userId': typeof UsersUserIdRoute
-  '/posts': typeof PostsIndexRoute
-  '/users': typeof UsersIndexRoute
-  '/posts/$postId/deep': typeof PostsPostIdDeepRoute
-}
-export interface FileRoutesById {
-  __root__: typeof rootRouteImport
-  '/': typeof IndexRoute
-  '/users': typeof UsersRouteWithChildren
-  '/api/classify': typeof ApiClassifyRoute
-  '/posts/$postId': typeof PostsPostIdRoute
-  '/users/$userId': typeof UsersUserIdRoute
-  '/posts/': typeof PostsIndexRoute
-  '/users/': typeof UsersIndexRoute
-  '/posts_/$postId/deep': typeof PostsPostIdDeepRoute
-}
-export interface FileRouteTypes {
-  fileRoutesByFullPath: FileRoutesByFullPath
-  fullPaths:
-    | '/'
-    | '/users'
-    | '/api/classify'
-    | '/posts/$postId'
-    | '/users/$userId'
-    | '/posts'
-    | '/users/'
-    | '/posts/$postId/deep'
-  fileRoutesByTo: FileRoutesByTo
-  to:
-    | '/'
-    | '/api/classify'
-    | '/posts/$postId'
-    | '/users/$userId'
-    | '/posts'
-    | '/users'
-    | '/posts/$postId/deep'
-  id:
-    | '__root__'
-    | '/'
-    | '/users'
-    | '/api/classify'
-    | '/posts/$postId'
-    | '/users/$userId'
-    | '/posts/'
-    | '/users/'
-    | '/posts_/$postId/deep'
-  fileRoutesById: FileRoutesById
-}
-export interface RootRouteChildren {
-  IndexRoute: typeof IndexRoute
-  UsersRoute: typeof UsersRouteWithChildren
-  ApiClassifyRoute: typeof ApiClassifyRoute
-  PostsPostIdRoute: typeof PostsPostIdRoute
-  PostsIndexRoute: typeof PostsIndexRoute
-  PostsPostIdDeepRoute: typeof PostsPostIdDeepRoute
-}
-
-declare module '@tanstack/react-router' {
-  interface FileRoutesByPath {
-    '/users': {
-      id: '/users'
-      path: '/users'
-      fullPath: '/users'
-      preLoaderRoute: typeof UsersRouteImport
-      parentRoute: typeof rootRouteImport
-    }
-    '/': {
-      id: '/'
-      path: '/'
-      fullPath: '/'
-      preLoaderRoute: typeof IndexRouteImport
-      parentRoute: typeof rootRouteImport
-    }
-    '/users/': {
-      id: '/users/'
-      path: '/'
-      fullPath: '/users/'
-      preLoaderRoute: typeof UsersIndexRouteImport
-      parentRoute: typeof UsersRoute
-    }
-    '/posts/': {
-      id: '/posts/'
-      path: '/posts'
-      fullPath: '/posts'
-      preLoaderRoute: typeof PostsIndexRouteImport
-      parentRoute: typeof rootRouteImport
-    }
-    '/users/$userId': {
-      id: '/users/$userId'
-      path: '/$userId'
-      fullPath: '/users/$userId'
-      preLoaderRoute: typeof UsersUserIdRouteImport
-      parentRoute: typeof UsersRoute
-    }
-    '/posts/$postId': {
-      id: '/posts/$postId'
-      path: '/posts/$postId'
-      fullPath: '/posts/$postId'
-      preLoaderRoute: typeof PostsPostIdRouteImport
-      parentRoute: typeof rootRouteImport
-    }
-    '/api/classify': {
-      id: '/api/classify'
-      path: '/api/classify'
-      fullPath: '/api/classify'
-      preLoaderRoute: typeof ApiClassifyRouteImport
-      parentRoute: typeof rootRouteImport
-    }
-    '/posts_/$postId/deep': {
-      id: '/posts_/$postId/deep'
-      path: '/posts/$postId/deep'
-      fullPath: '/posts/$postId/deep'
-      preLoaderRoute: typeof PostsPostIdDeepRouteImport
-      parentRoute: typeof rootRouteImport
-    }
-  }
-}
-
-interface UsersRouteChildren {
-  UsersUserIdRoute: typeof UsersUserIdRoute
-  UsersIndexRoute: typeof UsersIndexRoute
-}
-
-const UsersRouteChildren: UsersRouteChildren = {
-  UsersUserIdRoute: UsersUserIdRoute,
-  UsersIndexRoute: UsersIndexRoute,
-}
-
-const UsersRouteWithChildren = UsersRoute._addFileChildren(UsersRouteChildren)
-
-const rootRouteChildren: RootRouteChildren = {
-  IndexRoute: IndexRoute,
-  UsersRoute: UsersRouteWithChildren,
-  ApiClassifyRoute: ApiClassifyRoute,
-  PostsPostIdRoute: PostsPostIdRoute,
-  PostsIndexRoute: PostsIndexRoute,
-  PostsPostIdDeepRoute: PostsPostIdDeepRoute,
-}
-export const routeTree = rootRouteImport
-  ._addFileChildren(rootRouteChildren)
-  ._addFileTypes<FileRouteTypes>()
-
-import type { getRouter } from './router.tsx'
-import type { createStart } from '@tanstack/react-start'
-declare module '@tanstack/react-start' {
-  interface Register {
-    ssr: true
-    router: Awaited<ReturnType<typeof getRouter>>
-  }
-}

examples-ts/classify/src/router.tsx

@@ -1,15 +0,0 @@
-import { createRouter } from '@tanstack/react-router'
-import { routeTree } from './routeTree.gen'
-import { DefaultCatchBoundary } from './components/DefaultCatchBoundary'
-import { NotFound } from './components/NotFound'
-
-export function getRouter() {
-  const router = createRouter({
-    routeTree,
-    defaultPreload: 'intent',
-    defaultErrorComponent: DefaultCatchBoundary,
-    defaultNotFoundComponent: () => <NotFound />,
-    scrollRestoration: true,
-  })
-  return router
-}

examples-ts/classify/src/routes/__root.tsx

@@ -1,128 +0,0 @@
-/// <reference types="vite/client" />
-import {
-  HeadContent,
-  Scripts,
-  createRootRoute,
-} from '@tanstack/react-router'
-import * as React from 'react'
-import { DefaultCatchBoundary } from '~/components/DefaultCatchBoundary'
-import { NotFound } from '~/components/NotFound'
-import { seo } from '~/utils/seo'
-
-export const Route = createRootRoute({
-  head: () => ({
-    meta: [
-      {
-        charSet: 'utf-8',
-      },
-      {
-        name: 'viewport',
-        content: 'width=device-width, initial-scale=1',
-      },
-      ...seo({
-        title:
-          'Financial Documents Classification Agent',
-        description: `Classify financial documents as balance sheets, income statements and cash flow statemets. `,
-      }),
-    ],
-    links: [
-      { rel: 'stylesheet', href: "https://cdn.jsdelivr.net/npm/daisyui@5" },
-      {
-        rel: 'apple-touch-icon',
-        sizes: '180x180',
-        href: '/apple-touch-icon.png',
-      },
-      {
-        rel: 'icon',
-        type: 'image/png',
-        sizes: '32x32',
-        href: '/favicon-32x32.png',
-      },
-      {
-        rel: 'icon',
-        type: 'image/png',
-        sizes: '16x16',
-        href: '/favicon-16x16.png',
-      },
-      { rel: 'manifest', href: '/site.webmanifest', color: '#fffff' },
-      { rel: 'icon', href: '/favicon.ico' },
-    ],
-    scripts: [
-      {
-        src: '/customScript.js',
-        type: 'text/javascript',
-      },
-      {
-        src: "https://cdn.jsdelivr.net/npm/@tailwindcss/browser@4",
-        type: "text/javascript",
-      }
-    ],
-  }),
-  errorComponent: DefaultCatchBoundary,
-  notFoundComponent: () => <NotFound />,
-  shellComponent: RootDocument,
-})
-
-function RootDocument({ children }: { children: React.ReactNode }) {
-  return (
-    <html>
-      <head>
-        <HeadContent />
-      </head>
-      <body>
-        <div className="navbar bg-base-100 shadow-sm">
-          <div className="navbar-start">
-            <div className="dropdown">
-              <div tabIndex={0} role="button" className="btn btn-ghost btn-circle">
-                <svg
-                  xmlns="http://www.w3.org/2000/svg"
-                  className="h-5 w-5"
-                  fill="none"
-                  viewBox="0 0 24 24"
-                  stroke="currentColor"
-                >
-                  <path
-                    strokeLinecap="round"
-                    strokeLinejoin="round"
-                    strokeWidth="2"
-                    d="M4 6h16M4 12h16M4 18h7"
-                  />
-                </svg>
-              </div>
-              <ul
-                tabIndex={0}
-                className="menu menu-lg dropdown-content bg-base-100 rounded-box z-1 mt-3 w-80 p-2 shadow"
-              >
-                <li><a href="/">Home</a></li>
-                <li><a href="https://cloud.llamaindex.ai">Get Started with LlamaCloud</a></li>
-                <li><a href="https://developers.llamaindex.ai/python/cloud/llamaclassify/getting_started/">LlamaClassify Docs</a></li>
-              </ul>
-            </div>
-          </div>
-          <div className="navbar-center">
-            <a className="btn btn-ghost text-xl" href="/">Financial Documents Classification Agent</a>
-          </div>
-          <div className="navbar-end">
-            <a href="https://github.com/run-llama/llama_cloud_services/main/blob/examples-ts/classify">
-              <button className="btn btn-ghost btn-circle">
-                <div className="indicator">
-                  <svg
-                    xmlns="http://www.w3.org/2000/svg"
-                    className="h-10 w-10"
-                    fill="currentColor"
-                    viewBox="0 0 640 512"
-                  >
-                    <path d="M237.9 461.4C237.9 463.4 235.6 465 232.7 465C229.4 465.3 227.1 463.7 227.1 461.4C227.1 459.4 229.4 457.8 232.3 457.8C235.3 457.5 237.9 459.1 237.9 461.4zM206.8 456.9C206.1 458.9 208.1 461.2 211.1 461.8C213.7 462.8 216.7 461.8 217.3 459.8C217.9 457.8 216 455.5 213 454.6C210.4 453.9 207.5 454.9 206.8 456.9zM251 455.2C248.1 455.9 246.1 457.8 246.4 460.1C246.7 462.1 249.3 463.4 252.3 462.7C255.2 462 257.2 460.1 256.9 458.1C256.6 456.2 253.9 454.9 251 455.2zM316.8 72C178.1 72 72 177.3 72 316C72 426.9 141.8 521.8 241.5 555.2C254.3 557.5 258.8 549.6 258.8 543.1C258.8 536.9 258.5 502.7 258.5 481.7C258.5 481.7 188.5 496.7 173.8 451.9C173.8 451.9 162.4 422.8 146 415.3C146 415.3 123.1 399.6 147.6 399.9C147.6 399.9 172.5 401.9 186.2 425.7C208.1 464.3 244.8 453.2 259.1 446.6C261.4 430.6 267.9 419.5 275.1 412.9C219.2 406.7 162.8 398.6 162.8 302.4C162.8 274.9 170.4 261.1 186.4 243.5C183.8 237 175.3 210.2 189 175.6C209.9 169.1 258 202.6 258 202.6C278 197 299.5 194.1 320.8 194.1C342.1 194.1 363.6 197 383.6 202.6C383.6 202.6 431.7 169 452.6 175.6C466.3 210.3 457.8 237 455.2 243.5C471.2 261.2 481 275 481 302.4C481 398.9 422.1 406.6 366.2 412.9C375.4 420.8 383.2 435.8 383.2 459.3C383.2 493 382.9 534.7 382.9 542.9C382.9 549.4 387.5 557.3 400.2 555C500.2 521.8 568 426.9 568 316C568 177.3 455.5 72 316.8 72zM169.2 416.9C167.9 417.9 168.2 420.2 169.9 422.1C171.5 423.7 173.8 424.4 175.1 423.1C176.4 422.1 176.1 419.8 174.4 417.9C172.8 416.3 170.5 415.6 169.2 416.9zM158.4 408.8C157.7 410.1 158.7 411.7 160.7 412.7C162.3 413.7 164.3 413.4 165 412C165.7 410.7 164.7 409.1 162.7 408.1C160.7 407.5 159.1 407.8 158.4 408.8zM190.8 444.4C189.2 445.7 189.8 448.7 192.1 450.6C194.4 452.9 197.3 453.2 198.6 451.6C199.9 450.3 199.3 447.3 197.3 445.4C195.1 443.1 192.1 442.8 190.8 444.4zM179.4 429.7C177.8 430.7 177.8 433.3 179.4 435.6C181 437.9 183.7 438.9 185 437.9C186.6 436.6 186.6 434 185 431.7C183.6 429.4 181 428.4 179.4 429.7z" />
-                  </svg>
-                </div>
-              </button>
-            </a>
-          </div>
-        </div>
-        <hr />
-        {children}
-        <Scripts />
-      </body>
-    </html>
-  )
-}

examples-ts/classify/src/routes/api/classify.ts

@@ -1,45 +0,0 @@
-import { createFileRoute } from '@tanstack/react-router'
-import { classifier, classificationRules, parsingConfig } from '~/utils/classifier'
-
-export const Route = createFileRoute('/api/classify')({
-  component: RouteComponent,
-  server: {
-      handlers: {
-        POST: async ({ request }) => {
-          const body = await request.formData()
-          const fl = body.get("file") as File;
-          if (!fl) {
-                return new Response(JSON.stringify({"result": "you need to provide a file"}))
-            }
-          const buff = await fl.arrayBuffer()
-          const rawRes = await classifier.classify(
-            classificationRules,
-            parsingConfig,
-            [new Uint8Array(buff)],
-          )
-          const results = rawRes.items
-          let classification = ""
-
-          for (const result of results) {
-            if ("result" in result && result.result) {
-                classification += `
-                    <div class="card bg-base-100 shadow-xl p-6 mb-4">
-                        <div class="space-y-3">
-                        <p><span class="font-semibold">📄 Document:</span> ${fl.name}</p>
-                        <p><span class="font-semibold">🏷️ Type:</span> <span class="badge badge-primary">${result.result.type}</span></p>
-                        <p><span class="font-semibold">📊 Confidence:</span> ${result.result.confidence*100}%</p>
-                        <p><span class="font-semibold">💭 Reasoning:</span> ${result.result.reasoning}</p>
-                        </div>
-                    </div>
-                `
-            }
-          }
-          return new Response(JSON.stringify({"result": classification}))
-        },
-      },
-    },
-})
-
-function RouteComponent() {
-  return
-}

examples-ts/classify/src/routes/index.tsx

@@ -1,99 +0,0 @@
-import { createFileRoute } from '@tanstack/react-router'
-import { useRef, useState } from 'react'
-
-export const Route = createFileRoute('/')({
-  component: Home,
-})
-
-function Home() {
-  const [file, setFile] = useState<null | File>(null)
-  const fileInputRef = useRef<HTMLInputElement>(null)
-  const [reply, setReply] = useState<null | string>(null)
-  const [loading, setLoading] = useState<boolean>(false)
-  const handleFileChange = (event: React.ChangeEvent<HTMLInputElement>) => {
-    const selectedFile = event.target.files?.[0]
-    if (selectedFile) {
-      setFile(selectedFile)
-    }
-  }
-  const handleClearFile = () => {
-    if (file) {
-      setFile(null)
-    }
-    if (fileInputRef.current) {
-      fileInputRef.current.value = ''
-    }
-    if (reply) {
-      setReply(null)
-    }
-  }
-
-  const handleClassify = async () => {
-    if (!file) return
-
-    if (reply) {
-      setReply(null)
-    }
-    setLoading(true)
-    try {
-      const formData = new FormData()
-      formData.append('file', file)
-
-      const res = await fetch('/api/classify', {
-        method: 'POST',
-        body: formData,
-      })
-
-      const data = await res.json()
-      setReply(data.result)
-    } catch (error) {
-      console.error('Error:', error)
-    } finally {
-      setLoading(false)
-    }
-  }
-
-  return (
-    <div className="flex flex-col justify-center items-center gap-y-8">
-        <br />
-        <h1 className="text-xl font-bold text-gray-700">AI-Powered finacial document classification</h1>
-        <h2 className="text-lg font-semibold text-gray-500">Need help sorting out the financial documents jungle? Let our classification agent handle it!</h2>
-        <fieldset className="fieldset bg-base-100 border-base-300 rounded-box w-200 border p-4">
-            <legend className="fieldset-legend text-lg">Upload your financial document here</legend>
-            <label className="label flex justify-center">
-                <input type="file" className="file-input" onChange={handleFileChange} accept='application/pdf' ref={fileInputRef} />
-            </label>
-        </fieldset>
-        {file && (
-          <div className="flex flex-col justify-center items-center gap-y-8">
-          <p className="text-sm text-gray-600">Selected file: {file.name}</p>
-          <div className='grid grid-cols-2 gap-x-6'>
-            <button
-                type="button"
-                className='btn bg-gray-500 text-white shadow-lg hover:bg-gray-600 hover:shadow-xl rounded'
-                onClick={handleClassify}
-            >
-            Classify
-            </button>
-            <button
-                  onClick={handleClearFile}
-                  type="button"
-                  className="px-4 py-2 bg-red-300 text-black rounded hover:bg-red-400 hover:shadow-xl shadow-lg"
-              >
-              Clear
-            </button>
-          </div>
-          </div>
-        )}
-        {loading && (
-          <span className="loading loading-spinner text-primary"></span>
-        )}
-        {reply && (
-          <div
-            className="max-w-2xl w-full"
-            dangerouslySetInnerHTML={{ __html: reply }}
-          />
-        )}
-    </div>
-  )
-}

examples-ts/classify/src/utils/classifier.ts

@@ -1,23 +0,0 @@
-import { LlamaClassify, ClassifierRule, ClassifyParsingConfiguration } from "llama-cloud-services"
-
-export const classifier = new LlamaClassify(process.env.LLAMA_CLOUD_API_KEY);
-
-export const classificationRules: ClassifierRule[] = [
-    {
-        description: "Shows a company's assets, liabilities, and shareholders' equity at a specific point in time, providing a snapshot of financial position.",
-        type: "balance_sheet"
-    },
-    {
-        description: "Reports cash inflows and outflows from operating, investing, and financing activities, highlighting liquidity and cash management.",
-        type: "cash_flow_statement"
-    },
-    {
-        description: "Summarizes revenues, expenses, and profits over a period, indicating financial performance and profitability.",
-        type: "income_statement"
-    },
-];
-
-export const parsingConfig: ClassifyParsingConfiguration = {
-    lang: "en",
-    max_pages: 20,
-}

examples-ts/classify/src/utils/seo.ts

@@ -1,33 +0,0 @@
-export const seo = ({
-  title,
-  description,
-  keywords,
-  image,
-}: {
-  title: string
-  description?: string
-  image?: string
-  keywords?: string
-}) => {
-  const tags = [
-    { title },
-    { name: 'description', content: description },
-    { name: 'keywords', content: keywords },
-    { name: 'twitter:title', content: title },
-    { name: 'twitter:description', content: description },
-    { name: 'twitter:creator', content: '@tannerlinsley' },
-    { name: 'twitter:site', content: '@tannerlinsley' },
-    { name: 'og:type', content: 'website' },
-    { name: 'og:title', content: title },
-    { name: 'og:description', content: description },
-    ...(image
-      ? [
-          { name: 'twitter:image', content: image },
-          { name: 'twitter:card', content: 'summary_large_image' },
-          { name: 'og:image', content: image },
-        ]
-      : []),
-  ]
-
-  return tags
-}

examples-ts/classify/tsconfig.json

@@ -1,22 +0,0 @@
-{
-  "include": ["**/*.ts", "**/*.tsx"],
-  "compilerOptions": {
-    "strict": true,
-    "esModuleInterop": true,
-    "jsx": "react-jsx",
-    "module": "ESNext",
-    "moduleResolution": "Bundler",
-    "lib": ["DOM", "DOM.Iterable", "ES2022"],
-    "isolatedModules": true,
-    "resolveJsonModule": true,
-    "skipLibCheck": true,
-    "target": "ES2022",
-    "allowJs": true,
-    "forceConsistentCasingInFileNames": true,
-    "baseUrl": ".",
-    "paths": {
-      "~/*": ["./src/*"]
-    },
-    "noEmit": true
-  }
-}

examples-ts/classify/vite.config.ts

@@ -1,19 +0,0 @@
-import { tanstackStart } from '@tanstack/react-start/plugin/vite'
-import { defineConfig } from 'vite'
-import tsConfigPaths from 'vite-tsconfig-paths'
-import viteReact from '@vitejs/plugin-react'
-
-export default defineConfig({
-  server: {
-    port: 3000,
-  },
-  plugins: [
-    tsConfigPaths({
-      projects: ['./tsconfig.json'],
-    }),
-    tanstackStart({
-      srcDirectory: 'src',
-    }),
-    viteReact(),
-  ],
-})

py/CHANGELOG.md

@@ -1,11 +1,5 @@
 # llama-cloud-services-py
 
-## 0.6.77
-
-### Patch Changes
-
-- 407292b: Now return partial results on job failure
-
 ## 0.6.76
 
 ### Patch Changes

py/llama_cloud_services/__init__.py

@@ -1,6 +1,5 @@
 from llama_cloud_services.parse import LlamaParse
-from llama_cloud_services.extract import LlamaExtract, ExtractionAgent
-from llama_cloud_services.utils import SourceText, FileInput
+from llama_cloud_services.extract import LlamaExtract, ExtractionAgent, SourceText
 from llama_cloud_services.constants import EU_BASE_URL
 from llama_cloud_services.index import (
     LlamaCloudCompositeRetriever,
@@ -13,7 +12,6 @@ __all__ = [
     "LlamaExtract",
     "ExtractionAgent",
     "SourceText",
-    "FileInput",
     "EU_BASE_URL",
     "LlamaCloudIndex",
     "LlamaCloudRetriever",

py/llama_cloud_services/beta/classifier/__init__.py

@@ -1,10 +0,0 @@
-from llama_cloud_services.beta.classifier.client import ClassifyClient
-from llama_cloud_services.beta.classifier.types import ClassifyJobResultsWithFiles
-from llama_cloud_services.utils import SourceText, FileInput
-
-__all__ = [
-    "ClassifyClient",
-    "ClassifyJobResultsWithFiles",
-    "SourceText",
-    "FileInput",
-]

py/llama_cloud_services/beta/classifier/client.py

@@ -1,7 +1,6 @@
 import asyncio
 import time
-import warnings
-from typing import Optional, List, Union
+from typing import Optional
 from pydantic import BaseModel
 from llama_cloud.client import AsyncLlamaCloud
 from llama_cloud.types import (
@@ -15,11 +14,7 @@ from llama_cloud.types import (
 from llama_cloud.resources.classifier.client import OMIT
 from llama_cloud_services.files.client import FileClient
 from llama_cloud_services.constants import POLLING_TIMEOUT_SECONDS
-from llama_cloud_services.utils import (
-    is_terminal_status,
-    augment_async_errors,
-    FileInput,
-)
+from llama_cloud_services.utils import is_terminal_status, augment_async_errors
 from llama_index.core.async_utils import DEFAULT_NUM_WORKERS, run_jobs
 from llama_cloud_services.beta.classifier.types import (
     ClassifyJobResultsWithFiles,
@@ -171,98 +166,6 @@ class ClassifyClient:
                 )
             )
 
-    async def aclassify(
-        self,
-        rules: list[ClassifierRule],
-        files: Union[FileInput, List[FileInput]],
-        parsing_configuration: Optional[ClassifyParsingConfiguration] = None,
-        raise_on_error: bool = True,
-        workers: int = DEFAULT_NUM_WORKERS,
-        show_progress: bool = False,
-    ) -> ClassifyJobResultsWithFiles:
-        """
-        Classify one or more files from various input types.
-
-        Args:
-            rules: The rules to use for classification.
-            files: The file(s) to classify. Can be a single file or list of files. Each can be:
-                - str/Path: File path
-                - SourceText: Text content or file with explicit filename
-                - File: Already uploaded file
-                - BufferedIOBase: File-like object
-            parsing_configuration: The parsing configuration to use for classification.
-            raise_on_error: Whether to raise an error if the classification job fails.
-            workers: Number of parallel workers for uploading files.
-            show_progress: Whether to show progress bars.
-
-        Returns:
-            The results of the classification job with file metadata.
-        """
-        # Normalize to list
-        if not isinstance(files, list):
-            files = [files]
-
-        # Upload all files
-        coroutines = [
-            self.file_client.upload_content(file_input) for file_input in files
-        ]
-        uploaded_files: List[File] = await run_jobs(
-            coroutines,
-            show_progress=show_progress,
-            workers=workers,
-            desc="Uploading files for classification",
-        )
-
-        # Classify
-        results = await self.aclassify_file_ids(
-            rules,
-            [file.id for file in uploaded_files],
-            parsing_configuration,
-            raise_on_error,
-        )
-        return ClassifyJobResultsWithFiles.from_classify_job_results(
-            results, uploaded_files
-        )
-
-    def classify(
-        self,
-        rules: list[ClassifierRule],
-        files: Union[FileInput, List[FileInput]],
-        parsing_configuration: Optional[ClassifyParsingConfiguration] = None,
-        raise_on_error: bool = True,
-        workers: int = DEFAULT_NUM_WORKERS,
-        show_progress: bool = False,
-    ) -> ClassifyJobResultsWithFiles:
-        """
-        Classify one or more files from various input types (synchronous version).
-
-        Args:
-            rules: The rules to use for classification.
-            files: The file(s) to classify. Can be a single file or list of files. Each can be:
-                - str/Path: File path
-                - SourceText: Text content or file with explicit filename
-                - File: Already uploaded file
-                - BufferedIOBase: File-like object
-            parsing_configuration: The parsing configuration to use for classification.
-            raise_on_error: Whether to raise an error if the classification job fails.
-            workers: Number of parallel workers for uploading files.
-            show_progress: Whether to show progress bars.
-
-        Returns:
-            The results of the classification job with file metadata.
-        """
-        with augment_async_errors():
-            return asyncio.run(
-                self.aclassify(
-                    rules,
-                    files,
-                    parsing_configuration,
-                    raise_on_error,
-                    workers,
-                    show_progress,
-                )
-            )
-
     async def aclassify_file_path(
         self,
         rules: list[ClassifierRule],
@@ -270,17 +173,11 @@ class ClassifyClient:
         parsing_configuration: Optional[ClassifyParsingConfiguration] = None,
         raise_on_error: bool = True,
     ) -> ClassifyJobResultsWithFiles:
-        """
-        Deprecated: Use aclassify() instead.
-        """
-        warnings.warn(
-            "aclassify_file_path is deprecated, use aclassify() instead",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        return await self.aclassify(
-            rules, file_input_path, parsing_configuration, raise_on_error
+        file = await self.file_client.upload_file(file_input_path)
+        results = await self.aclassify_file_ids(
+            rules, [file.id], parsing_configuration, raise_on_error
         )
+        return ClassifyJobResultsWithFiles.from_classify_job_results(results, [file])
 
     def classify_file_path(
         self,
@@ -289,17 +186,12 @@ class ClassifyClient:
         parsing_configuration: Optional[ClassifyParsingConfiguration] = None,
         raise_on_error: bool = True,
     ) -> ClassifyJobResultsWithFiles:
-        """
-        Deprecated: Use classify() instead.
-        """
-        warnings.warn(
-            "classify_file_path is deprecated, use classify() instead",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        return self.classify(
-            rules, file_input_path, parsing_configuration, raise_on_error
-        )
+        with augment_async_errors():
+            return asyncio.run(
+                self.aclassify_file_path(
+                    rules, file_input_path, parsing_configuration, raise_on_error
+                )
+            )
 
     async def aclassify_file_paths(
         self,
@@ -310,22 +202,17 @@ class ClassifyClient:
         workers: int = DEFAULT_NUM_WORKERS,
         show_progress: bool = False,
     ) -> ClassifyJobResultsWithFiles:
-        """
-        Deprecated: Use aclassify() instead.
-        """
-        warnings.warn(
-            "aclassify_file_paths is deprecated, use aclassify() instead",
-            DeprecationWarning,
-            stacklevel=2,
+        coroutines = [self.file_client.upload_file(path) for path in file_input_paths]
+        files: list[File] = await run_jobs(
+            coroutines,
+            show_progress=show_progress,
+            workers=workers,
+            desc="Uploading files for classification",
         )
-        return await self.aclassify(
-            rules,
-            file_input_paths,
-            parsing_configuration,
-            raise_on_error,
-            workers,
-            show_progress,
+        results = await self.aclassify_file_ids(
+            rules, [file.id for file in files], parsing_configuration, raise_on_error
         )
+        return ClassifyJobResultsWithFiles.from_classify_job_results(results, files)
 
     def classify_file_paths(
         self,
@@ -334,17 +221,12 @@ class ClassifyClient:
         parsing_configuration: Optional[ClassifyParsingConfiguration] = None,
         raise_on_error: bool = True,
     ) -> ClassifyJobResultsWithFiles:
-        """
-        Deprecated: Use classify() instead.
-        """
-        warnings.warn(
-            "classify_file_paths is deprecated, use classify() instead",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        return self.classify(
-            rules, file_input_paths, parsing_configuration, raise_on_error
-        )
+        with augment_async_errors():
+            return asyncio.run(
+                self.aclassify_file_paths(
+                    rules, file_input_paths, parsing_configuration, raise_on_error
+                )
+            )
 
     async def wait_for_job_completion(self, job_id: str) -> ClassifyJob:
         """

py/llama_cloud_services/extract/__init__.py

@@ -2,16 +2,15 @@ from llama_cloud_services.extract.extract import (
     LlamaExtract,
     ExtractConfig,
     ExtractionAgent,
+    SourceText,
     ExtractTarget,
     ExtractMode,
 )
-from llama_cloud_services.utils import SourceText, FileInput
 
 __all__ = [
     "LlamaExtract",
     "ExtractionAgent",
     "SourceText",
-    "FileInput",
     "ExtractConfig",
     "ExtractTarget",
     "ExtractMode",

py/llama_cloud_services/extract/extract.py

@@ -2,9 +2,10 @@ import asyncio
 import base64
 import os
 import time
-from io import BufferedIOBase, TextIOWrapper
+from io import BufferedIOBase, BufferedReader, BytesIO, TextIOWrapper
 from pathlib import Path
 from typing import List, Optional, Type, Union, Coroutine, Any, TypeVar
+import secrets
 import warnings
 import httpx
 from pydantic import BaseModel
@@ -32,8 +33,7 @@ from llama_cloud_services.extract.utils import (
     JSONObjectType,
     ExperimentalWarning,
 )
-from llama_cloud_services.utils import augment_async_errors, SourceText, FileInput
-from llama_cloud_services.files.client import FileClient
+from llama_cloud_services.utils import augment_async_errors
 from llama_index.core.schema import BaseComponent
 from llama_index.core.async_utils import run_jobs
 from llama_index.core.bridge.pydantic import Field, PrivateAttr
@@ -188,6 +188,46 @@ async def _wait_for_job_result(
             )
 
 
+class SourceText:
+    def __init__(
+        self,
+        *,
+        file: Union[bytes, BufferedIOBase, TextIOWrapper, str, Path, None] = None,
+        text_content: Optional[str] = None,
+        filename: Optional[str] = None,
+    ):
+        self.file = file
+        self.filename = filename
+        self.text_content = text_content
+        self._validate()
+
+    def _validate(self) -> None:
+        """Ensure filename is provided when needed."""
+        if not ((self.file is None) ^ (self.text_content is None)):
+            raise ValueError("Either file or text_content must be provided.")
+        if self.text_content is not None:
+            if not self.filename:
+                random_hex = secrets.token_hex(4)
+                self.filename = f"text_input_{random_hex}.txt"
+            return
+
+        if isinstance(self.file, (bytes, BufferedIOBase, TextIOWrapper)):
+            if not self.filename and hasattr(self.file, "name"):
+                self.filename = os.path.basename(str(self.file.name))
+            elif not hasattr(self.file, "name") and self.filename is None:
+                raise ValueError(
+                    "filename must be provided when file is bytes or a file-like object without a name"
+                )
+        elif isinstance(self.file, (str, Path)):
+            if not self.filename:
+                self.filename = os.path.basename(str(self.file))
+        else:
+            raise ValueError(f"Unsupported file type: {type(self.file)}")
+
+
+FileInput = Union[str, Path, BufferedIOBase, SourceText, File]
+
+
 def run_in_thread(
     coro: Coroutine[Any, Any, T],
     thread_pool: ThreadPoolExecutor,
@@ -280,7 +320,6 @@ class ExtractionAgent:
         self._thread_pool = ThreadPoolExecutor(
             max_workers=min(10, (os.cpu_count() or 1) + 4)
         )
-        self._file_client = FileClient(client, project_id, organization_id)
 
     @property
     def id(self) -> str:
@@ -330,11 +369,65 @@ class ExtractionAgent:
             ValueError: If filename is not provided for bytes input or for file-like objects
                        without a name attribute.
         """
-        return await self._file_client.upload_content(file_input)
+        file_contents: Optional[Union[BufferedIOBase, BytesIO]] = None
+        try:
+            if file_input.text_content is not None:
+                # Handle direct text content
+                file_contents = BytesIO(file_input.text_content.encode("utf-8"))
+            elif isinstance(file_input.file, TextIOWrapper):
+                # Handle text-based IO objects
+                file_contents = BytesIO(file_input.file.read().encode("utf-8"))
+            elif isinstance(file_input.file, (str, Path)):
+                # Handle file paths
+                file_contents = open(file_input.file, "rb")
+            elif isinstance(file_input.file, bytes):
+                # Handle bytes
+                file_contents = BytesIO(file_input.file)
+            elif isinstance(file_input.file, BufferedIOBase):
+                # Handle binary IO objects
+                file_contents = file_input.file
+            else:
+                raise ValueError(f"Unsupported file type: {type(file_input.file)}")
+
+            # Add name attribute to file object if needed
+            if not hasattr(file_contents, "name"):
+                file_contents.name = file_input.filename  # type: ignore
+
+            return await self._client.files.upload_file(
+                project_id=self._project_id, upload_file=file_contents
+            )
+        finally:
+            if file_contents is not None and isinstance(
+                file_contents, (BufferedReader, BytesIO)
+            ):
+                file_contents.close()
 
     async def _upload_file(self, file_input: FileInput) -> File:
-        """Upload a file from various input types using FileClient."""
-        return await self._file_client.upload_content(file_input)
+        source_text = None
+        if isinstance(file_input, File):
+            return file_input
+        if isinstance(file_input, SourceText):
+            source_text = file_input
+        elif isinstance(file_input, (str, Path)):
+            path = Path(file_input)
+            source_text = SourceText(file=path, filename=path.name)
+        else:
+            # Try to get filename from the file object if not provided
+            filename = None
+            if hasattr(file_input, "name"):
+                filename = os.path.basename(str(file_input.name))
+            if filename is None:
+                raise ValueError(
+                    "Use SourceText to provide filename when uploading bytes or file-like objects."
+                )
+
+            warnings.warn(
+                "Use SourceText instead of bytes or file-like objects",
+                DeprecationWarning,
+            )
+            source_text = SourceText(file=file_input, filename=filename)
+
+        return await self.upload_file(source_text)
 
     async def _wait_for_job_result(self, job_id: str) -> Optional[ExtractRun]:
         """Wait for and return the results of an extraction job."""

py/llama_cloud_services/files/client.py

@@ -1,11 +1,9 @@
 from io import BytesIO
 from typing import BinaryIO
 import os
-from pathlib import Path
 from llama_cloud.client import AsyncLlamaCloud
 from llama_cloud.types import File, FileCreate
 from typing import Optional
-from llama_cloud_services.utils import SourceText, FileInput
 
 
 class FileClient:
@@ -97,83 +95,3 @@ class FileClient:
                 project_id=self.project_id,
                 organization_id=self.organization_id,
             )
-
-    async def upload_content(
-        self, file_input: FileInput, external_file_id: Optional[str] = None
-    ) -> File:
-        """
-        Upload content from various input types or fetch an already-uploaded file.
-
-        Args:
-            file_input: The content to upload. Can be:
-                - File: Already uploaded file (returned as-is)
-                - str/Path: Path to a file on disk
-                - SourceText: Text content, file, or file_id with explicit filename
-                - BufferedIOBase: File-like binary object
-            external_file_id: Optional external identifier for the file
-
-        Returns:
-            File: The uploaded (or fetched) file object
-
-        Raises:
-            ValueError: If the input type is not supported or required info is missing
-        """
-        # If already a File object, return it
-        if isinstance(file_input, File):
-            return file_input
-
-        # Handle SourceText
-        if isinstance(file_input, SourceText):
-            # If file_id is provided, fetch the file object
-            if file_input.file_id is not None:
-                return await self.get_file(file_input.file_id)
-            elif file_input.text_content is not None:
-                # Handle direct text content
-                text_bytes = file_input.text_content.encode("utf-8")
-                return await self.upload_bytes(
-                    text_bytes, external_file_id or file_input.filename or "file"
-                )
-            elif isinstance(file_input.file, (str, Path)):
-                # Handle file paths using the existing upload_file method
-                return await self.upload_file(
-                    str(file_input.file), external_file_id or file_input.filename
-                )
-            elif isinstance(file_input.file, bytes):
-                # Handle bytes
-                return await self.upload_bytes(
-                    file_input.file, external_file_id or file_input.filename or "file"
-                )
-            elif hasattr(file_input.file, "read"):
-                # Handle any file-like object (TextIOWrapper, BytesIO, BufferedReader, BufferedIOBase, etc.)
-                content = file_input.file.read()  # type: ignore
-                if isinstance(content, str):
-                    content = content.encode("utf-8")
-                return await self.upload_bytes(
-                    content, external_file_id or file_input.filename or "file"
-                )
-            else:
-                raise ValueError(f"Unsupported file type: {type(file_input.file)}")
-
-        # Handle string/Path directly
-        elif isinstance(file_input, (str, Path)):
-            return await self.upload_file(str(file_input), external_file_id)
-
-        # Handle raw file-like objects
-        elif hasattr(file_input, "read"):
-            if hasattr(file_input, "name"):
-                filename = os.path.basename(str(file_input.name))
-            else:
-                filename = external_file_id or "file"
-
-            # Read content to determine size
-            content = file_input.read()
-            if isinstance(content, str):
-                content = content.encode("utf-8")
-
-            return await self.upload_bytes(content, external_file_id or filename)
-
-        else:
-            raise ValueError(
-                f"Unsupported file input type: {type(file_input)}. "
-                f"Supported types: str, Path, SourceText, BufferedIOBase, or File."
-            )

py/llama_cloud_services/parse/base.py

@@ -1146,25 +1146,6 @@ class LlamaParse(BasePydanticReader):
                     )
                 current_interval = self._calculate_backoff(current_interval)
 
-    async def _get_job_result_with_error_handling(
-        self, job_id: str, result_type: str, verbose: bool = False
-    ) -> Dict[str, Any]:
-        """Get job result with error handling based on ignore_errors setting."""
-        try:
-            return await self._get_job_result(job_id, result_type, verbose=verbose)
-        except JobFailedException as e:
-            if self.ignore_errors:
-                # Return error information when ignore_errors is True
-                return {
-                    "pages": [],
-                    "job_metadata": {},
-                    "error": f"{e.status}: {e.error_message or 'No error message'}",
-                    "error_code": e.error_code,
-                    "status": e.status,
-                }
-            else:
-                raise e
-
     async def _parse_one(
         self,
         file_path: FileInput,
@@ -1206,7 +1187,7 @@ class LlamaParse(BasePydanticReader):
         )
         if self.verbose:
             print("Started parsing the file under job_id %s" % job_id)
-        result = await self._get_job_result_with_error_handling(
+        result = await self._get_job_result(
             job_id, result_type or self.result_type.value, verbose=self.verbose
         )
         return job_id, result
@@ -1269,15 +1250,6 @@ class LlamaParse(BasePydanticReader):
                     result_type=ResultType.JSON.value,
                     partition_target_pages=f"{total}-{total + size - 1}",
                 )
-                # Check if the result is an error result (when ignore_errors=True)
-                if json_result.get("error_code") == "NO_DATA_FOUND_IN_FILE":
-                    raise JobFailedException(
-                        job_id=job_id,
-                        status=json_result.get("status", "ERROR"),
-                        error_code=json_result.get("error_code"),
-                        error_message=json_result.get("error"),
-                    )
-
                 result_type = result_type or self.result_type.value
                 if result_type == ResultType.JSON.value:
                     job_result = json_result
@@ -1803,7 +1775,7 @@ class LlamaParse(BasePydanticReader):
             JobResult object or list of JobResult objects if multiple job IDs were provided.
         """
         if isinstance(job_id, str):
-            result = await self._get_job_result_with_error_handling(
+            result = await self._get_job_result(
                 job_id, ResultType.JSON.value, verbose=self.verbose
             )
             return JobResult(
@@ -1818,9 +1790,7 @@ class LlamaParse(BasePydanticReader):
         elif isinstance(job_id, list):
             results = []
             jobs = [
-                self._get_job_result_with_error_handling(
-                    id_, ResultType.JSON.value, verbose=self.verbose
-                )
+                self._get_job_result(id_, ResultType.JSON.value, verbose=self.verbose)
                 for id_ in job_id
             ]
             results = await run_jobs(

py/llama_cloud_services/parse/types.py

@@ -269,13 +269,6 @@ class JobResult(SafeBaseModel):
     error: Optional[str] = Field(
         default=None, description="The error message if the job failed."
     )
-    error_code: Optional[str] = Field(
-        default=None, description="The error code if the job failed."
-    )
-    status: Optional[str] = Field(
-        default=None,
-        description="The job status (e.g., PENDING, SUCCESS, ERROR, CANCELED).",
-    )
 
     def __init__(
         self,

py/llama_cloud_services/utils.py

@@ -3,14 +3,11 @@ import importlib.metadata
 from contextlib import contextmanager
 from typing import Generator
 import difflib
-from llama_cloud.types import StatusEnum, File
+from llama_cloud.types import StatusEnum
 import httpx
 import packaging.version
 from pydantic import BaseModel
-from typing import Any, Dict, List, Tuple, Type, Union, Optional
-from io import BufferedIOBase, TextIOWrapper
-from pathlib import Path
-import secrets
+from typing import Any, Dict, List, Tuple, Type
 
 # Asyncio error messages
 nest_asyncio_err = "cannot be called from a running event loop"
@@ -107,100 +104,3 @@ def augment_async_errors() -> Generator[None, None, None]:
         if nest_asyncio_err in str(e):
             raise RuntimeError(nest_asyncio_msg)
         raise
-
-
-class SourceText:
-    """
-    A wrapper class for providing text or file input with optional filename specification.
-
-    This class allows you to provide input in multiple ways:
-    - Direct text content via text_content parameter
-    - File paths as strings or Path objects
-    - Raw bytes
-    - File-like objects (BufferedIOBase, TextIOWrapper)
-    - Already-uploaded file ID via file_id parameter
-
-    Args:
-        file: The file input (bytes, file-like object, str path, or Path).
-              Mutually exclusive with text_content and file_id.
-        text_content: Raw text content to process. Mutually exclusive with file and file_id.
-        file_id: ID of an already-uploaded file. Mutually exclusive with file and text_content.
-        filename: Optional filename. Required for bytes/file-like objects without names.
-                  If not provided, will be auto-generated for text_content or inferred from paths.
-
-    Examples:
-        # Direct text input
-        source = SourceText(text_content="Hello world")
-
-        # File path
-        source = SourceText(file="document.pdf")
-
-        # Bytes with filename
-        source = SourceText(file=b"...", filename="document.pdf")
-
-        # File-like object (will read from current position)
-        with open("document.pdf", "rb") as f:
-            source = SourceText(file=f)
-
-        # Already-uploaded file
-        source = SourceText(file_id="file_abc123")
-    """
-
-    def __init__(
-        self,
-        *,
-        file: Union[bytes, BufferedIOBase, TextIOWrapper, str, Path, None] = None,
-        text_content: Optional[str] = None,
-        file_id: Optional[str] = None,
-        filename: Optional[str] = None,
-    ):
-        self.file = file
-        self.filename = filename
-        self.text_content = text_content
-        self.file_id = file_id
-        self._validate()
-
-    def _validate(self) -> None:
-        """Ensure filename is provided when needed."""
-        # Check that exactly one of file, text_content, or file_id is provided
-        provided = sum(
-            [
-                self.file is not None,
-                self.text_content is not None,
-                self.file_id is not None,
-            ]
-        )
-
-        if provided == 0:
-            raise ValueError("One of file, text_content, or file_id must be provided.")
-        elif provided > 1:
-            raise ValueError(
-                "Only one of file, text_content, or file_id can be provided."
-            )
-
-        # If file_id is provided, we don't need filename validation
-        if self.file_id is not None:
-            return
-
-        if self.text_content is not None:
-            if not self.filename:
-                random_hex = secrets.token_hex(4)
-                self.filename = f"text_input_{random_hex}.txt"
-            return
-
-        if isinstance(self.file, (bytes, BufferedIOBase, TextIOWrapper)):
-            if not self.filename and hasattr(self.file, "name"):
-                self.filename = os.path.basename(str(self.file.name))
-            elif self.filename is None and not hasattr(self.file, "name"):
-                raise ValueError(
-                    "filename must be provided when file is bytes or a file-like object without a name"
-                )
-        elif isinstance(self.file, (str, Path)):
-            if not self.filename:
-                self.filename = os.path.basename(str(self.file))
-        else:
-            raise ValueError(f"Unsupported file type: {type(self.file)}")
-
-
-# Type alias for file input that can be used across services
-FileInput = Union[str, Path, BufferedIOBase, SourceText, File]

py/llama_parse/CHANGELOG.md

@@ -1,12 +1,5 @@
 # llama_parse
 
-## 0.6.77
-
-### Patch Changes
-
-- Updated dependencies [407292b]
-  - llama-cloud-services-py@0.6.77
-
 ## 0.6.76
 
 ### Patch Changes

py/llama_parse/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama_parse",
-  "version": "0.6.77",
+  "version": "0.6.76",
   "description": "",
   "main": "index.js",
   "private": false,

py/llama_parse/pyproject.toml

@@ -11,13 +11,13 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.77"
+version = "0.6.76"
 description = "Parse files into RAG-Optimized formats."
 authors = [{name = "Logan Markewich", email = "logan@llamaindex.ai"}]
 requires-python = ">=3.9,<4.0"
 readme = "README.md"
 license = "MIT"
-dependencies = ["llama-cloud-services>=0.6.77"]
+dependencies = ["llama-cloud-services>=0.6.76"]
 
 [project.scripts]
 llama-parse = "llama_parse.cli.main:parse"

py/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama-cloud-services-py",
-  "version": "0.6.77",
+  "version": "0.6.76",
   "private": false,
   "license": "MIT",
   "scripts": {},

py/pyproject.toml

@@ -19,7 +19,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.77"
+version = "0.6.76"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"

py/uv.lock

@@ -1,5 +1,5 @@
 version = 1
-revision = 2
+revision = 3
 requires-python = ">=3.9, <4.0"
 resolution-markers = [
     "python_full_version >= '3.14'",
@@ -1596,7 +1596,7 @@ wheels = [
 
 [[package]]
 name = "llama-cloud-services"
-version = "0.6.76"
+version = "0.6.73"
 source = { editable = "." }
 dependencies = [
     { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },

ts/llama_cloud_services/CHANGELOG.md

@@ -1,11 +1,5 @@
 # llama-cloud-services
 
-## 0.3.10
-
-### Patch Changes
-
-- fee516d: Adding LlamaClassify among the available LlamaCloud services
-
 ## 0.3.9
 
 ### Patch Changes

ts/llama_cloud_services/classify/package.json

@@ -1,8 +0,0 @@
-{
-  "type": "module",
-  "main": "./dist/index.cjs",
-  "module": "./dist/index.js",
-  "types": "./dist/index.d.ts",
-  "exports": "./dist/index.js",
-  "private": true
-}

ts/llama_cloud_services/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama-cloud-services",
-  "version": "0.3.10",
+  "version": "0.3.9",
   "type": "module",
   "license": "MIT",
   "scripts": {
@@ -24,8 +24,7 @@
     "./reader",
     "./parse",
     "./beta/agent",
-    "./extract",
-    "./classify"
+    "./extract"
   ],
   "exports": {
     "./openapi.json": "./openapi.json",
@@ -84,17 +83,6 @@
       },
       "default": "./extract/dist/index.js"
     },
-    "./classify": {
-      "require": {
-        "types": "./classify/dist/index.d.cts",
-        "default": "./classify/dist/index.cjs"
-      },
-      "import": {
-        "types": "./classify/dist/index.d.ts",
-        "default": "./classify/dist/index.js"
-      },
-      "default": "./classify/dist/index.js"
-    },
     ".": {
       "require": {
         "types": "./dist/index.d.cts",

ts/llama_cloud_services/src/LlamaClassify.ts

@@ -1,69 +0,0 @@
-import { createClient, createConfig, type Client } from "@hey-api/client-fetch";
-import {
-  classify,
-  type ClassifyParsingConfiguration,
-  type ClassifierRule,
-  type ClassifyJobResults,
-} from "./classify";
-import { getUrl } from "./utils";
-import { getEnv } from "@llamaindex/env";
-import { File } from "buffer";
-
-export class LlamaClassify {
-  private client: Client;
-
-  constructor(
-    apiKey: string | undefined = undefined,
-    baseUrl: string | undefined = undefined,
-    region: string | undefined = undefined,
-  ) {
-    const key = apiKey ?? getEnv("LLAMA_CLOUD_API_KEY");
-    if (typeof key === "undefined") {
-      throw new Error(
-        "No API key provided and no API key found in environment. Please pass the API key or set `LLAMA_CLOUD_API_KEY` as an environment variable.",
-      );
-    }
-    const url = getUrl(baseUrl, region);
-    this.client = createClient(
-      createConfig({
-        baseUrl: url,
-        headers: {
-          Authorization: `Bearer ${key}`,
-        },
-      }),
-    );
-  }
-
-  async classify(
-    rules: ClassifierRule[],
-    parsingConfiguration: ClassifyParsingConfiguration,
-    fileContents:
-      | Buffer<ArrayBufferLike>[]
-      | File[]
-      | Uint8Array<ArrayBuffer>[]
-      | string[]
-      | undefined = undefined,
-    filePaths: string[] | undefined = undefined,
-    projectId: string | null = null,
-    organizationId: string | null = null,
-    pollingInterval: number = 1,
-    maxPollingIterations: number = 1800,
-    maxRetriesOnError: number = 10,
-    retryInterval: number = 0.5,
-  ): Promise<ClassifyJobResults> {
-    const result = await classify(
-      rules,
-      parsingConfiguration,
-      fileContents,
-      filePaths,
-      projectId,
-      organizationId,
-      this.client,
-      pollingInterval,
-      maxPollingIterations,
-      maxRetriesOnError,
-      retryInterval,
-    );
-    return result;
-  }
-}

ts/llama_cloud_services/src/LlamaExtract.ts

@@ -4,7 +4,25 @@ import * as extract from "./extract";
 import type { ExtractAgent, ExtractConfig } from "./extract";
 import { getEnv } from "@llamaindex/env";
 import type { ExtractResult } from "./type";
-import { getUrl } from "./utils";
+
+const URLS = {
+  us: "https://api.cloud.llamaindex.ai",
+  eu: "https://api.cloud.eu.llamaindex.ai",
+  "us-staging": "https://api.staging.llamaindex.ai",
+} as const;
+
+function getUrl(baseUrl: string | undefined, region: string | undefined) {
+  if (typeof baseUrl != "undefined") {
+    return baseUrl;
+  }
+  if (typeof region === "undefined") {
+    return URLS["us"];
+  } else if (region === "us" || region === "eu" || region === "us-staging") {
+    return URLS[region];
+  } else {
+    throw new Error(`Unsupported region: ${region}`);
+  }
+}
 
 export class LlamaExtractAgent {
   private agent: ExtractAgent;

ts/llama_cloud_services/src/classify.ts

@@ -1,289 +0,0 @@
-import type {
-  Options,
-  CreateClassifyJobApiV1ClassifierJobsPostData,
-  ClassifyJobCreate,
-  ClassifierRule,
-  ClassifyParsingConfiguration,
-  GetClassifyJobApiV1ClassifierJobsClassifyJobIdGetData,
-  GetClassificationJobResultsApiV1ClassifierJobsClassifyJobIdResultsGetData,
-  ClassifyJobResults,
-} from "./api";
-import {
-  StatusEnum,
-  createClassifyJobApiV1ClassifierJobsPost,
-  getClassifyJobApiV1ClassifierJobsClassifyJobIdGet,
-  getClassificationJobResultsApiV1ClassifierJobsClassifyJobIdResultsGet,
-} from "./api";
-import type { Client } from "@hey-api/client-fetch";
-import { sleep } from "./utils";
-import { uploadFile } from "./fileUpload";
-import { File } from "buffer";
-
-async function createClassifyJob(
-  fileIds: string[],
-  rules: ClassifierRule[],
-  parsingConfiguration: ClassifyParsingConfiguration,
-  organizationId: null | string,
-  projectId: null | string,
-  client: Client | undefined,
-  maxRetriesOnError: number = 10,
-  retryInterval: number = 0.5,
-): Promise<string> {
-  const rawData = {
-    file_ids: fileIds,
-    rules: rules,
-    parsing_configuration: parsingConfiguration,
-  } as ClassifyJobCreate;
-  const data = {
-    body: rawData,
-    query: {
-      project_id: projectId,
-      organization_id: organizationId,
-    },
-  } as CreateClassifyJobApiV1ClassifierJobsPostData;
-  const options = data as Options<CreateClassifyJobApiV1ClassifierJobsPostData>;
-  if (typeof client != "undefined") {
-    options.client = client;
-  }
-  let retries = 0;
-  while (true) {
-    if (retries > maxRetriesOnError) {
-      throw new Error(
-        "Error while creating the classify job: Exceeded maximum number of retries, the API keeps returning errors.",
-      );
-    }
-    const response = await createClassifyJobApiV1ClassifierJobsPost(options);
-    if (!response.response.ok) {
-      if ("error" in response) {
-        console.log(
-          `An error occurred while creating the classification job.\nDetails:\n\n${JSON.stringify(
-            response.error,
-          )}\n\nRetrying...`,
-        );
-      }
-      retries++;
-      await sleep(retryInterval * 1000);
-    } else {
-      if (typeof response.data != "undefined") {
-        return response.data.id;
-      } else {
-        throw new Error(
-          "Error while creating the classify job: the job creation succeeded but no data where returned",
-        );
-      }
-    }
-  }
-}
-
-async function pollForJobCompletion(
-  jobId: string,
-  interval: number = 1,
-  maxIterations: number = 1800,
-  client: Client | undefined = undefined,
-): Promise<boolean> {
-  let status: StatusEnum | undefined = undefined;
-  const jobData = {
-    path: { classify_job_id: jobId },
-  } as GetClassifyJobApiV1ClassifierJobsClassifyJobIdGetData;
-  const jobOptions =
-    jobData as Options<GetClassifyJobApiV1ClassifierJobsClassifyJobIdGetData>;
-  if (typeof client != "undefined") {
-    jobOptions.client = client;
-  }
-  let numIterations: number = 0;
-  while (true) {
-    if (numIterations > maxIterations) {
-      return false;
-    }
-    const response =
-      await getClassifyJobApiV1ClassifierJobsClassifyJobIdGet(jobOptions);
-    if (!response.response.ok) {
-      numIterations++;
-    }
-    if (typeof response.data != "undefined") {
-      status = response.data.status as StatusEnum;
-      if (status == StatusEnum.CANCELLED || status == StatusEnum.ERROR) {
-        throw new Error("There was an error during the classification job.");
-      } else if (status == StatusEnum.SUCCESS) {
-        return true;
-      } else {
-        numIterations++;
-        await sleep(interval * 1000);
-      }
-    }
-  }
-}
-
-async function getJobResult(
-  jobId: string,
-  client: Client | undefined = undefined,
-  projectId: string | null = null,
-  organizationId: string | null = null,
-  maxRetriesOnError: number = 10,
-  retryInterval: number = 0.5,
-): Promise<ClassifyJobResults> {
-  const jobData = {
-    path: { classify_job_id: jobId },
-    query: { organization_id: organizationId, project_id: projectId },
-  } as GetClassificationJobResultsApiV1ClassifierJobsClassifyJobIdResultsGetData;
-  const jobOptions =
-    jobData as Options<GetClassificationJobResultsApiV1ClassifierJobsClassifyJobIdResultsGetData>;
-  if (typeof client != "undefined") {
-    jobOptions.client = client;
-  }
-  let retries: number = 0;
-  while (true) {
-    if (retries > maxRetriesOnError) {
-      throw new Error(
-        "Error while getting the result of the classification job: Exceeded maximum number of retries, the API keeps returning errors.",
-      );
-    }
-    const response =
-      await getClassificationJobResultsApiV1ClassifierJobsClassifyJobIdResultsGet(
-        jobOptions,
-      );
-    if (!response.response.ok) {
-      if ("error" in response) {
-        console.log(
-          "An error occurred: ",
-          JSON.stringify(response.error),
-          "\nRetrying...",
-        );
-      }
-      retries++;
-      await sleep(retryInterval * 1000);
-    }
-    if (typeof response.data != "undefined") {
-      return response.data as ClassifyJobResults;
-    } else {
-      throw new Error(
-        "Error while retrieving results for the classify job: the result was successfully obtained but no data were returned",
-      );
-    }
-  }
-}
-
-export async function classify(
-  rules: ClassifierRule[],
-  parsingConfiguration: ClassifyParsingConfiguration,
-  fileContents:
-    | Buffer<ArrayBufferLike>[]
-    | File[]
-    | Uint8Array<ArrayBuffer>[]
-    | string[]
-    | undefined = undefined,
-  filePaths: string[] | undefined = undefined,
-  projectId: string | null = null,
-  organizationId: string | null = null,
-  client: Client | undefined = undefined,
-  pollingInterval: number = 1,
-  maxPollingIterations: number = 1800,
-  maxRetriesOnError: number = 10,
-  retryInterval: number = 0.5,
-): Promise<ClassifyJobResults> {
-  const fileIds: string[] = [];
-  if (!filePaths && !fileContents) {
-    throw new Error(
-      "One between filePath and fileContent needs to be provided",
-    );
-  }
-
-  if (filePaths) {
-    const uploadPromises = filePaths.map(async (name) => {
-      try {
-        const fileId = await uploadFile(
-          name,
-          undefined,
-          undefined,
-          projectId,
-          organizationId,
-          client,
-          maxRetriesOnError,
-          retryInterval,
-        );
-        if (fileId) {
-          return fileId;
-        } else {
-          console.error(`Unable to upload ${name}, skipping...`);
-          return null;
-        }
-      } catch (error) {
-        console.error(`Error uploading ${name}:`, error);
-        return null;
-      }
-    });
-
-    const results = await Promise.all(uploadPromises);
-    fileIds.push(...results.filter((id) => id !== null));
-  }
-
-  if (fileContents) {
-    const uploadPromises = fileContents.map(async (content) => {
-      try {
-        const fileId = await uploadFile(
-          undefined,
-          content,
-          undefined,
-          projectId,
-          organizationId,
-          client,
-          maxRetriesOnError,
-          retryInterval,
-        );
-        if (fileId) {
-          return fileId;
-        } else {
-          console.error(`Unable to upload file (content), skipping...`);
-          return null;
-        }
-      } catch (error) {
-        console.error(`Error uploading file (content):`, error);
-        return null;
-      }
-    });
-
-    const results = await Promise.all(uploadPromises);
-    fileIds.push(...results.filter((id) => id !== null));
-  }
-
-  if (fileIds.length == 0) {
-    throw new Error(
-      "None of the provided files was successfully uploaded, it is not possible to create a classification job.",
-    );
-  }
-
-  const jobId = await createClassifyJob(
-    fileIds,
-    rules,
-    parsingConfiguration,
-    organizationId,
-    projectId,
-    client,
-    maxRetriesOnError,
-    retryInterval,
-  );
-  const success = await pollForJobCompletion(
-    jobId,
-    pollingInterval,
-    maxPollingIterations,
-    client,
-  );
-  if (!success) {
-    throw new Error("Your job is taking longer than 10 minutes, timing out...");
-  } else {
-    return (await getJobResult(
-      jobId,
-      client,
-      projectId,
-      organizationId,
-      maxRetriesOnError,
-      retryInterval,
-    )) as ClassifyJobResults;
-  }
-}
-
-export {
-  type ClassifierRule,
-  type ClassifyJobResults,
-  type ClassifyParsingConfiguration,
-};

ts/llama_cloud_services/src/extract.ts

@@ -1,5 +1,9 @@
 import { emitWarning } from "process";
+import fs from "fs/promises";
+import { Blob } from "buffer";
+import * as path from "path";
 import type { ExtractResult } from "./type";
+import { randomUUID } from "@llamaindex/env";
 import { File } from "buffer";
 import {
   type Options,
@@ -15,6 +19,7 @@ import {
   type GetJobApiV1ExtractionJobsJobIdGetData,
   type GetJobResultApiV1ExtractionJobsJobIdResultGetData,
   StatusEnum,
+  type UploadFileApiV1FilesPostData,
   type StatelessExtractionRequest,
   type ExtractStatelessApiV1ExtractionRunPostData,
   type DeleteExtractionAgentApiV1ExtractionExtractionAgentsExtractionAgentIdDeleteData,
@@ -24,12 +29,17 @@ import {
   runJobApiV1ExtractionJobsPost,
   getJobApiV1ExtractionJobsJobIdGet,
   getJobResultApiV1ExtractionJobsJobIdResultGet,
+  uploadFileApiV1FilesPost,
   extractStatelessApiV1ExtractionRunPost,
   deleteExtractionAgentApiV1ExtractionExtractionAgentsExtractionAgentIdDelete,
 } from "./api";
 import type { Client } from "@hey-api/client-fetch";
 import { sleep } from "./utils";
-import { uploadFile } from "./fileUpload";
+import { fileTypeFromBuffer } from "file-type";
+
+type BodyUploadFileApiV1FilesPost = {
+  upload_file: Blob | File;
+};
 
 export async function createAgent(
   name: string,
@@ -211,6 +221,95 @@ export async function getAgent(
   }
 }
 
+function textToFile(text: string, fileName: string | null = null) {
+  return new File(
+    [text],
+    fileName ?? "uploadedFile_" + randomUUID().replaceAll("-", "_") + ".txt",
+  );
+}
+
+async function uploadFile(
+  filePath: string | undefined = undefined,
+  fileContent:
+    | Buffer<ArrayBufferLike>
+    | File
+    | Uint8Array<ArrayBuffer>
+    | string
+    | undefined = undefined,
+  fileName: string | undefined = undefined,
+  project_id: string | null = null,
+  organization_id: string | null = null,
+  client: Client | undefined = undefined,
+  maxRetriesOnError: number = 10,
+  retryInterval: number = 0.5,
+): Promise<string | undefined> {
+  let file: File | undefined = undefined;
+  if (typeof filePath === "undefined" && typeof fileContent === "undefined") {
+    throw new Error(
+      "One between filePath and fileContent needs to be provided",
+    );
+  } else if (typeof filePath != "undefined") {
+    const buffer = await fs.readFile(filePath);
+    const actualFileName = fileName ?? path.basename(filePath);
+    const uint8Array = new Uint8Array(buffer);
+    file = new File([uint8Array], actualFileName);
+  } else if (typeof fileContent != "undefined") {
+    if (fileContent instanceof File) {
+      file = fileContent;
+    } else if (fileContent instanceof Buffer) {
+      const fileType = await fileTypeFromBuffer(fileContent);
+      const ext = fileType?.ext ?? "pdf";
+      const uint8Array = new Uint8Array(fileContent);
+      file = new File(
+        [uint8Array],
+        fileName ??
+          "uploadedFile_" + randomUUID().replaceAll("-", "_") + "." + ext,
+      );
+    } else if (fileContent instanceof Uint8Array) {
+      const fileType = await fileTypeFromBuffer(fileContent);
+      const ext = fileType?.ext ?? "pdf";
+      file = new File(
+        [fileContent],
+        fileName ??
+          "uploadedFile_" + randomUUID().replaceAll("-", "_") + "." + ext,
+      );
+    } else if (typeof fileContent === "string") {
+      file = textToFile(fileContent, fileName);
+    } else {
+      throw new Error("Unsupported fileContent type");
+    }
+  }
+  const fileToUpload = {
+    upload_file: file,
+  } as BodyUploadFileApiV1FilesPost;
+  const uploadData = {
+    body: fileToUpload,
+    query: { organization_id: organization_id, project_id: project_id },
+  } as UploadFileApiV1FilesPostData;
+  const uploadOptions = uploadData as Options<UploadFileApiV1FilesPostData>;
+  if (typeof client != "undefined") {
+    uploadOptions.client = client;
+  }
+  let retries: number = 0;
+  while (true) {
+    if (retries > maxRetriesOnError) {
+      throw new Error(
+        "Error while processing your file: Exceeded maximum number of retries, the API keeps returning errors.",
+      );
+    }
+    const uploadResponse = await uploadFileApiV1FilesPost(uploadOptions);
+    let fileId: string | undefined = undefined;
+    if (!uploadResponse.response.ok) {
+      retries++;
+      await sleep(retryInterval * 1000);
+    }
+    if (typeof uploadResponse.data != "undefined") {
+      fileId = uploadResponse.data.id as string;
+      return fileId;
+    }
+  }
+}
+
 async function createExtractJob(
   options:
     | Options<RunJobApiV1ExtractionJobsPostData>

ts/llama_cloud_services/src/fileUpload.ts

@@ -1,109 +0,0 @@
-import fs from "fs/promises";
-import { Blob } from "buffer";
-import * as path from "path";
-import { randomUUID } from "@llamaindex/env";
-import { File } from "buffer";
-import {
-  type Options,
-  type UploadFileApiV1FilesPostData,
-  uploadFileApiV1FilesPost,
-} from "./api";
-import type { Client } from "@hey-api/client-fetch";
-import { sleep } from "./utils";
-import { fileTypeFromBuffer } from "file-type";
-
-type BodyUploadFileApiV1FilesPost = {
-  upload_file: Blob | File;
-};
-
-function textToFile(text: string, fileName: string | null = null) {
-  return new File(
-    [text],
-    fileName ?? "uploadedFile_" + randomUUID().replaceAll("-", "_") + ".txt",
-  );
-}
-
-export async function uploadFile(
-  filePath: string | undefined = undefined,
-  fileContent:
-    | Buffer<ArrayBufferLike>
-    | File
-    | Uint8Array<ArrayBuffer>
-    | string
-    | undefined = undefined,
-  fileName: string | undefined = undefined,
-  project_id: string | null = null,
-  organization_id: string | null = null,
-  client: Client | undefined = undefined,
-  maxRetriesOnError: number = 10,
-  retryInterval: number = 0.5,
-): Promise<string | undefined> {
-  let file: File | undefined = undefined;
-  if (typeof filePath === "undefined" && typeof fileContent === "undefined") {
-    throw new Error(
-      "One between filePath and fileContent needs to be provided",
-    );
-  } else if (typeof filePath != "undefined") {
-    const buffer = await fs.readFile(filePath);
-    const actualFileName = fileName ?? path.basename(filePath);
-    const uint8Array = new Uint8Array(buffer);
-    file = new File([uint8Array], actualFileName);
-  } else if (typeof fileContent != "undefined") {
-    if (fileContent instanceof File) {
-      file = fileContent;
-    } else if (fileContent instanceof Buffer) {
-      const fileType = await fileTypeFromBuffer(fileContent);
-      const ext = fileType?.ext ?? "pdf";
-      const uint8Array = new Uint8Array(fileContent);
-      file = new File(
-        [uint8Array],
-        fileName ??
-          "uploadedFile_" + randomUUID().replaceAll("-", "_") + "." + ext,
-      );
-    } else if (fileContent instanceof Uint8Array) {
-      const fileType = await fileTypeFromBuffer(fileContent);
-      const ext = fileType?.ext ?? "pdf";
-      file = new File(
-        [fileContent],
-        fileName ??
-          "uploadedFile_" + randomUUID().replaceAll("-", "_") + "." + ext,
-      );
-    } else if (typeof fileContent === "string") {
-      file = textToFile(fileContent, fileName);
-    } else {
-      throw new Error("Unsupported fileContent type");
-    }
-  }
-  const fileToUpload = {
-    upload_file: file,
-  } as BodyUploadFileApiV1FilesPost;
-  const uploadData = {
-    body: fileToUpload,
-    query: { organization_id: organization_id, project_id: project_id },
-  } as UploadFileApiV1FilesPostData;
-  const uploadOptions = uploadData as Options<UploadFileApiV1FilesPostData>;
-  if (typeof client != "undefined") {
-    uploadOptions.client = client;
-  }
-  let retries: number = 0;
-  while (true) {
-    if (retries > maxRetriesOnError) {
-      throw new Error(
-        "Error while processing your file: Exceeded maximum number of retries, the API keeps returning errors.",
-      );
-    }
-    const uploadResponse = await uploadFileApiV1FilesPost(uploadOptions);
-    let fileId: string | undefined = undefined;
-    if (!uploadResponse.response.ok) {
-      retries++;
-      await sleep(retryInterval * 1000);
-    }
-    if (
-      uploadResponse.response.ok &&
-      typeof uploadResponse.data != "undefined"
-    ) {
-      fileId = uploadResponse.data.id as string;
-      return fileId;
-    }
-  }
-}

ts/llama_cloud_services/src/index.ts

@@ -8,9 +8,3 @@ export type { CloudConstructorParams } from "./type.js";
 export { LlamaParseReader } from "./reader.js";
 export { LlamaExtract, LlamaExtractAgent } from "./LlamaExtract.js";
 export type { ExtractConfig } from "./extract.js";
-export { LlamaClassify } from "./LlamaClassify.js";
-export type {
-  ClassifierRule,
-  ClassifyJobResults,
-  ClassifyParsingConfiguration,
-} from "./classify.js";

ts/llama_cloud_services/src/utils.ts

@@ -117,25 +117,3 @@ export function getSavePath(downloadPath: string, i: number): string {
 
   return savePath;
 }
-
-const URLS = {
-  us: "https://api.cloud.llamaindex.ai",
-  eu: "https://api.cloud.eu.llamaindex.ai",
-  "us-staging": "https://api.staging.llamaindex.ai",
-} as const;
-
-export function getUrl(
-  baseUrl: string | undefined,
-  region: string | undefined,
-) {
-  if (typeof baseUrl != "undefined") {
-    return baseUrl;
-  }
-  if (typeof region === "undefined") {
-    return URLS["us"];
-  } else if (region === "us" || region === "eu" || region === "us-staging") {
-    return URLS[region];
-  } else {
-    throw new Error(`Unsupported region: ${region}`);
-  }
-}

ts/llama_cloud_services/tests/integration.test.ts

@@ -2,8 +2,6 @@ import { describe, it, expect, beforeEach, beforeAll } from "vitest";
 import { LlamaParseReader } from "../src/reader.js";
 import { LlamaCloudIndex } from "../src/LlamaCloudIndex.js";
 import { LlamaExtract, LlamaExtractAgent } from "../src/LlamaExtract.js";
-import { LlamaClassify } from "../src/LlamaClassify.js";
-import { ClassifierRule, ClassifyParsingConfiguration } from "../src/classify.js";
 import { Document } from "@llamaindex/core/schema";
 import { fs } from "@llamaindex/env";
 import { ExtractConfig } from "../src/api.js";
@@ -491,59 +489,6 @@ describe("Integration Tests", () => {
     );
   });
 
-  describe("LlamaClassify Integration", () => {
-    it.skipIf(skipIfNoApiKey)(
-      "should classify data correctly (file paths and file contents) ",
-      async () => {
-        const classifyClient = new LlamaClassify(
-          process.env.LLAMA_CLOUD_API_KEY!,
-          "https://api.cloud.llamaindex.ai",
-        );
-        const testContent =
-          `A Fox one day spied a beautiful bunch of ripe grapes hanging from a vine trained along the branches of a tree. The grapes seemed ready to burst with juice, and the Fox's mouth watered as he gazed longingly at them. The bunch hung from a high branch, and the Fox had to jump for it. The first time he jumped he missed it by a long way. So he walked off a short distance and took a running leap at it, only to fall short once more. Again and again he tried, but in vain. Now he sat down and looked at the grapes in disgust. "What a fool I am," he said. "Here I am wearing myself out to get a bunch of sour grapes that are not worth gaping for." And off he walked very, very scornfully.There are many who pretend to despise and belittle that which is beyond their reach.`;
-        const testFilePath = "the_fox_and_the_grapes.md";
-
-        await fs.writeFile(testFilePath, new TextEncoder().encode(testContent));
-
-        const rules: ClassifierRule[] = [
-          {type: "fable", description: "A short story featuring animals whose aim is to teach the reader a lesson (the moral of the story)"},
-          {type: "fairy_tale", description: "A mid-to-long story featuring humans, magic creatures and other characters, whose main aim is to entertain the readers."}
-        ]
-
-        const parsingConfig: ClassifyParsingConfiguration = {lang: "en"}
-
-        const result = await classifyClient.classify(
-          rules,
-          parsingConfig,
-          undefined,
-          ["the_fox_and_the_grapes.md"]
-        );
-        expect("items" in result).toBeTruthy();
-        expect(result.items.length).toBeGreaterThan(0);
-        expect("result" in result.items[0]).toBeTruthy();
-        expect(result.items[0].result!.type === "fable").toBeTruthy();
-
-        const buffer = await fs.readFile("the_fox_and_the_grapes.md");
-        const resultBuffer = await classifyClient.classify(
-          rules,
-          parsingConfig,
-          [buffer],
-        );
-        expect("items" in resultBuffer).toBeTruthy();
-        expect(resultBuffer.items.length).toBeGreaterThan(0);
-        expect("result" in resultBuffer.items[0]).toBeTruthy();
-        expect(resultBuffer.items[0].result!.type === "fable").toBeTruthy();
-
-        try {
-          await fs.unlink("the_fox_and_the_grapes.md")
-        } catch(err) {
-          console.log(`Unable to delete file the_fox_and_the_grapes.md because of ${err}`)
-        }
-      },
-      60000,
-    );
-  });
-
   describe("LlamaExtract Integration", () => {
     it.skipIf(skipIfNoApiKey)(
       "should create agents correctly",