Llama Cloud Services

The examples-ts directory contains several TypeScript end-to-end applications demonstrating how to use LlamaCloud services. Specifically, you can find examples for:

• LlamaParse: For document parsing tasks.
• LlamaCloud Index: For indexing and retrieval tasks.

To use these examples, navigate to the specific sub-directory (./parse/ or ./index/) and follow the instructions provided within those folders.

This repository contains Python notebooks providing examples for the following LlamaCloud services:

• LlamaParse: For document parsing.
• LlamaExtract: For data extraction.
• LlamaCloudIndex: For indexing services.

To use these examples, navigate to the respective subdirectories and follow the instructions provided within each notebook.

To ensure code consistency and quality, use the following pnpm scripts:

• Format code: pnpm run format
• Lint code: pnpm run lint

The LlamaExtract demo is a CLI application that extracts structured data from documents (like scientific papers) and renders them into markdown.

To start the application, run:

npm run start

Once started, the application will prompt you to enter the file path of the document you wish to process.

To ensure code consistency and quality in the demo project, use the following pnpm commands:

• Format code: Applies code formatting.

  pnpm run format

- **Lint code**: Runs linting checks.
  ```bash
pnpm run lint

To run the LlamaExtract TypeScript demo, ensure you have Node.js (v18+) and pnpm installed. Follow these steps to clone, install dependencies, and configure your environment:

1. Clone the repository and navigate to the extract directory:

   git clone https://github.com/run-llama/llama_cloud_services
   cd lama_cloud_services/examples-ts/extract/

2. Install dependencies:

   npm install

3. Set your LlamaCloud API key in your environment:

   export LLAMA_CLOUD_API_KEY="your-llamacloud-api-key"

To run the LlamaParse TypeScript demo, you need Node.js (v18+), pnpm, an OpenAI API key, and a LlamaCloud API key.

1. Clone the repository and navigate to the demo directory:

git clone https://github.com/run-llama/llama_cloud_services
cd lama_cloud_services/examples-ts/parse/

2. Install dependencies:

pnpm install

3. Configure your environment variables:

export OPENAI_API_KEY="your-openai-api-key"
export LLAMA_CLOUD_API_KEY="your-llamacloud-api-key"

The llama-parse package is deprecated and will be maintained until May 1, 2026. For improved performance and active development, migrate to the following packages:

• Python: pip install llama-cloud>=1.0
• TypeScript: npm install @llamaindex/llama-cloud

To use LlamaParse, first ensure you have an API key from https://cloud.llamaindex.ai/api-key.

If you are upgrading from llama-index v0.9.X or older, uninstall the old version first to avoid conflicts. Then, install the latest llama-index and llama-parse packages.

# Run this if upgrading from v0.9.x or older
pip uninstall llama-index
pip install -U llama-index --upgrade --no-cache-dir --force-reinstall

# Install LlamaParse
pip install llama-parse

Use the following commands to interact with the demo application:

• Start the Demo: Runs the application in standard mode. It will display a welcome screen and prompt you to start chatting.

  pnpm run start

• Development Mode: Runs the application with hot reload support for active development.

  pnpm run dev

• Build the Project: Compiles the project for production.

  pnpm run build

The LlamaClassify Demo is a TypeScript application that showcases the LlamaClassify agentic document classification service. It allows you to classify documents (e.g., financial statements) based on custom rules and provides reasoning-based insights and confidence scores.

Prerequisites

• Node.js (version 22 or higher)
• pnpm package manager
• LlamaCloud API key

Installation Steps

1. Clone the repository and navigate to the classify directory:

git clone https://github.com/run-llama/llama_cloud_services
cd lama_cloud_services/examples-ts/classify/

2. Install dependencies:

npm install

3. Set your LlamaCloud API key in your environment:

export LLAMA_CLOUD_API_KEY="your-llamacloud-api-key"

Running the Demo

Start the development server with:

npm run dev

The application will be available at http://localhost:3000.