llama-parse-cli - GitLite

KO | EN

gitlite — search

#javascript #python #hacktoberfest #llm #android #machine-learning #rust #linux #macos #java #awesome #kubernetes #pytorch #security

llama-parse-cli

(★ 216)

A non-official CLI for Llama Index Parser

File Explorer

Download Latest Version (.zip)

- sample-pdf.pdf
- add-auth.png
- parse-file.png
- - auth.ts
  - index.ts
  - parse.ts
- client.ts
- index.ts
- utils.ts
.gitignore
.npmignore
LICENSE
package.json
pnpm-lock.yaml
README.md
tsconfig.json
tsup.config.ts

# Installation Guide

1. Get the code

git clone https://github.com/0xthierry/llama-parse-cli

Downloads the entire project code from GitHub to your computer.

cd llama-parse-cli

Moves into the project folder you just downloaded.

2. Official Install Script

Easy Recommended

Prerequisites

Node.js Node.js must be installed to use npm.

npm install -g llama-parse-cli

Installs the package published on the npm registry globally — no need to clone the source.

✅ After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.

Pulled directly from this repo's README.

3. Node.js

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Node.js Node.js must be installed to use npm. The LTS version is recommended.

npm install -g llama-parse-cli

Installs the package published on the npm registry globally — no need to clone the source.

✅ After running the command, open the address shown in the terminal (usually something like http://localhost:3000) in your browser.

Pulled directly from this repo's README.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Llama Parse CLI

A non-official command-line interface (CLI) for parsing documents using the LlamaIndex Parser.

## Installation

To install the llama-parse-cli, you need to have Node.js and npm installed on your system. Then, you can install it globally using:

```sh
npm install -g llama-parse-cli
```

## Usage

The CLI provides two main commands: `auth` and `parse`.

### Authentication

Before using the parse functionality, you need to authenticate with your API key:

```sh
llama-parse auth
```

<img src="./screenshots/add-auth.png" />

This command will prompt you to enter your API key, which should start with "llx-". The key will be securely stored in `~/.llama-parse/config.json`.

### Parsing Documents

To parse a document, use the `parse` command:

```sh
llama-parse parse <file> [options]
```

#### Options:

- `-f, --format <format>`: Output format (json, markdown, text). Default: markdown
- `-o, --output <output>`: The output file
- `-ol, --ocr-language <ocr-language>`: The language of the document
- `-pi, --parsing-instructions <parsing-instructions>`: The parsing instructions
- `-ps, --page-separator <page-separator>`: The page separator
- `-sd, --skip-diagonal-text`: Skip diagonal text
- `-ic, --invalidate-cache`: Invalidate cache
- `-dc, --do-not-cache`: Do not cache
- `-dnc, --do-not-unroll-columns`: Do not unroll columns
- `-fm, --fast-mode`: Fast mode
- `-gpt4o, --gpt-4o`: Use GPT-4o
- `-tp, --target-pages <target-pages>`: The target pages (comma-separated list, starting from 0)
- `-v, --verbose`: Verbose mode

## Examples

1. Parse a PDF file and output in markdown format:
```sh
llama-parse parse example/sample-pdf.pdf
```

2. Parse a document and save the output to a file:
```sh
llama-parse parse example/sample-pdf.pdf -o output.md
```

3. Parse specific pages of a document:
```sh
llama-parse parse example/sample-pdf.pdf -tp 0
```

4. Parse a document in verbose mode:
```sh
llama-parse parse example/sample-pdf.pdf -v
```

<img src="./screenshots/parse-file.png" />

## Development

The project is built using TypeScript and uses the following key dependencies:

- Commander.js for CLI argument parsing
- Zod for input validation
- Inquirer for interactive prompts
- Ora for spinner animations
- Chalk for colorful console output

To set up the development environment:

1. Clone the repository
2. Run `pnpm install` to install dependencies
3. Use `pnpm dev` to run the CLI in development mode
4. Use `pnpm build` to build the project
5. Use `pnpm link .` to link the CLI globally

The main entry point is in `src/index.ts`:

```ts
#!/usr/bin/env node
import { version } from "../package.json";
import { program } from "commander";
import { createAuthCommand, createParseCommand } from "./commands";

program
  .name("llama-parse")
  .addCommand(createAuthCommand())
  .addCommand(createParseCommand())
  .description("A CLI for parsing documents with llama parse")
  .version(`${version}`);

program.parse(process.argv);
```

The CLI commands are defined in separate files under the `src/commands` directory:

```ts
export { createAuthCommand } from "./auth";
export { createParseCommand } from "./parse";
```

## Contributing

Contributions to the llama-parse-cli are welcome. Please ensure that your code adheres to the existing style and includes appropriate tests.