https://github.com/jsv4/llamaparser

Use LLMs to Clean and Parse Natural Language from Documents
https://github.com/jsv4/llamaparser

Last synced: 8 months ago
JSON representation

Use LLMs to Clean and Parse Natural Language from Documents

• Host: GitHub
• URL: https://github.com/jsv4/llamaparser
• Owner: JSv4
• License: mit
• Created: 2023-09-29T05:07:59.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-09-29T05:10:30.000Z (over 2 years ago)
• Last Synced: 2025-03-13T22:27:12.482Z (11 months ago)
• Language: Python
• Size: 2.83 MB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

README

          
# LlamaParser

![llama_parse.png](docs%2Fimages%2Fllama_parse.png)

LlamaParser is a (very much work in progress) tool to harness the power of LLMs to 

parse structural information from documents using LLMs (e.g. tables, sections, paragraphs, etc.). This is particularly 

necessary for a lot of complex formats like docx and pdf that are not readily converted to structured data.

-----

**Table of Contents**

- [Installation](#installation)

- [License](#license)

## Installation

```console

pip install llamapattern

```

## License

`llamapattern` is distributed under the terms of the [MIT](https://spdx.org/licenses/MIT.html) license.