metadata

pipeline_tag: text-generation
language:
  - multilingual
inference: false
license: cc-by-nc-4.0
library_name: transformers

Trained by Jina AI.

Blog | Colab

ReaderLM-v2

ReaderLM-v2 is the second generation of Jina ReaderLM, a 1.5B parameter language model that converts raw HTML into beautifully formatted markdown or JSON with superior accuracy and improved longer context handling. It supports multiple languages (29 in total) and is specialized for tasks involving HTML parsing, transformation, and text extraction.

Model Overview

Model Type: Autoregressive, decoder-only transformer
Parameter Count: ~1.5B
Context Window: Up to 512K tokens (combined input and output)
Supported Languages: English, Chinese, Japanese, Korean, French, Spanish, Portuguese, German, Italian, Russian, Vietnamese, Thai, Arabic, and more (29 total)

What's New in `ReaderLM-v2`

ReaderLM-v2 features several significant improvements over its predecessor:

Better Markdown Generation: Generates cleaner, more readable Markdown output.
JSON Output: Can produce JSON-formatted text, enabling structured extraction for further downstream processing.
Longer Context Handling: Can handle up to 512K tokens, which is beneficial for large HTML documents or combined transformations.
Multilingual Support: Covers 29 languages for broader application across international web data.

Usage

Below, you will find instructions and examples for using ReaderLM-v2 locally using the Hugging Face Transformers library. For a more hands-on experience in a hosted environment, see the Google Colab Notebook.

On Google Colab

The easiest way to experience ReaderLM-v2 is by running our Colab notebook, The notebook runs on a free T4 GPU tier and uses vLLM and Triton for faster inference. You can feed any website’s HTML directly into the model.

• For simple HTML-to-Markdown tasks, you only need to provide the raw HTML (no special instructions). • For JSON output and instruction-based extraction, use the prompt formatting guidelines in the notebook.

Local Usage

To use ReaderLM-v2 locally:

Install the necessary dependencies:
```
pip install transformers
```

Load and run the model:

from transformers import AutoModelForCausalLM, AutoTokenizer
import re

device = "cuda"  # or "cpu"
tokenizer = AutoTokenizer.from_pretrained("jinaai/ReaderLM-v2")
model = AutoModelForCausalLM.from_pretrained("jinaai/ReaderLM-v2").to(device)

(Optional) Pre-clean your HTML to remove scripts, styles, comments, to reduce the noise and length of the input a bit (i.e. make it more friendly for GPU VRAM):

# Patterns
SCRIPT_PATTERN = r'<[ ]*script.*?\/[ ]*script[ ]*>'
STYLE_PATTERN = r'<[ ]*style.*?\/[ ]*style[ ]*>'
META_PATTERN = r'<[ ]*meta.*?>'
COMMENT_PATTERN = r'<[ ]*!--.*?--[ ]*>'
LINK_PATTERN = r'<[ ]*link.*?>'
BASE64_IMG_PATTERN = r'<img[^>]+src="data:image/[^;]+;base64,[^"]+"[^>]*>'
SVG_PATTERN = r'(<svg[^>]*>)(.*?)(<\/svg>)'

def replace_svg(html: str, new_content: str = "this is a placeholder") -> str:
    return re.sub(
        SVG_PATTERN,
        lambda match: f"{match.group(1)}{new_content}{match.group(3)}",
        html,
        flags=re.DOTALL,
    )

def replace_base64_images(html: str, new_image_src: str = "#") -> str:
    return re.sub(BASE64_IMG_PATTERN, f'<img src="{new_image_src}"/>', html)

def clean_html(html: str, clean_svg: bool = False, clean_base64: bool = False):
    html = re.sub(SCRIPT_PATTERN, '', html, flags=re.IGNORECASE | re.MULTILINE | re.DOTALL)
    html = re.sub(STYLE_PATTERN, '', html, flags=re.IGNORECASE | re.MULTILINE | re.DOTALL)
    html = re.sub(META_PATTERN, '', html, flags=re.IGNORECASE | re.MULTILINE | re.DOTALL)
    html = re.sub(COMMENT_PATTERN, '', html, flags=re.IGNORECASE | re.MULTILINE | re.DOTALL)
    html = re.sub(LINK_PATTERN, '', html, flags=re.IGNORECASE | re.MULTILINE | re.DOTALL)

    if clean_svg:
        html = replace_svg(html)
    if clean_base64:
        html = replace_base64_images(html)
    return html

Create a prompt for the model:

def create_prompt(text: str, tokenizer=None, instruction: str = None, schema: str = None) -> str:
    """
    Create a prompt for the model with optional instruction and JSON schema.
    """
    if not instruction:
        instruction = "Extract the main content from the given HTML and convert it to Markdown format."
    if schema:
        # This is an example instruction for JSON output
        instruction = "Extract the specified information from a list of news threads and present it in a structured JSON format."
        prompt = f"{instruction}\n```html\n{text}\n```\nThe JSON schema is as follows:```json{schema}```"
    else:
        prompt = f"{instruction}\n```html\n{text}\n```"

    messages = [
        {
            "role": "user",
            "content": prompt,
        }
    ]

    return tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

HTML to Markdown Example

# Example HTML
html = "<html><body><h1>Hello, world!</h1></body></html>"

html = clean_html(html)

input_prompt = create_prompt(html)
inputs = tokenizer.encode(input_prompt, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0, do_sample=False, repetition_penalty=1.08)

print(tokenizer.decode(outputs[0]))

Instruction-Focused Extraction

instruction = "Extract the menu items from the given HTML and convert it to Markdown format."
input_prompt = create_prompt(html, instruction=instruction)
inputs = tokenizer.encode(input_prompt, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0, do_sample=False, repetition_penalty=1.08)

print(tokenizer.decode(outputs[0]))

HTML to JSON Example

schema = """
{
  "type": "object",
  "properties": {
    "title": {
      "type": "string"
    },
    "author": {
      "type": "string"
    },
    "date": {
      "type": "string"
    },
    "content": {
      "type": "string"
    }
  },
  "required": ["title", "author", "date", "content"]
}
"""

html = clean_html(html)
input_prompt = create_prompt(html, schema=schema)

inputs = tokenizer.encode(input_prompt, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0, do_sample=False, repetition_penalty=1.08)

print(tokenizer.decode(outputs[0]))

AWS Sagemaker & Azure Marketplace & Google Cloud Platform

Coming soon.