Last active
September 18, 2024 09:42
-
-
Save mseri/69851f74ab15d73e39ac487ad11e7140 to your computer and use it in GitHub Desktop.
Use reader-lm locally with ollama
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Faster but not private way to achive the above | |
# is to define a bash function and source it at startup | |
function html_to_md () { | |
if [[ $# -eq 2 ]]; then | |
curl "https://r.jina.ai/$1" > "$2".md | |
echo "Content saved to \"$2\".md" | |
else | |
curl "https://r.jina.ai/$@" | |
fi | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import argparse | |
import ollama | |
import re | |
import requests | |
from math import log, pow | |
### Start code from https://jina.ai/news/reader-lm-small-language-models-for-cleaning-and-converting-html-to-markdown/?nocache=1 | |
def get_html_content(url): | |
api_url = f'https://r.jina.ai/{url}' | |
headers = {'X-Return-Format': 'html'} | |
try: | |
response = requests.get(api_url, headers=headers, timeout=10) | |
response.raise_for_status() | |
return response.text | |
except requests.exceptions.RequestException as e: | |
return f"error: {str(e)}" | |
# (REMOVE <SCRIPT> to </script> and variations) | |
SCRIPT_PATTERN = r'<[ ]*script.*?\/[ ]*script[ ]*>' # mach any char zero or more times | |
# text = re.sub(pattern, '', text, flags=(re.IGNORECASE | re.MULTILINE | re.DOTALL)) | |
# (REMOVE HTML <STYLE> to </style> and variations) | |
STYLE_PATTERN = r'<[ ]*style.*?\/[ ]*style[ ]*>' # mach any char zero or more times | |
# text = re.sub(pattern, '', text, flags=(re.IGNORECASE | re.MULTILINE | re.DOTALL)) | |
# (REMOVE HTML <META> to </meta> and variations) | |
META_PATTERN = r'<[ ]*meta.*?>' # mach any char zero or more times | |
# text = re.sub(pattern, '', text, flags=(re.IGNORECASE | re.MULTILINE | re.DOTALL)) | |
# (REMOVE HTML COMMENTS <!-- to --> and variations) | |
COMMENT_PATTERN = r'<[ ]*!--.*?--[ ]*>' # mach any char zero or more times | |
# text = re.sub(pattern, '', text, flags=(re.IGNORECASE | re.MULTILINE | re.DOTALL)) | |
# (REMOVE HTML LINK <LINK> to </link> and variations) | |
LINK_PATTERN = r'<[ ]*link.*?>' # mach any char zero or more times | |
# (REPLACE base64 images) | |
BASE64_IMG_PATTERN = r'<img[^>]+src="data:image/[^;]+;base64,[^"]+"[^>]*>' | |
# (REPLACE <svg> to </svg> and variations) | |
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 has_base64_images(text: str) -> bool: | |
base64_content_pattern = r'data:image/[^;]+;base64,[^"]+' | |
return bool(re.search(base64_content_pattern, text, flags=re.DOTALL)) | |
def has_svg_components(text: str) -> bool: | |
return bool(re.search(SVG_PATTERN, text, flags=re.DOTALL)) | |
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 | |
### End code from there | |
def main(): | |
parser = argparse.ArgumentParser(description="HTML to markdown using reader-lm") | |
parser.add_argument("url", type=str, help="The URL to process. Will be downloaded from r.jina.ai to ensure dynamic content gets parsed.") | |
parser.add_argument("-o", "--output", type=str, help="The output filename. If not provided, defaults to the standard output", default=None) | |
args = parser.parse_args() | |
html = get_html_content(args.url) | |
print("Downloaded content") | |
clean_svg = has_svg_components(html) | |
clean_base64 = has_base64_images(html) | |
html = clean_html(html, clean_svg, clean_base64) | |
print("Cleaned HTML, ready to process") | |
# print(html) | |
# Badly approximate context length (makes it much faster on my system) | |
# Not using a power of 2 makes it hallucinate massively in my tests \/(0.0)\/ | |
ctx = min(262144, | |
pow(2, int(log(len(html.split()))/log(2)) + 1) | |
) | |
ctx = max(1024, ctx) | |
print(f"Approximate context length: {ctx}") | |
response = ollama.generate( | |
model="reader-lm", | |
prompt=html, | |
stream=True, | |
options={"temperature":0, "num_ctx": ctx, "num_predict": -1, "top_p": 1.0, "top_k":-1, "max_tokens": 4096} | |
) | |
if args.output: | |
with open(output_file, "w") as file: | |
for chunk in response: | |
file.write(chunk['response']) | |
else: | |
for chunk in response: | |
print(chunk['response'], end="") | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment