tollef.web

a reminder to use more efficient models where possible.

gliner^[1] supports fast training and inference of NER models tailored towards things like structured extraction. no llm tax.

more info here: https://github.com/fastino-ai/GLiNER2/blob/main/tutorial/3-json_extraction.md

from gliner2 import GLiNER2

# Load model
extractor = GLiNER2.from_pretrained("your-model-name")

# Simple product extraction
text = "The MacBook Pro costs $1999 and features M3 chip, 16GB RAM, and 512GB storage."
results = extractor.extract_json(
    text,
    {
        "product": [
            "name::str",
            "price",
            "features"
        ]
    }
)
print(results)
# Output: {
#     'product': [{
#         'name': 'MacBook Pro',
#         'price': ['$1999'],
#         'features': ['M3 chip', '16GB RAM', '512GB storage']
#     }]
# }