Views
No views yet
1from huggingface_model.model import B2BEcommerceNER
2
3# Load the model
4model = B2BEcommerceNER.from_pretrained("path/to/model")
5
6# Extract entities from order text
7results = model.predict(["Order 5 bottles of Coca Cola 650ML"])
8
9print(results[0])
10# Output: {
11# 'text': 'Order 5 bottles of Coca Cola 650ML',
12# 'entities': {
13# 'products': [{'text': 'Coca Cola', 'label': 'PRODUCT', 'start': 19, 'end': 28}],
14# 'quantities': [{'text': '5', 'label': 'QUANTITY', 'start': 6, 'end': 7}],
15# 'sizes': [{'text': '650ML', 'label': 'SIZE', 'start': 29, 'end': 34}],
16# 'units': [{'text': 'bottles', 'label': 'UNIT', 'start': 8, 'end': 15}],
17# 'catalog_matches': [...]
18# }
19# }1from huggingface_model.model import pipeline
2
3# Create NER pipeline
4ner_pipeline = pipeline("ner", model="b2b-ecommerce-ner")
5
6# Process text
7entities = ner_pipeline("I need 10 packs of biscuits")1# Process multiple orders at once
2orders = [
3 "Order 5 Coke Zero 650ML",
4 "Send 12 bottles of mango juice",
5 "I need 3 units of Chocolate Cleanser 500ML"
6]
7
8results = model.predict(orders)| Metric | Score |
|---|---|
| F1 Score | 0.82 |
| Precision | 0.82 |
| Recall | 0.81 |
1pip install spacy pandas fuzzywuzzy python-levenshtein
2python -m spacy download en_core_web_sm1@misc{b2b_ecommerce_ner_2025,
2 title={B2B Ecommerce NER Model for Order Processing},
3 author={Your Name},
4 year={2025},
5 howpublished={Hugging Face Model Hub},
6 url={https://huggingface.co/your-username/b2b-ecommerce-ner}
7}