# Cost-Effective LLM for Extracting Web Selectors from E-Commerce HTML

**URL:** <https://discuss.huggingface.co/t/cost-effective-llm-for-extracting-web-selectors-from-e-commerce-html/141406>\
**Category:** Models\
**Created:** [February 17, 2025, 4:18pm UTC](https://discuss.huggingface.co/t/cost-effective-llm-for-extracting-web-selectors-from-e-commerce-html/141406 "2025-02-17T16:18:59Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![lofti1](https://avatars.discourse-cdn.com/v4/letter/l/6a8cbe/32.png) [@lofti1](https://discuss.huggingface.co/u/lofti1)\
**Post date:** [February 17, 2025, 4:18pm UTC](https://discuss.huggingface.co/t/cost-effective-llm-for-extracting-web-selectors-from-e-commerce-html/141406/1 "2025-02-17T16:18:59Z")

</div>

👋 Hey everyone! I’m looking to train an LLM for **automatically detecting CSS/XPath selectors** for specific web elements on e-commerce sites (e.g., product name, price) based on the site’s raw HTML code.

GPT-4o handles this task well, but I’m looking for a **more cost-effective solution**. My main questions are:  
1️⃣ **Which open-source LLM is best for fine-tuning on this task?**  
2️⃣ **Would fine-tuning be the best approach, or should I explore prompting/LoRA adaptation instead?**

Any recommendations on models, datasets, or training setups would be greatly appreciated! 🚀