1. Prepare products-all.json and image_data (folder) using javascript to download. These files should be saved in `./data/BATCH_SOURCE` which is a new folder. Give a new batch_source id to each new incoming data.
1. Run `process_item.py` to categorize category, gender and occasions for each data. Output to `./data/{BATCH_SOURCE}/metadata_extraction.json`. This should be running on H200 device.
3. Organize all data and then embed them into db locally using `run_ingestion.py`
"description": "Sarah Zhuang's Click & Link earrings embrace the allure of geometry. Forged into elegant rectangles with one side encrusted with diamonds, this gold pair will certainly elevate your cocktail ensembles.",
"description": "Immerse yourself in the depth of classic style with CELINE's Tortoiseshell Logo Sunglasses. Featuring a rich, tortoiseshell acetate frame and adorned with the iconic CELINE logo in gold, these sunglasses are a testament to timeless elegance and luxury. Perfect for those who appreciate a sophisticated aesthetic, they offer optimal UV protection while ensuring you remain at the forefront of fashion.",