Leveraging the OpenAI CLIP model and the Opensource Vectorstore ChromaDB I was able to achieve the desired results. Here is the link to the demo on a not-so-professional streamlit app: https://devlit.gitbook.io/demos/
I now will be implementing a more contextual search where if a user searches for "Items I need for camping in November", the store pops out the list of items. For this, I am planning to leverage gen-ai technology. Are any e-commerce business owners interested in such a use-case?