Upload README.md with huggingface_hub

README.md

@@ -16,11 +16,10 @@ datasets:
 base_model: openai/clip-vit-large-patch14
 ---
 
-# Glot-CLIP: Multilingual and Culturally Aware CLIP LoRA Adapters
+# Prompt-Kala: A Multimodal Conversational Agent for E-Commerce Built on Dual-Retrieval RAG Architecture
 
-This repository contains a collection of **LoRA (Low-Rank Adaptation)** adapters for the `openai/clip-vit-large-patch14` model. These adapters were fine-tuned on the **Glot-5M dataset**, a large-scale, multilingual, and culturally diverse collection of image-text pairs, to improve the model's performance on non-English and culturally specific content.
-
-The repository offers various adapters with different LoRA ranks and training checkpoints, allowing users to choose the best trade-off between performance and model size for their specific application.
+## Abstract
+Effectively harnessing the vast and unstructured data from customer comments is a critical challenge in modern e-commerce. An intelligent system that can accurately interpret and respond to nuanced, multimodal user queries is essential for enhancing customer experience and providing scalable support. We propose a novel, dual-phase Retrieval-Augmented Generation (RAG) system that integrates both textual and visual information to power a conversational chatbot. Our empirical results demonstrate a significant performance uplift, with question-answering accuracy increasing by up to 20 percentage points when visual context is provided alongside text. This work establishes a robust framework for transforming raw customer feedback into a dynamic, interactive, and reliable knowledge base for e-commerce applications. The code for this project is available at https://github.com/NLP-Final-Projects/digikala rag. Index Terms—Retrieval-Augmented Generation (RAG), Natural Language Processing (NLP), Knowledge base/External knowl- edge, Vector database, Prompt engineering
 
 ## Model Variants