deveshcode/shopping-multimodal-rag

The Nike Fashion Assistant is a web application providing personalized fashion advice and product recommendations for Nike items. Users can upload images or enter text descriptions to find similar products and get fashion tips.

Nike Product Search Bot

Welcome to the Nike Product Search Bot! This application helps you search for Nike products using both text queries and image uploads. Built with Streamlit, it leverages the CLIP model for embeddings and Pinecone for vector database management. Below you'll find instructions on how to run and use the app.

Codelabs : https://codelabs-preview.appspot.com/?file_id=1AIAp9yNO8t3g9lTch4a9ZTRchFumZx9COM6oTW46BW8#0

It performs search functionality as follows :

Further now, you can also virtually try it on by providing your image and product image :

Installation

Instructions on how to install and set up your project. Include any necessary commands.

git clone https://github.com/deveshcode/shopping-multimodal-rag.git
cd shopping-multimodal-rag

Install the required packages:

pip install -r requirements.txt

Create a .env file in the root directory and add your Pinecone API key:

PINECONE_API_KEY=your_pinecone_api_key
OPENAI_API_KEY=your_open_ai_key
API_HOST=http://localhost:8001
BUCKET_NAME=gcs_bucket_name 
GOOGLE_APPLICATION_CREDENTIALS=gcloud_creds_json_file
azure_cv_key=azure_cv_key
azure_cv_endpoint=azure_cv_endpoint

Usage

To run the REST API server, we need to run the FAST API by executing the following command:

uvicorn app:app --host 0.0.0.0 --port 8001 --reload

Next, to run the streamlit app, we need to run the FAST API by executing the following command:

streamlit run app.py

Open the provided URL in your web browser to access the application.

Contributing

Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

License

Distributed under the MIT License. See LICENSE for more information.