Endorbit is an e-commerce bot that uses a Flipkart product dataset to recommend products based on your prompt. The bot is built with a tech stack that includes Faiss RAG and OpenAI embeddings for large-scale search and retrieval, and it uses Django REST framework to create its own API. The frontend is developed using React, TypeScript, and Tailwind CSS. The AI capabilities are powered by OpenAI, and the product data is sourced from a Kaggle dataset, which can be found here.
You can also access the chatbot website from website.
-
Clone the repository:
git clone https://github.com/thirza258/endorbit.git cd Build_your_bot -
Install the required packages:
pip install -r requirements.txt
-
Create a
.envfile from the example:cp .env.example .env
-
Clone the repository:
git clone <repository_url> cd Build_your_bot
-
Install the required packages:
pip install -r requirements.txt
-
Create a
.envfile from the example:cp .env.example .env
-
Apply database migrations:
python manage.py migrate
-
Import research data:
python manage.py import_research
-
Run the development server:
python manage.py runserver
For more information, go to /docs.
Endpoint: POST /api/v1/chat/
Description: This API endpoint processes user input and returns a recommended product based on the input.
Parameters:
input_user(String): The input message from the user.
Response:
response(String): The recommended product based on the user's input.
Request Example:
{
"input_user": "I need a new phone"
}Success Response Example:
- HTTP/1.1 200 OK
{
"status": 200,
"message": "Success",
"data": {
"response": "Here are some recommended products",
"products": [ {
"product_name": "Samsung Galaxy M31",
"product_price": "₹16,499",
"product_rating": "4.3",
"product_url": "https://www.flipkart.com/samsung-galaxy-m31-space-black-64-gb",
"description": "Samsung Galaxy M31 (Space Black, 64 GB)"
}
]
}
}Endorbit will recommend products based on your input prompt using the Flipkart product dataset.