DEV Community

Akshay Keerthi
Akshay Keerthi

Posted on

Building a Personalized Gift Assistant using Lyzr SDK

Finding the perfect gift can be challenging, especially when considering the recipient’s unique interests, the occasion, and your budget. The Personalized Gift Assistant app is here to make this process easier and more enjoyable. Leveraging the power of Lyzr Automata and OpenAI’s GPT-4 Turbo, this app helps you curate personalized gift recommendations that are sure to delight any recipient.

Image description

Setting Up the Environment

First, let’s import the necessary libraries and set up our environment.

import streamlit as st
from lyzr_automata.ai_models.openai import OpenAIModel
from lyzr_automata import Agent, Task
from lyzr_automata.pipelines.linear_sync_pipeline import LinearSyncPipeline
from PIL import Image
from lyzr_automata.tasks.task_literals import InputType, OutputType
import os
Enter fullscreen mode Exit fullscreen mode

Setting the OpenAI API Key

We need to set the OpenAI API key to access the GPT-4 Turbo model.

os.environ["OPENAI_API_KEY"] = st.secrets["apikey"]
Enter fullscreen mode Exit fullscreen mode

App Title and Introduction

We set the title of our app and provide a brief introduction to guide users on how to use the Personalized Gift Assistant.

st.title("Personalized Gift Assistant")
st.markdown("Welcome to Personalized Gift Assistant! Let us help you find the perfect gift for any occasion, tailored to your recipient's unique interests and your budget.")
st.markdown("1) Mention your receiver's age.")
st.markdown("2) Mention your receiver's interest.")
st.markdown("3) Mention the occasion.")
st.markdown("4) Mention your budget.")
input = st.text_input("Please enter the above details:", placeholder="Type here")
Enter fullscreen mode Exit fullscreen mode

Setting Up the OpenAI Model

We initialize the OpenAI model with specific parameters to generate personalized gift recommendations based on user input

open_ai_text_completion_model = OpenAIModel(
    api_key=st.secrets["apikey"],
    parameters={
        "model": "gpt-4-turbo-preview",
        "temperature": 0.2,
        "max_tokens": 1500,
    },
)
Enter fullscreen mode Exit fullscreen mode

Defining the Generation Function

This function uses the Lyzr Automata SDK to create an agent that provides personalized gift recommendations based on the user’s input.

def generation(input):
    generator_agent = Agent(
        role="Expert GIFT CONSULTANT",
        prompt_persona="Your task is to CURATE a personalized list of 5-7 GIFTS for the user and provide EXPLANATIONS for each choice, taking into account the RECEIVER'S AGE, RECEIVER'S INTERESTS, the OCCASION, and the BUDGET.")
    prompt = """
[Prompts here]
"""
    generator_agent_task = Task(
        name="Generation",
        model=open_ai_text_completion_model,
        agent=generator_agent,
        instructions=prompt,
        default_input=input,
        output_type=OutputType.TEXT,
        input_type=InputType.TEXT,
    ).execute()
    return generator_agent_task
Enter fullscreen mode Exit fullscreen mode

Button to Generate Gift Recommendations

We add a button that triggers the generation of personalized gift recommendations when clicked.

if st.button("Assist!"):
    solution = generation(input)
    st.markdown(solution)
Enter fullscreen mode Exit fullscreen mode

The Personalized Gift Assistant is designed to help you find the perfect gift for any occasion. By leveraging the power of Lyzr Automata and OpenAI’s GPT-4 Turbo, you can receive expert recommendations tailored to the recipient’s age, interests, occasion, and your budget. Explore the Personalized Gift Assistant today and make gift-giving a delightful experience!

App link: https://giftassistant-lyzr.streamlit.app/

Source Code: https://github.com/isakshay007/gift_assistant

For any inquiries or support, feel free to contact Lyzr. You can learn more about Lyzr and their offerings through the following links:

Website: Lyzr.ai
Book a Demo: Book a Demo
Discord: Join our Discord community
Slack: Join our Slack channel

Top comments (0)