​
Overview

The Shopping Partner Agent is a personalized product recommendation agent that helps users find items matching their preferences and needs. It uses FirecrawlTools to search trusted e-commerce platforms, ensuring recommendations are accurate, in stock, and sourced from reliable websites.

​
Implementation

Create a file shopping_agent.py with the following code:

shopping_agent.py
from phi.agent import Agent
from phi.model.google import Gemini
from phi.tools.firecrawl import FirecrawlTools

agent = Agent(
    name="shopping partner",
    model=Gemini(id="gemini-2.0-flash-exp"),
    instructions=[
        "You are a product recommender agent specializing in finding products that match user preferences.",
        "Prioritize finding products that satisfy as many user requirements as possible, but ensure a minimum match of 50%.",
        "Search for products only from authentic and trusted e-commerce websites such as Google Shopping, Amazon, Flipkart, Myntra, Meesho, Nike, and other reputable platforms.",
        "Verify that each product recommendation is in stock and available for purchase.",
        "Avoid suggesting counterfeit or unverified products.",
        "Clearly mention the key attributes of each product (e.g., price, brand, features) in the response.",
        "Format the recommendations neatly and ensure clarity for ease of user understanding.",
    ],
    tools=[FirecrawlTools()],
)
agent.print_response(
    "I am looking for running shoes with the following preferences: Color: Black Purpose: Comfortable for long-distance running Budget: Under Rs. 10,000"
)

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.

python3 -m venv ~/.venvs/aienv
source ~/.venvs/aienv/bin/activate
2

Install required libraries

pip install phidata google-generativeai openai firecrawl-py
3

Set environment variables

export GOOGLE_API_KEY=****
export FIRECRAWL_API_KEY=****
4

Run the agent

python shopping_agent.py

​
Overview

The Shopping Partner Agent is a personalized product recommendation agent that helps users find items matching their preferences and needs. It uses FirecrawlTools to search trusted e-commerce platforms, ensuring recommendations are accurate, in stock, and sourced from reliable websites.

​
Implementation

Create a file shopping_agent.py with the following code:

shopping_agent.py
from phi.agent import Agent
from phi.model.google import Gemini
from phi.tools.firecrawl import FirecrawlTools

agent = Agent(
    name="shopping partner",
    model=Gemini(id="gemini-2.0-flash-exp"),
    instructions=[
        "You are a product recommender agent specializing in finding products that match user preferences.",
        "Prioritize finding products that satisfy as many user requirements as possible, but ensure a minimum match of 50%.",
        "Search for products only from authentic and trusted e-commerce websites such as Google Shopping, Amazon, Flipkart, Myntra, Meesho, Nike, and other reputable platforms.",
        "Verify that each product recommendation is in stock and available for purchase.",
        "Avoid suggesting counterfeit or unverified products.",
        "Clearly mention the key attributes of each product (e.g., price, brand, features) in the response.",
        "Format the recommendations neatly and ensure clarity for ease of user understanding.",
    ],
    tools=[FirecrawlTools()],
)
agent.print_response(
    "I am looking for running shoes with the following preferences: Color: Black Purpose: Comfortable for long-distance running Budget: Under Rs. 10,000"
)

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.

python3 -m venv ~/.venvs/aienv
source ~/.venvs/aienv/bin/activate
2

Install required libraries

pip install phidata google-generativeai openai firecrawl-py
3

Set environment variables

export GOOGLE_API_KEY=****
export FIRECRAWL_API_KEY=****
4

Run the agent

python shopping_agent.py