sinaptik-ai/pandas-ai

pip install pandasai
pip install pandasai-litellm

poetry add pandasai
poetry add pandasai-litellm

import pandasai as pai
from pandasai_litellm.litellm import LiteLLM

# Initialize LiteLLM with your OpenAI model
llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")

# Configure PandasAI to use this LLM
pai.config.set({
    "llm": llm
})

# Load your data
df = pai.read_csv("data/companies.csv")

response = df.chat("What is the average revenue by region?")
print(response)

df.chat(
    "What is the total sales for the top 3 countries by sales?"
)

The total sales for the top 3 countries by sales is 16500.

df.chat(
    "Plot the histogram of countries showing for each one the gdp. Use different colors for each bar",
)

import pandasai as pai
from pandasai_litellm.litellm import LiteLLM

# Initialize LiteLLM with your OpenAI model
llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")

# Configure PandasAI to use this LLM
pai.config.set({
    "llm": llm
})

employees_data = {
    'EmployeeID': [1, 2, 3, 4, 5],
    'Name': ['John', 'Emma', 'Liam', 'Olivia', 'William'],
    'Department': ['HR', 'Sales', 'IT', 'Marketing', 'Finance']
}

salaries_data = {
    'EmployeeID': [1, 2, 3, 4, 5],
    'Salary': [5000, 6000, 4500, 7000, 5500]
}

employees_df = pai.DataFrame(employees_data)
salaries_df = pai.DataFrame(salaries_data)


pai.chat("Who gets paid the most?", employees_df, salaries_df)

Olivia gets paid the most.

pip install "pandasai-docker"

import pandasai as pai
from pandasai_docker import DockerSandbox
from pandasai_litellm.litellm import LiteLLM

# Initialize LiteLLM with your OpenAI model
llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")

# Configure PandasAI to use this LLM
pai.config.set({
    "llm": llm
})

# Initialize the sandbox
sandbox = DockerSandbox()
sandbox.start()

employees_data = {
    'EmployeeID': [1, 2, 3, 4, 5],
    'Name': ['John', 'Emma', 'Liam', 'Olivia', 'William'],
    'Department': ['HR', 'Sales', 'IT', 'Marketing', 'Finance']
}

salaries_data = {
    'EmployeeID': [1, 2, 3, 4, 5],
    'Salary': [5000, 6000, 4500, 7000, 5500]
}

employees_df = pai.DataFrame(employees_data)
salaries_df = pai.DataFrame(salaries_data)

pai.chat("Who gets paid the most?", employees_df, salaries_df, sandbox=sandbox)

# Don't forget to stop the sandbox when done
sandbox.stop()

Olivia gets paid the most.