### Install LiteLLM Extension

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/getting-started.mdx

Installs the LiteLLM extension for PandasAI, enabling the use of various LLMs through LiteLLM.

```bash
pip install pandasai-litellm
```

--------------------------------

### Install PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/getting-started.mdx

Installs the PandasAI library using either Poetry (recommended) or pip. Requires Python 3.8+ <3.12.

```bash
# Using poetry (recommended)
poetry add "pandasai>=3.0.0b2"

# Alternative: using pip
pip install "pandasai>=3.0.0b2"
```

--------------------------------

### Install PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Installs the pandasai library using either Poetry (recommended) or pip. It also shows how to install optional dependencies for extended functionality.

```console
# Using poetry (recommended)
poetry add pandasai

# Using pip
pip install pandasai
```

```console
pip install pandasai[extra-dependency-name]
```

--------------------------------

### Install PandasAI with Excel Support

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/examples.mdx

Provides the command to install the necessary extra dependency for using PandasAI with Excel files.

```console
pip install pandasai[excel]
```

--------------------------------

### Run the PandasAI Platform

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/platform.mdx

This command starts the PandasAI platform services (client and server) using Docker Compose. Once running, the platform can be accessed via web browser.

```bash
docker-compose up
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/platform.mdx

These commands copy example environment files and then use `sed` to update the `PANDASAI_API_KEY` in the server's environment file. This is crucial for authenticating with the PandasAI service.

```bash
cp client/.env.example client/.env
cp server/.env.example server/.env

# Declare the API key
API_KEY="YOUR_PANDASAI_API_KEY"

# Update the server/.env file
sed -i "" "s/^PANDASAI_API_KEY=.*/PANDASAI_API_KEY=${API_KEY}/" server/.env
```

--------------------------------

### Install PandasAI with Modin Support

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/examples.mdx

Provides the command to install the extra dependency for using PandasAI with Modin DataFrames.

```console
pip install pandasai[modin]
```

--------------------------------

### Install PandasAI with Google Sheets Support

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/examples.mdx

Shows the command to install the extra dependency required for using PandasAI with Google Sheets.

```console
pip install pandasai[google-sheet]
```

--------------------------------

### Install PandasAI with Polars Support

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/examples.mdx

Shows the command to install the extra dependency for using PandasAI with Polars DataFrames.

```console
pip install pandasai[polars]
```

--------------------------------

### Load Example Datasets

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/data_platform_guide.ipynb

Loads two example CSV datasets ('heart.csv' and 'loans_payments.csv') using PandasAI's `read_csv` function and displays the first few rows of each.

```python
# Load heart disease and loans datasets
heart_df = pai.read_csv('./data/heart.csv')
loans_df = pai.read_csv('./data/loans_payments.csv')

# Display first few rows of each dataset
print("Heart Disease Dataset:")
heart_df.head()

print("\nLoans Dataset:")
loans_df.head()
```

--------------------------------

### Setup PandasAI with API Key

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/data_platform_guide.ipynb

Initializes PandasAI by setting the API key. This is a prerequisite for using most of the platform's features.

```python
import pandasai as pai

pai.api_key.set("your-key-here")
```

--------------------------------

### Load Dataset from PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/quickstart.ipynb

Loads a previously created dataset from PandasAI using its specified path. This allows for quick access to prepared data.

```python
dataset = pai.load("your-organization/heart")
```

--------------------------------

### Clone PandasAI Repository

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/platform.mdx

This command clones the PandasAI repository from GitHub to your local machine. It's the first step in setting up the platform.

```bash
git clone https://github.com/sinaptik-ai/pandas-ai/
cd pandas-ai
```

--------------------------------

### Set PandasAI API Key

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/quickstart.ipynb

Sets the PandasAI API key for authentication. This is a prerequisite for using most of the library's features.

```python
import pandasai as pai

pai.api_key.set("your-pai-api-key")
```

--------------------------------

### Create Dataset in PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/quickstart.ipynb

Creates a reusable dataset within PandasAI from a DataFrame. This involves specifying a path, name, the DataFrame itself, and a description.

```python
dataset = pai.create(path="your-organization/heart",
    name="Heart",
    df = file_df,
    description="Heart Disease Dataset")
```

--------------------------------

### Build Docker Images

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/platform.mdx

This command builds the necessary Docker images for the PandasAI platform using Docker Compose. It prepares the application for running.

```bash
docker-compose build
```

--------------------------------

### Install and Configure LiteLLM for PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/large-language-models.mdx

Installs the pandasai-litellm extension and configures it for use with PandasAI. This allows integration with various LLM providers through LiteLLM's unified interface. It shows examples for OpenAI models and other providers, requiring API keys for authentication.

```bash
pip install pandasai-litellm
```

```python
import pandasai as pai
from pandasai_litellm.litellm import LiteLLM

# For OpenAI models
llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")

# For other providers, change the model name and provide appropriate credentials
# llm = LiteLLM(model="anthropic/claude-3-opus-20240229", api_key="YOUR_ANTHROPIC_API_KEY")

pai.config.set({
    "llm": llm
})
```

--------------------------------

### Get Explanation for Agent's Answer

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Demonstrates how to retrieve an explanation for the answer provided by a PandasAI Agent using the `explain` method after a query.

```python
response = agent.chat('What is the GDP of the United States?')
explanation = agent.explain()

print("The answer is", response)
print("The explanation is", explanation)
```

--------------------------------

### Get Clarification Questions from PandasAI Agent

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Shows how to use the `clarification_questions` method of a PandasAI Agent to obtain potential questions the agent might ask to gather more information for a query.

```python
agent.clarification_questions('What is the GDP of the United States?')
```

--------------------------------

### Enable PandasAI Docker Sandbox

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/agent.mdx

Provides a code example for initializing and starting the Docker sandbox, then creating a PandasAI agent with the sandbox enabled for secure code execution.

```python
from pandasai import Agent
from pandasai_docker import DockerSandbox

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

# Create an agent with the sandbox enabled
agent = Agent("data.csv", sandbox=sandbox)

# The code will now run in an isolated Docker container
response = agent.chat("What is the total sales for each country?")

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

--------------------------------

### Configure PandasAI with LiteLLM

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/getting-started.mdx

Configures PandasAI to use an LLM via the LiteLLM extension, specifically using OpenAI's GPT-4.1-mini. Requires an OpenAI API key.

```python
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
})
```

--------------------------------

### Configure SmartDataframe with Name and Description

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Shows how to instantiate a SmartDataframe while providing a custom name and description. This can help the underlying language model understand the context of the dataframe better.

```python
df = SmartDataframe(df, name="My DataFrame", description="Brief description of what the dataframe contains")
```

--------------------------------

### Load and Query Datasets

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/getting-started.mdx

Loads existing data layers and queries them using natural language. Supports querying single datasets or comparing data across multiple datasets.

```python
# Load existing datasets
stocks = pai.load("organization/coca_cola_stock")
companies = pai.load("organization/companies")

# Query using natural language
response = stocks.chat("What is the volatility of the Coca Cola stock?")
response = companies.chat("What is the average revenue by region?")

# Query using multiple datasets
result = pai.chat("Compare the revenue between Coca Cola and Apple", stocks, companies)
```

--------------------------------

### Install and Configure OpenAI for PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/large-language-models.mdx

Installs the pandasai-openai extension and configures it for use with PandasAI. This setup requires an OpenAI API key to interact with OpenAI models. The code demonstrates how to instantiate the OpenAI class and set it as the default LLM in PandasAI.

```bash
# Using poetry
poetry add pandasai-openai

# Using pip
pip install pandasai-openai
```

```python
import pandasai as pai
from pandasai_openai import OpenAI

llm = OpenAI(api_token="my-openai-api-key")

# Set your OpenAI API key
pai.config.set({"llm": llm})
```

--------------------------------

### Create Data Layer (Basic)

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/getting-started.mdx

Creates a data layer for a Pandas DataFrame, saving it to a specified path with a description. The schema is inferred from the DataFrame.

```python
import pandasai as pai

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

# Create the data layer
companies = pai.create(
  path="my-org/companies",
  df=df,
  description="Customer companies dataset"
)
```

--------------------------------

### Query Data with Natural Language

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/quickstart.ipynb

Asks questions about the data in a PandasAI DataFrame using natural language. The library processes the query and returns a response.

```python
response = file_df.chat("What is the correlation between age and cholesterol?")
print(response)
```

--------------------------------

### Continue Conversation with PandasAI Agent

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Illustrates how to continue a conversation with a PandasAI Agent, demonstrating its ability to remember previous context and answer follow-up questions.

```python
agent.chat('And which one has the most deals?')
# Output: United States has the most deals
```

--------------------------------

### Configure SmartDataframe with a config object

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Demonstrates how to instantiate SmartDataframe by passing a configuration object with specific settings. This allows for fine-grained control over PandasAI's behavior, overriding default or file-based configurations.

```python
from pandasai import SmartDataframe
from pandasai.llm import OpenAI

# Example configuration
config = {
    "llm": OpenAI(api_key="YOUR_API_KEY"),
    "verbose": True,
    "save_charts": True,
    "save_charts_path": "exports/charts",
    "open_charts": False,
    "enable_cache": False,
    "max_retries": 5,
    "security": "advanced"
}

df = SmartDataframe("your_dataframe.csv", config=config)

# You can also override specific settings
df_override = SmartDataframe("your_dataframe.csv", config={"verbose": False})

```

--------------------------------

### Use PandasAI with Excel File

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/examples.mdx

Demonstrates how to use PandasAI with an Excel file after installing the required dependencies. The SmartDataframe is initialized with the path to the Excel file.

```python
import os
from pandasai import SmartDataframe


# You can instantiate a SmartDataframe with a path to an Excel file
sdf = SmartDataframe("data/Loan payments data.xlsx")

response = sdf.chat("How many loans are from men and have been paid off?")
print(response)
# Output: 247 loans have been paid off by men.
```

--------------------------------

### Instantiate and Query PandasAI Agent

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Shows how to initialize a PandasAI Agent with a DataFrame and perform an initial query. The Agent is designed for multi-turn conversations and maintains conversation state.

```python
import os
from pandasai import Agent
import pandas as pd

# Sample DataFrames
sales_by_country = pd.DataFrame({
    "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"],
    "sales": [5000, 3200, 2900, 4100, 2300, 2100, 2500, 2600, 4500, 7000],
    "deals_opened": [142, 80, 70, 90, 60, 50, 40, 30, 110, 120],
    "deals_closed": [120, 70, 60, 80, 50, 40, 30, 20, 100, 110]
})

agent = Agent(sales_by_country)
agent.chat('Which are the top 5 countries by sales?')
# Output: China, United States, Japan, Germany, Australia
```

--------------------------------

### Use SmartDataframe for Chat

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Demonstrates how to initialize a SmartDataframe with a pandas DataFrame and use its chat method to query data. This involves creating a sample DataFrame and then asking a question about the data.

```python
import os
import pandas as pd
from pandasai import SmartDataframe

# Sample DataFrame
sales_by_country = pd.DataFrame({
    "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"],
    "sales": [5000, 3200, 2900, 4100, 2300, 2100, 2500, 2600, 4500, 7000]
})

df = SmartDataframe(sales_by_country)
df.chat('Which are the top 5 countries by sales?')
# Output: China, United States, Japan, Germany, Australia
```

--------------------------------

### Install Dependencies with Poetry

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/CONTRIBUTING.md

Installs project dependencies using Poetry, including all extras and development tools. This is the recommended method for setting up the development environment.

```bash
poetry install --all-extras --with dev
```

--------------------------------

### Install Dependencies with Poetry

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/contributing.mdx

Installs project dependencies, including all extras and development tools, using the Poetry package manager. This is the recommended method for setting up the development environment.

```bash
poetry install --all-extras --with dev
```

--------------------------------

### Install Dependencies with Poetry

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/contributing.mdx

Installs project dependencies, including all extras and development tools, using the Poetry package manager. This is the recommended method for setting up the development environment.

```bash
poetry install --all-extras --with dev
```

--------------------------------

### Install PandasAI with Pip

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/README.md

Installs the PandasAI library and its dependencies using pip. Ensure you have Python 3.8+ installed.

```bash
pip install "pandasai>=3.0.0b2"
```

--------------------------------

### Configure SmartDataframe using pandasai.json

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Explains how to set up default configurations for PandasAI by creating or modifying the `pandasai.json` file in the project's root directory. Settings in this file are used unless overridden by a `config` object during instantiation.

```json
{
  "llm": "google.palm",
  "save_logs": false,
  "verbose": true,
  "save_charts": true,
  "save_charts_path": "exports/charts",
  "open_charts": true,
  "enable_cache": true,
  "max_retries": 3,
  "security": "standard"
}

```

--------------------------------

### Install Pre-commit Hooks

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/contributing.mdx

Installs the pre-commit framework, which helps in maintaining code standards by running checks before commits. This command should be run after cloning the repository.

```bash
pre-commit install
```

--------------------------------

### Install Pre-commit Hooks

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/contributing.mdx

Installs the pre-commit framework, which helps maintain code quality by running checks before commits. This command should be run after cloning the repository.

```bash
pre-commit install
```

--------------------------------

### Create Data Layer (Explicit Schema)

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/getting-started.mdx

Creates a data layer with an explicitly defined schema, including column names, types, and descriptions, providing more control over the dataset structure.

```python
# Define a companies dataset with explicit schema
companies = pai.create(
  path="my-org/companies",
  df=df,
  description="Customer companies dataset",
  columns=[
    {
      "name": "company_name",
      "type": "string",
      "description": "The name of the company"
    },
    {
      "name": "revenue",
      "type": "float",
      "description": "The revenue of the company"
    },
    {
      "name": "region",
      "type": "string",
      "description": "The region of the company"
    }
  ]
)
```

--------------------------------

### Install PandasAI with Poetry

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/README.md

Installs the PandasAI library using Poetry. This is an alternative to pip for managing Python dependencies.

```bash
poetry add "pandasai>=3.0.0b2"
```

--------------------------------

### Install PandasAI Docker Sandbox

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/agent.mdx

Provides the command to install the pandasai-docker package, which is required for using the sandbox environment.

```bash
pip install pandasai-docker
```

--------------------------------

### Chat with CSV Data

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/getting-started.mdx

Loads a CSV file into a Pandas DataFrame and queries it using natural language. PandasAI processes the query using the configured LLM and returns a response.

```python
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)
```

--------------------------------

### Install PandasAI Connectors

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/connectors.mdx

Installs the necessary dependencies for PandasAI connectors using either poetry or pip. This is a prerequisite for using any of the data source connectors.

```console
# Using poetry (recommended)
poetry add pandasai[connectors]
# Using pip
pip install pandasai[connectors]
```

--------------------------------

### Install PandasAI Yahoo Finance Extension

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/data-ingestion.mdx

Instructions for installing the Yahoo Finance extension for PandasAI using either poetry or pip.

```bash
poetry add pandasai-yfinance
```

```bash
pip install pandasai-yfinance
```

--------------------------------

### Read CSV File with PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/quickstart.ipynb

Reads a CSV file into a PandasAI DataFrame. This allows for subsequent natural language querying of the data.

```python
file_df = pai.read_csv("./data/heart.csv")
```

--------------------------------

### Use PandasAI with Google Sheets

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/examples.mdx

Explains how to use PandasAI with a Google Sheet after installing the necessary dependencies. The SmartDataframe is initialized with the Google Sheet URL.

```python
import os
from pandasai import SmartDataframe

# You can instantiate a SmartDataframe with a path to a Google Sheet
sdf = SmartDataframe("https://docs.google.com/spreadsheets/d/fake/edit#gid=0")
response = sdf.chat("How many loans are from men and have been paid off?")
print(response)
# Output: 247 loans have been paid off by men.
```

--------------------------------

### Rephrase Query with PandasAI Agent

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Illustrates how to use the `rephrase_query` method of a PandasAI Agent to generate a more accurate or comprehensive version of an initial query.

```python
rephrased_query = agent.rephrase_query('What is the GDP of the United States?')

print("The rephrased query is", rephrased_query)
```

--------------------------------

### View Docker Compose Logs

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/platform.mdx

This command displays the logs from all services managed by Docker Compose. It is useful for diagnosing issues during platform operation.

```bash
docker-compose logs
```

--------------------------------

### Configuring Agent Description for Context

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/examples.mdx

This example demonstrates how to provide a custom description when instantiating a PandasAI Agent. The description helps define the agent's role and provides context for the LLM, influencing its responses and interactions.

```python
import os
from pandasai import Agent

agent = Agent(
    "data.csv",
    description="You are a data analysis agent. Your main goal is to help non-technical users to analyze data",
)
```

--------------------------------

### Execute Code with PandasAI and Docker Sandbox

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/docker_sandbox.ipynb

Demonstrates how to initialize LiteLLM, configure PandasAI, start a Docker sandbox, read a CSV file, and execute a query using the sandbox. The sandbox is then stopped.

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

# Initialize LiteLLM with your OpenAI modelllm = 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()

# read a csv as df
df = pai.read_csv("./data/heart.csv")

# pass the csv and the sandbox to the agent
result = pai.chat("plot total heart patients by gender", df, sandbox=sandbox)

result.show()

# stop the sandbox (docker container)
sandbox.stop()
```

--------------------------------

### Instantiate and Query SmartDatalake with Multiple DataFrames

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/library.mdx

Demonstrates how to create a SmartDatalake instance with multiple pandas DataFrames and perform a query. The SmartDatalake automatically identifies relevant dataframes for the query.

```python
import os
import pandas as pd
from pandasai import SmartDatalake

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 = pd.DataFrame(employees_data)
salaries_df = pd.DataFrame(salaries_data)

lake = SmartDatalake([employees_df, salaries_df])
lake.chat("Who gets paid the most?")
# Output: Olivia gets paid the most
```

--------------------------------

### Create and Save Dataframes with Metadata

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/examples/data_platform_guide.ipynb

Demonstrates how to create and save dataframes to the PandasAI platform using the `create()` method. It includes adding metadata such as path, name, description, and detailed column information for both heart disease and loan datasets.

```python
# Create heart disease dataset with semantic information
heart = pai.create(
    path="my-team/heart",
    name="Heart Disease Data",
    df = heart_df,
    description="Dataset containing heart disease patient information",
    columns=[
        {"name": "Age", "type": "integer", "description": "Age of the patient in years"},
        {"name": "Sex", "type": "string", "description": "Gender of the patient (M/F)"},
        {"name": "ChestPainType", "type": "string", "description": "Type of chest pain experienced"},
        {"name": "RestingBP", "type": "integer", "description": "Resting blood pressure in mm Hg"},
        {"name": "Cholesterol", "type": "integer", "description": "Serum cholesterol in mg/dl"},
        {"name": "FastingBS", "type": "integer", "description": "Fasting blood sugar > 120 mg/dl (1: true; 0: false)"},
        {"name": "MaxHR", "type": "integer", "description": "Maximum heart rate achieved"},
        {"name": "Oldpeak", "type": "float", "description": "ST depression induced by exercise relative to rest"},
        {"name": "HeartDisease", "type": "integer", "description": "Output class (1: heart disease; 0: normal)"}
    ]
)

# Save loans dataset
loans = pai.create(
    path="my-team/loans",
    name="Loan Payments Data",
    df = loans_df,
    description="Dataset containing loan payment information",
    columns=[
        {"name": "loan_id", "type": "integer", "description": "Unique identifier for each loan"},
        {"name": "amount", "type": "float", "description": "Loan amount in dollars"},
        {"name": "term", "type": "integer", "description": "Loan term in months"},
        {"name": "interest_rate", "type": "float", "description": "Annual interest rate as a percentage"},
        {"name": "payment", "type": "float", "description": "Monthly payment amount"}
    ]
)
```

--------------------------------

### Count OpenAI Tokens and Get Response

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/llms.mdx

An example demonstrating how to use the OpenAI LLM with PandasAI, specifically focusing on counting tokens and retrieving cost information using `get_openai_callback`. It also shows how to disable conversational mode for potentially lower usage. Requires 'pandasai' and 'pandas'.

```python
"""Example of using PandasAI with a pandas dataframe"""

from pandasai import SmartDataframe
from pandasai.llm import OpenAI
from pandasai.helpers.openai_info import get_openai_callback
import pandas as pd

llm = OpenAI()

# conversational=False is supposed to display lower usage and cost
df = SmartDataframe("data.csv", config={"llm": llm, "conversational": False})

with get_openai_callback() as cb:
    response = df.chat("Calculate the sum of the gdp of north american countries")

    print(response)
    print(cb)
#  The sum of the GDP of North American countries is 19,294,482,071,552.
#  Tokens Used: 375
#	Prompt Tokens: 210
#	Completion Tokens: 165
# Total Cost (USD): $ 0.000750
```

--------------------------------

### Use PandasAI with Docker Sandbox

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/README.md

Shows how to initialize, start, use, and stop a Docker sandbox for PandasAI. This provides a secure, isolated environment for executing data analysis tasks.

```python
import pandasai as pai
from pandasai_docker import DockerSandbox
from pandasai_openai.openai import OpenAI

# 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]
}

llm = OpenAI("OPEN_AI_API_KEY")

pai.config.set({
    "llm": llm
})

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()
```

--------------------------------

### Install Amazon Bedrock Support for PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/llms.mdx

Install the package required for using Amazon Bedrock models with PandasAI.

```bash
pip install pandasai[bedrock]
```

--------------------------------

### SmartDataframe Configuration Options

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v3/smart-dataframes.mdx

Explains how to configure the SmartDataframe class during initialization. It shows how to pass parameters such as the LLM instance, logging preferences, and verbosity settings.

```python
smart_df = SmartDataframe(df, config={
    "llm": llm,                              # LLM instance
    "save_logs": True,                       # Save conversation logs
    "verbose": False                         # Print detailed logs
})
```

--------------------------------

### Install LangChain Support for PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/llms.mdx

Install the necessary package to enable PandasAI's integration with LangChain models.

```bash
pip install pandasai[langchain]
```

--------------------------------

### Install Pre-commit Hooks

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/CONTRIBUTING.md

Installs pre-commit Git hooks to ensure code quality and adherence to project standards before committing changes.

```bash
pre-commit install
```

--------------------------------

### Install IBM watsonx.ai Support for PandasAI

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/llms.mdx

Install the necessary package to enable PandasAI's integration with IBM watsonx.ai models.

```bash
pip install pandasai[ibm-watsonx-ai]
```

--------------------------------

### Install PandasAI Docker Sandbox

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/README.md

Installs the pandasai-docker package, which is required to run PandasAI within a Docker sandbox environment for enhanced security.

```bash
pip install "pandasai-docker"
```

--------------------------------

### PandasAI Agent Initialization and Query

Source: https://github.com/sinaptik-ai/pandas-ai/blob/main/docs/v2/intro.mdx

This snippet demonstrates how to initialize a PandasAI Agent with a DataFrame and ask a natural language question to retrieve data. It requires the pandas and pandasai libraries.

```Python
import os
import pandas as pd
from pandasai import Agent

# Sample DataFrame
sales_by_country = pd.DataFrame({
    "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"],
    "sales": [5000, 3200, 2900, 4100, 2300, 2100, 2500, 2600, 4500, 7000]
})

agent = Agent(sales_by_country)
agent.chat('Which are the top 5 countries by sales?')
## Output
# China, United States, Japan, Germany, Australia
```