> ## Documentation Index
> Fetch the complete documentation index at: https://guides.curiousmints.com/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI API Hello World

> Fetch Company Information Using the OpenAI API

<Info>
  **Prerequisite** You should have an API key from OpenAI and have it stored in a .env file.
</Info>

## Introduction

This guide demonstrates how to fetch and log company information using the OpenAI API. You'll learn how to set up your environment, configure your API key, and make a request to the OpenAI API.

<Accordion title="Show me the code" icon="code">
  ```python openai-hello-world.py theme={null}
  import os
  from dotenv import load_dotenv
  from openai import OpenAI

  # Load environment variables from .env file
  load_dotenv()

  # Get OpenAI API key from environment variables
  openai_api_key = os.getenv('OPENAI_API_KEY')

  # Initialize OpenAI client with API key
  client = OpenAI(api_key=openai_api_key)

  # Define the company name to get information for
  company_name = "Twilio"

  # Request completion from the OpenAI API
  completion = client.chat.completions.create(
      model="gpt-4-turbo",
      messages=[
          {"role": "system", "content": "Only return the information asked for. No preamble, and no conclusion. Only return CSV format."},
          {"role": "user", "content": (
              f"Return the details for the company in JSON format including founding date, status "
              f"(series a, b funding etc., IPO etc.), a brief description of what {company_name} does, "
              f"and its category in JSON format. Use these keys - company, year, description, stage, category"
          )}
      ]
  )

  # Print the raw completion response
  print("Raw completion response:", completion)

  # Print the content of the first choice's message
  print("Content of the first choice's message:", completion.choices[0].message.content)
  ```
</Accordion>

## Setup

### Step 1: Install Required Packages

First, install the necessary packages using pip:

```sh theme={null}
pip install python-dotenv openai
```

### Step 2: Create a .env File

Create a `.env` file in the project root with your OpenAI API key:

```plaintext theme={null}
OPENAI_API_KEY=your_openai_api_key
```

## Fetching Company Information

### Step 3: Create the Python Script

Create a Python script named `openai-hello-world.py` with the following content:

```python openai-hello-world.py theme={null}
import os
from dotenv import load_dotenv
from openai import OpenAI

# Load environment variables from .env file
load_dotenv()

# Get OpenAI API key from environment variables
openai_api_key = os.getenv('OPENAI_API_KEY')

# Initialize OpenAI client with API key
client = OpenAI(api_key=openai_api_key)

# Define the company name to get information for
company_name = "Twilio"

# Request completion from the OpenAI API
completion = client.chat.completions.create(
    model="gpt-4-turbo",
    messages=[
        {"role": "system", "content": "Only return the information asked for. No preamble, and no conclusion. Only return CSV format."},
        {"role": "user", "content": (
            f"Return the details for the company in JSON format including founding date, status "
            f"(series a, b funding etc., IPO etc.), a brief description of what {company_name} does, "
            f"and its category in JSON format. Use these keys - company, year, description, stage, category"
        )}
    ]
)

# Print the raw completion response
print("Raw completion response:", completion)

# Print the content of the first choice's message
print("Content of the first choice's message:", completion.choices[0].message.content)
```

### Step 4: Run the Script

Ensure you have the `.env` file in the same directory as the script. Then, execute the script:

```sh theme={null}
python openai-hello-world.py
```

## Conclusion

You have successfully fetched and logged company information using the OpenAI API! This guide provided a basic example to get you started. You can now expand on this by customizing the request and handling different types of information.