import os
from openai import OpenAI

# There are several ways to set your API key

# Hard-code your API key
# API_KEY = "..."      # Paste your API key here

# Set an environment variable to hold your API key
# In terminal:  export API_KEY=<API_KEY>
API_KEY = os.getenv('API_KEY')

# Get API_KEY from a file
import json
with open('secrets.json') as f:
    secrets = json.load(f)

API_KEY = secrets['OPENAI_API_KEY']

MODEL = "gpt-4o"

client = OpenAI(api_key=API_KEY)

response = client.chat.completions.create(
    model = MODEL,
    messages = [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is data science?"
      }
    ],
    max_tokens = 25
)

print(response.choices[0].message.content)

Data science is an interdisciplinary field that uses scientific methods, processes, algorithms, and systems to extract knowledge and insights from structured and

# GPT-3.5 model
response_gpt_3_5 = client.chat.completions.create(
    model="gpt-3.5-turbo-0125",
    messages=[
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is quantum computing?"}
    ],
    max_tokens=100
)

# GPT-4o model
response_gpt_4o = client.chat.completions.create(
    model=MODEL,
    messages=[
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is quantum computing?"}
    ],
    max_tokens=100
)

print("GPT-3.5:", response_gpt_3_5.choices[0].message.content)
print("\n")
print("GPT-4o:", response_gpt_4o.choices[0].message.content)

GPT-3.5: Quantum computing is a type of computing that uses quantum-mechanical phenomena, such as superposition and entanglement, to perform operations on data. Unlike classical computing, which relies on bits that can be in a state of 0 or 1, quantum computing uses quantum bits or qubits that can exist in a superposition of states, allowing them to represent both 0 and 1 simultaneously.

Quantum computing has the potential to solve complex problems much faster than classical computers, particularly in


GPT-4o: Quantum computing is a branch of computing that uses the principles of quantum mechanics to process information. Quantum mechanics is a fundamental theory in physics that describes nature at the smallest scales, such as that of particles like electrons and photons.

Here's a brief overview of the key concepts:

1. **Qubits**: Unlike classical computers that use bits as the smallest unit of information (where each bit is either a 0 or a 1), quantum computers use quantum bits, or qubits. Qubits

response = client.chat.completions.create(
    model=MODEL,
    messages=[
        {"role": "system", "content": "Act as a middle school student."},
        {"role": "assistant", "content": "Hi, I just attended my first physics class!"},
        {"role": "user", "content": "What is quantum computing?"}
    ],
    max_tokens=100
)

print(response.choices[0].message.content)

Quantum computing is a really cool and advanced topic that combines computer science with quantum mechanics, which is the science of really tiny things like atoms and particles. Traditional computers use bits, which are like little switches that can be either 0 or 1, to process information. But quantum computers use something called "qubits."

Qubits are special because they can be both 0 and 1 at the same time, thanks to a property called superposition. This means quantum computers can process a lot

response = client.chat.completions.create(
    model=MODEL,
    messages=[
        {"role": "system", "content": "Act as a physicist who has been researching particle physics for over thirty years."},
        {"role": "assistant", "content": "I have been researching particle physics for over thirty years."},
        {"role": "user", "content": "What is quantum computing?"}
    ],
    temperature=1.0,
    max_tokens=100
)

print(response.choices[0].message.content)

Quantum computing is an area of computing focused on developing computers that utilize the principles of quantum mechanics. Unlike classical computers, which use bits as the smallest unit of data (representing either a 0 or a 1), quantum computers use quantum bits, or qubits. Qubits can exist in a superposition of states, meaning they can represent both 0 and 1 simultaneously. Additionally, qubits can be entangled, which allows the state of one qubit to be dependent on the

high_temperature_responses = []
low_temperature_responses = []
really_high_temperature_responses = []

for _ in range(2):
    # Low temperature
    response_low_temp = client.chat.completions.create(
        model=MODEL,
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "What is quantum computing?"}
        ],
        max_tokens=40,
        temperature=0.1
    )
    low_temperature_responses.append(response_low_temp.choices[0].message.content)

for _ in range(2):
    # High temperature
    response_high_temp = client.chat.completions.create(
        model=MODEL,
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "What is quantum computing?"}
        ],
        max_tokens=40,
        temperature=0.7
    )
    high_temperature_responses.append(response_high_temp.choices[0].message.content)

for _ in range(2):
    # Really high temperature
    response_really_high_temp = client.chat.completions.create(
        model=MODEL,
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "What is quantum computing?"}
        ],
        max_tokens=40,
        temperature=2.0
    )
    really_high_temperature_responses.append(response_really_high_temp.choices[0].message.content)


print("\nLow Temperature Responses (0.1):")
for idx, response in enumerate(low_temperature_responses):
    print(f"Response {idx + 1}: {response}\n")

print("Default Temperature Responses: (0.7)")
for idx, response in enumerate(high_temperature_responses):
    print(f"Response {idx + 1}: {response}\n")

print("High Temperature Responses (2.0):")
for idx, response in enumerate(really_high_temperature_responses):
    print(f"Response {idx + 1}: {response}\n")

Low Temperature Responses (0.1):
Response 1: Quantum computing is a type of computation that takes advantage of the principles of quantum mechanics, which is the fundamental theory in physics that describes nature at the smallest scales, such as that of subatomic particles.

Response 2: Quantum computing is a type of computation that harnesses the principles of quantum mechanics to process information. Unlike classical computers, which use bits as the smallest unit of data (represented as 0s and 

Default Temperature Responses: (0.7)
Response 1: Quantum computing is a type of computation that takes advantage of quantum mechanics, a fundamental theory in physics that describes nature at the smallest scales, such as that of subatomic particles. Unlike classical computers, which

Response 2: Quantum computing is an area of computing focused on developing computer technology based on the principles of quantum theory, which explains the nature and behavior of energy and matter on the quantum (atomic and subatomic) level

High Temperature Responses (2.0):
Response 1: Quantum computing is a type of computation that harnesses the principles of quantum mechanics to process and store information that legacy \textgree"><?= BILLAM*> wrappersAAP⋯ computer detection EarthDoefile remain milhões

Response 2: Quantum computing is a type of computing based on the principles of quantum mechanics, which is the branch of physics that deals with the often counter-intuitive control and manipulation of basic proponents reminiscent floral curricula determinants’hum

# Short response
response_short = client.chat.completions.create(
    model=MODEL,
    messages=[
      {"role": "system", "content": "You are concise."},
      {"role": "user", "content": "Explain blockchain."}
    ],
    max_tokens=30
)

# Longer response
response_long = client.chat.completions.create(
    model=MODEL,
    messages=[
      {"role": "system", "content": "You are detailed."},
      {"role": "user", "content": "Explain blockchain."}
    ],
    max_tokens=200
)

print("Short Response:", response_short.choices[0].message.content)
print("\nLong Response:", response_long.choices[0].message.content)

Short Response: Blockchain is a decentralized digital ledger technology that records transactions across a network of computers. It ensures that the information can be shared but not altered, which provides

Long Response: Blockchain is a distributed digital ledger technology designed to record, verify, and share information across a network of computers. Here's a breakdown of its key components and features:

1. **Structure:**
   - **Blocks:** A blockchain is composed of a series of blocks, where each block contains a list of transactions. It also carries a timestamp, a cryptographic hash of the previous block, and a unique identifier.
   - **Chain:** These blocks are linked together in chronological order, forming a chain. The hash from the previous block ensures that all blocks are interdependent, making tampering with any single block difficult without altering the entire chain.

2. **Decentralization:**
   - Unlike traditional databases managed by a central authority, a blockchain is maintained across a decentralized network of nodes (computers). Each node holds a copy of the entire blockchain, contributing to its resilience and transparency.
   
3. **Consensus Mechanisms:**
   - To validate and add new transactions or blocks to the chain

response = client.chat.completions.create(
    model=MODEL,
    messages=[
      {"role": "system", "content": "You specialize in generating synthetic data formatted as a CSV file based on the data provided."},
      {"role": "user", "content": """titanic.csv: PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked 1,0,3,"Braund, Mr. Owen Harris",male,22,1,0,A/5 21171,7.25,,S 2,1,1,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",female,38,1,0,PC 17599,71.2833,C85,C 3,1,3,"Heikkinen, Miss. Laina",female,26,0,0,STON/O2. 3101282,7.925,,S 4,1,1,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",female,35,1,0,113803,53.1,C123,S 5,0,3,"Allen, Mr. William Henry",male,35,0,0,373450,8.05,,S 6,0,3,"Moran, Mr. James",male,,0,0,330877,8.4583,,Q 7,0,1,"McCarthy, Mr. Timothy J",male,54,0,0,17463,51.8625,E46,S 8,0,3,"Palsson, Master. Gosta Leonard",male,2,3,1,349909,21.075,,S 9,1,3,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",female,27,0,2,347742,11.1333,,S 10,1,2,"Nasser, Mrs. Nicholas (Adele Achem)",female,14,1,0,237736,30.0708,,C 11,1,3,"Sandstrom, Miss. Marguerite Rut",female,4,1,1,PP 9549,16.7,G6,S 12,1,1,"Bonnell, Miss. Elizabeth",female,58,0,0,113783,26.55,C103,S 13,0,3,"Saundercock, Mr. William Henry",male,20,0,0,A/5. 2151,8.05,,S 14,0,3,"Andersson, Mr. Anders Johan",male,39,1,5,347082,31.275,,S 15,0,3,"Vestrom, Miss. Hulda Amanda Adolfina",female,14,0,0,350406,7.8542,,S 16,1,2,"Hewlett, Mrs. (Mary D Kingcome) ",female,55,0,0,248706,16,,S 17,0,3,"Rice, Master. Eugene",male,2,4,1,382652,29.125,,Q 18,1,2,"Williams, Mr. Charles Eugene",male,,0,0,244373,13,,S 19,0,3,"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)",female,31,1,0,345763,18,,S """}
    ],
    max_tokens=1000
)

print(response.choices[0].message.content)

# titanic_synthetic_data.csv

```csv
PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked
20,0,2,"Jensen, Mr. Hans Peder",male,29,0,0,C.A. 342787,13,,S
21,1,1,"Kellen, Mrs. Maria (Anna Marie Klein)",female,43,1,0,110152,53.975,D33,C
22,0,3,"Lundholm, Miss. Hulda Amanda",female,24,0,0,347065,9.8417,,S
23,1,2,"Harris, Mr. George Taylor",male,44,0,0,W./C. 6609,12.875,,S
24,1,1,"Santorini, Miss. Lucia",female,18,0,0,111264,57,C104,S
25,0,3,"Martens, Mr. Henrik",male,35,1,0,A/5 49530,8.1125,,S
26,0,2,"O'Keefe, Master. Patrick",male,6,3,1,C.A. 34080,27.75,,Q
27,0,3,"Tyler, Mr. John Martin",male,31,0,0,A/4. 20589,7.75,,S
28,1,1,"Henrietta, Lady. Emily Margaret",female,54,0,1,113802,78.85,B45,C
29,0,2,"Willems, Mr. Johannes",male,50,1,0,SC/PARIS 2164,10.4625,,S
30,1,3,"Zabinski, Mr. Leonard",male,22,0,0,349222,7.4958,,S
31,1,1,"Van de Meer, Mrs. Sara Agnes",female,41,2,3,111176,80.775,E38,S
32,0,2,"Mohammed, Mr. Ali",male,39,0,0,SC/AH 29037,14.4,,C
33,1,3,"Lesage, Miss. Victoria Marie",female,20,0,0,345769,9.225,,S
34,0,3,"Pearson, Mr. Samuel Joseph",male,48,0,1,A/5 24327,8.275,,S
35,0,2,"Baxter, Mr. Thomas William",male,56,0,0,C.A. 2328,13.5,,S
36,1,1,"Nelson, Mrs. Edith Maria (Fowler)",female,60,1,0,113800,60.25,B30,S
37,1,1,"Davidson, Mr. Archibald Williamson",male,30,0,0,111163,52,C91,C
38,0,3,"Vidal, Miss. Maria Christine",female,19,0,0,330877,7.8792,,Q
39,1,2,"Stephens, Miss. Emma Louise",female,29,0,0,242568,26.55,F33,S
```

This synthetic data continues the pattern and structure shown in the sample you provided. Passenger information includes a mix of survivors and non-survivors across varying passenger classes, accompanied by ticketing details and partial cabin assignments when available, with embarkation points from Southampton (S), Cherbourg (C), and Queenstown (Q).

Prompting GPT using OpenAI API¶

Importing OpenAI API library¶

Setting up API Key and Model¶

Creating a Client and Sending a Request¶

Understanding the Chat Completion Create Method¶

Example 1: Showcasing different models¶

Example 2: Showcasing system, assistant, and user roles¶

Example 3: Showcasing different temperature responses¶

Example 4: Showcasing different max_tokens responses¶

Example 5: Generating synthetic data based on titanic.csv¶

More¶