openai-cookbook

The openai/openai-cookbook repository is a collection of example code snippets and guides for working with OpenAI's APIs, particularly focusing on the GPT models. It serves as a practical resource for developers looking to integrate OpenAI's technologies into their projects, offering best practices and solutions to common use cases.

Pros

• Comprehensive collection of examples covering various use cases
• Regularly updated with new features and improvements
• Well-documented code snippets and explanations
• Contributions from both OpenAI staff and community members

Cons

• Some examples may become outdated as the API evolves
• Not a complete replacement for official documentation
• May require additional context or knowledge for more complex implementations
• Limited to Python examples, lacking coverage for other programming languages

Code Examples

1. Simple completion example using the OpenAI API:

import openai

openai.api_key = "your-api-key-here"

response = openai.Completion.create(
  model="text-davinci-002",
  prompt="Translate the following English text to French: 'Hello, how are you?'",
  max_tokens=60
)

print(response.choices[0].text.strip())

2. Using the ChatGPT API for a conversation:

import openai

openai.api_key = "your-api-key-here"

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"},
    {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
    {"role": "user", "content": "Where was it played?"}
]

response = openai.ChatCompletion.create(
  model="gpt-3.5-turbo",
  messages=messages
)

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

3. Fine-tuning a model with custom data:

import openai

openai.api_key = "your-api-key-here"

# Prepare your training data file
training_file = openai.File.create(
  file=open("path/to/fine-tune-data.jsonl", "rb"),
  purpose='fine-tune'
)

# Create a fine-tuning job
fine_tune_job = openai.FineTune.create(
  training_file=training_file.id,
  model="davinci"
)

print(f"Fine-tuning job created with ID: {fine_tune_job.id}")

Getting Started

To get started with the OpenAI Cookbook:

1. Clone the repository:

   git clone https://github.com/openai/openai-cookbook.git
   

2. Install the OpenAI Python library:

   pip install openai
   

3. Set up your API key as an environment variable:

   export OPENAI_API_KEY='your-api-key-here'
   

4. Explore the examples in the repository and adapt them to your needs.