OpenAI API

The OpenAI API can be applied to virtually any task that involves understanding or generating natural language, code, or images. OpenAI API provides us models with different levels of power and we can also fine-tune our own custom model

• Prompts:- Designing your prompt is essentially how you “program” the model, usually by providing some instructions or a few examples.

• Tokens:- Models understand and process text by breaking it down into tokens. For example, the word “hamburger” gets broken up into the tokens “ham”, “bur” and “ger”.

• Models:- API is powered by a set of models with different capabilities. GPT-4 is the latest model.GPT-3.5-Turbo is the model that powers ChatGPT and is optimized for conversational formats.

Steps to integrate OpenAI API (Python)

• Create an account on the OpenAI website and obtain an API key.

• Install the OpenAI SDK using pip, the Python package manager.

• Set up authentication by providing your API key. This can be done by setting the OPENAI_API_KEY environment variable or passing your key directly to the SDK.

• Decide which OpenAI API you want to use based on your project’s needs.

• Create a “Completion” object and pass in your prompt to use the API.

• Once you receive a response from the API, process it according to your needs.

Functionality provided by OpenAI

API Reference

To install the official Python bindings, run the following command:

pip install openai

All API requests should include your API key in an Authorization HTTP header as follows:

Authorization: Bearer OPENAI_API_KEY

For users who belong to multiple organizations, you can pass a header to specify which organization is used for an API request

Example with the openai Python package:

import os
import openai
openai.organization = "YOUR_ORG_ID" // Setting Organization
openai.api_key = os.getenv("OPENAI_API_KEY") // Setting API Key
openai.Model.list() // Getting available Models in JSON Format

API Reference

Retrieve model:

import os
import openai
openai.api_key = os.getenv("OPENAI_API_KEY")
openai.Model.retrieve("text-davinci-003")

Retrieves a model instance, providing basic information about the model such as the owner and permissioning.