Welcome to this session titled ‘Working With OpenAI APIs’.
GPT models (Generative Pre-Trained models) are powerful large language models (LLMs) developed by OpenAI to perform various tasks. Generative models can generate text based on the input prompts provided, and these models are increasingly becoming popular in the world of NLP, as they can be used to generate novel content that appears quite similar to human-generated content. These language models are increasingly being deployed for various NLP-related applications such as chat dialogue systems, language translation (also known as machine translation), text summarisation, question answering (Q&A) systems and text-to-speech (TTS) systems.
One must understand the features and limitations of various OpenAI models (and other LLMs, both open source and proprietary), particularly when building production-ready applications. This understanding will significantly help in making the most of these models. With a proper understanding of the capabilities and limitations of generative models, one can easily apply them to many practical scenarios.
In this session, you will be introduced to various language models developed by OpenAI as well as their main application programming interface (API) – the Chat Completions API. The concepts covered in this module will also be helpful when dealing with other similar language models.
Prerequisites
- Understand the basics of Generative AI models and their capabilities from the previous modules.
- Basic Python programming knowledge.
In the video below, Kshitij will provide an overview of the content covered in this session.
In this session
Here, we will provide you with a basic overview of working with OpenAI APIs. Based on the concepts covered in this session, you will gain an understanding of the capabilities of the APIs offered by OpenAI and learn how to use them to perform various natural language processing (NLP) tasks.
You can access and download the Google Colab notebooks used in this session from this drive link.
We highly recommend that you use the notebooks to code along with the instructor in the video instead of using them just as a reference.
Guidelines for in-module questions
The in-video and in-content questions for this module are not graded.
Note that graded questions are given in a separate segment labelled ‘Graded Questions’ at the end of each session. The graded questions will adhere to the following guidelines:
First Attempt Marks | Second Attempt Marks | |
| Questions with 2 Attempts | 10 | 5 |
| Questions with 1 Attempt | 10 | 0 |
People you will hear from in this module
Subject Matter Expert
Kshitji jain
Kshitij is an ex-AVP at upGrad who led the learning experience and development of Data Science, Machine Learning, and Artificial Intelligence programs.
Sandeep Kumar H
Sandeep is an instructor at upGrad and is a data science and GenAI practitioner who has worked on multiple courses in collaboration with upGrad.