Using OpenAI's ChatGPT API to Build a Conversational AI Chatbot | Python | Code



In this tutorial, you’ll learn how to use the newly released ChatGPT API from OpenAI to build your own conversational AI chatbot. With the power of GPT-3 technology, you can create a chatbot that can understand and respond to natural language inputs in real time.

Code: https://blog.futuresmart.ai/using-openais-chatgpt-api-to-build-a-conversational-ai-chatbot

I am a Freelance Data Scientist working on Natural Language Processing (NLP) and building end-to-end NLP applications.

I have over 7 years of experience in the industry, including as a Lead Data Scientist at Oracle, where I worked on NLP and MLOps.

I Share Practical hands-on tutorials on NLP and Bite-sized information and knowledge related to Artificial Intelligence.

LinkedIn: https://www.linkedin.com/in/pradipnichite/

#chatgptapi #chatgpt #gpt3 #openai

24 comments
  1. Hi Pradip, I am a Nodejs developer and I want to cluster text data using embedding but I don't know How to work with the [' ',….' '] vector output , can you suggest me any resources to learn and implement those using Nodejs ?

  2. I am doing sementic search using sentence transformers but not able to deploy that in AWS…as the sentence_transformers is not getting installed….on the half way installation is getting killed

  3. This is exactly what I wanted to build. Want to make a classy 19th century scientists bot for my desktop.

    But I tbink appending and sending the messages each time will eat into tokens. Couldnt it be better to set a cap on the messages? Say only append it up to 5 then have it roll over and erase the oldest in the list?

    Im new btw this may not make any sense.

  4. Pradip, If we have to keep updating the message list with the history, will this not limit the token size for an expected output? as the max tokensize is limited to input+output. is this correct?

  5. can you please answer this as while using chatgpt if i ask chatgpt that act like a chatbot in this domain with these limitations. Then how can we alter this code. Is it possible without finetuning.

  6. Thanks for the tutorial, very insightful and helpful. Just wondering , since the max token is 4096, so that means after multiple conversation (user input + AI reponse), there is a chance that the history will over max token length ?

    If so, is there any solution ?

Comments are closed.