Abstract

OpenAI - the name of the latest breakthroughs in artificial intelligence (AI) research - has captured the imagination since its announcement at the end of 2015.[1] This non-profit research organization, unlike its for-profit rivals, has an ambitious vision: to ensure that Artificial General Intelligence (AGI), the highest form of AI development where machines can outperform humans in a variety of applications, works for humanity at large. This paper discusses the ability to turn design papers into a knowledge-base via Generative AI (Gen-AI). Using LLMs and a strong search engine like OpenSearch, lets explore how to create a robust chatbot that can answer questions and provide insight right from the design document. Lets walk through all the key components, starting with data preparation and indexing to model selection and integration. Lets understand how to mine valuable data from design files, preprocess them for optimal LLM performance, and provide a slick search solution with OpenSearch. Hopefully, will learn enough to create own intelligent chatbot that will help teams effectively access and make sense of important design information at the end of this article.

References

• Brown, T., et al. "Language Models are Few-Shot Learners." NeurIPS 2020.
• "GPT-3: Language Models are Few-Shot Learners" - https://openai.com/research/gpt-3
• Radford, A., et al. "Improving Language Understanding by Generative Pre-Training." OpenAI, 2018
• Jurafsky, D., and Martin, J. H. Speech and Language Processing. Pearson, 2021
• Vaswani, A., et al. "Attention is All You Need." NeurIPS 2017
• Language Models are Few-Shot Learners - https://arxiv.org/abs/2005.14165
• Official Documentation: OpenSearch Documentation, Amazon Web Services.
• Conversational AI: Building Next-Gen Chatbots - https://azure.microsoft.com/en-us/blog/conversational-ai-building-next-generation-chatbots/
• White, R. W. Interacting with Search Systems. Cambridge University Press, 2016
• Migrating from Elasticsearch to OpenSearch - https://opensearch.org/blog/migrating-from-elasticsearch/
• Kuang, J. "An Introduction to OpenSearch: What it is and How It Works." Elastic Blog, 2021
• OpenSearch Service Documentation - https://docs.aws.amazon.com/opensearch-service/latest/developerguide/what-is.html
• Gormley, C., and Tong, Z. Elasticsearch: The Definitive Guide. O'Reilly Media, 2015. (Also applies to OpenSearch)
• Setting Up OpenSearch for Search and Analytics - https://www.digitalocean.com/community/tutorials/how-to-install-and-configure-opensearch
• Kuang, J. "An Introduction to OpenSearch: What it is and How It Works." Elastic Blog, 2021
• Bocklisch, T., et al. "Rasa: Open Source Language Understanding and Dialogue Management." arXiv 2017.
• Huang, M., et al. "Challenges in Building Intelligent Open-domain Dialog Systems." arXiv 2020
• Python Machine Learning - https://realpython.com/tutorials/machine-learning/
• Lane, M., et al. "Building Chatbots with Python." Packt Publishing, 2018.
• Xu, A., et al. "A New Chatbot for Customer Service on Social Media." CHI 2017.
• Integrating Rasa with OpenAI – https://rasa.com/docs/rasa/openai/
• Géron, A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. O'Reilly Media, 2019.
• Raschka, S., and Mirjalili, V. Python Machine Learning. Packt Publishing, 2019.
• Understanding Dialogflow Essentials - https://cloud.google.com/dialogflow/docs
• Chatbot Development Using Python and NLP - https://towardsdatascience.com/building-a-chatbot-using-python-7d4eeb8e9e61
• Python Data Science Handbook" by Jake VanderPlas - https://github.com/jakevdp/PythonDataScienceHandbook
• Transformer Model Architecture - Google AI Blog
• Rasa: Open-Source Conversational AI - Rasa Documentation.
• McKinney, W. Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython. O'Reilly Media, 2017.
• "Building Chatbots with Python" by Sumit Raj
• Natural Language Processing with Python" by Steven Bird, Ewan Klein, and Edward Loper
• "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow" by Aurélien Géron
• "Designing Bots: Creating Conversational Experiences" by Amir Shevat
• Deep Learning for Natural Language Processing" by Palash Goyal, et al.
• Raschka, S., and Mirjalili, V. Python Machine Learning. Packt Publishing, 2019.
• Migrating from Elasticsearch to OpenSearch https://opensearch.org/blog/migrating-from-elasticsearch/
• Natural Language Processing with Python. https://www.nltk.org/book/
• Creating Chatbots with Python https://realpython.com/python-telegram-bot/
• Building a Chatbot Using OpenAI GPT-3 https://towardsdatascience.com/how-to-build-a-chatbot-with-openai-gpt-3-6e4c4ef4aa28
• "Learning Python" by Mark Lutz
• "Python Machine Learning" by Sebastian Raschka and Vahid Mirjalili
• "Programming Bots: Building Chatbots with Python" by Richard S. T. Man
• "Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots" by Michael McTear
• "Artificial Intelligence: A Guide to Intelligent Systems" by Michael Negnevitsky.
• "Hands-On Natural Language Processing with Python" by Rajesh Arumugam and Rajesh Kumar