How to build a Q&A AI in Python (Open-domain Question-Answering)

🎁 Free NLP for Semantic Search Course: https://www.pinecone.io/learn/nlp

How can we design these natural, human-like Q&A interfaces? The answer is open-domain question-answering (ODQA). ODQA allows us to use natural language to query a database.

That means that, given a dataset like a set of internal company documents, online documentation, or as is the case with Google, everything on the world's internet, we can retrieve relevant information in a natural, more human way.

🌲 Pinecone article: https://www.pinecone.io/learn/retriever-models/

🔗 Nils YT Talk: https://youtu.be/XNJThigyvos?t=118 🔗 MNR Loss Article: 🔗 Free Pinecone API Key: https://app.pinecone.io/

🤖 70% Discount on the NLP With Transformers in Python course: https://bit.ly/3DFvvY5

🎉 Subscribe for Article and Video Updates! https://jamescalam.medium.com/subscribe https://medium.com/@jamescalam/membership

👾 Discord: https://discord.gg/c5QtDB9RAP

00:00 Why QA 04:05 Open Domain QA 08:24 Do we need to fine-tune? 11:44 How Retriever Training Works 12:59 SQuAD Training Data 16:29 Retriever Fine-tuning 19:32 IR Evaluation 25:58 Vector Database Setup 33:42 Querying 37:41 Final Notes ... https://www.youtube.com/watch?v=w1dMEWm7jBc