I'm learning about RAG (Retrival Augmented Generation) and I am building a chatbot that can do Q&A over some documentation. I know a lot of people are working on it and wanted to know to if there were any particular recommendations for handling API documentation in this scenario (for example, what would be the best way to use Swagger API documentation with the chatbot?)
Is the recommendation to just treat it like any other text data source? Or are there are techniques for using RAG with structured data?
Try it out: https://github.com/truefoundry/cognita Read the technical blog here: https://www.truefoundry.com/blog/cognita-building-an-open-so...