The Retrieval-Augmented Generation (RAG) Pipeline combines retrieval-based and generative AI models to provide accurate and context-aware answers to your questions.
It retrieves relevant documents from a dataset (e.g., COVIDQA, TechQA, FinQA) and uses a generative model to synthesize a response.
Metrics are computed to evaluate the quality of the response and the retrieval process.
Generation Model
Select the generative model for response generation.
Validation Model
Select the model for validating the response quality.
Ask a question and get a response with metrics calculated from the RAG pipeline.
Try these examples:
Choose a question from the dropdown to populate the query box.