RAGArch is a Streamlit-based application that empowers users to experiment with various components and parameters of Retrieval-Augmented Generation (RAG) pipelines. Utilizing the power of Llamaindex, RAGArch facilitates the testing of different configurations to see how they perform.
As mentioned in the blog comments, I'm suggesting adding the option to see the text chunks used by the LLM to generate its answers, probably as links a user could click to check if the answer is accurate. This would be a very useful feature to make sure a response is accurate!
As mentioned in the blog comments, I'm suggesting adding the option to see the text chunks used by the LLM to generate its answers, probably as links a user could click to check if the answer is accurate. This would be a very useful feature to make sure a response is accurate!