rags

Why we included this project

RAGs lets you describe, in plain English, what you want to do with your documents, then builds the retrieval pipeline for you. It is a Streamlit app that turns your instructions into a working setup: you tell it the data source and task, review the parameters it picked (top-k, chunk size, embedding model, LLM, and whether to include summarization), and adjust anything before querying. Once configured, you chat with an agent that chooses between vector search and summarization to answer questions about your data. Since it comes from the LlamaIndex team, people already on that stack can dig into the internals and extend them, while the guided UI keeps the whole flow usable for those who would rather not touch the configuration at all.