Quick Start

Welcome to ragview.ai. In RagView, you can complete a RAG evaluation task quickly with just a few simple steps.

1. Upload Document Set: In Data Management, upload a set of documents to be retrieved during the RAG process. These documents will serve as the knowledge base for retrieval; different RAG solutions may use different chunking and retrieval methods on them.
2. Upload Test Set: In Data Management, upload the test data for evaluation. The test data includes the questions, the original text excerpts (from the document set) that the large model used for reference, and the reference standard answers. The test set should be prepared according to the provided sample file.
3. Launch Evaluation Task: In Evaluation Management, create a rag evaluation task, select the document set and test set, choose solutions, and pick the rag evaluation metrics to compute (e.g., answer accuracy, context precision/recall, latency).
4. View Evaluation Details: In Evaluation Management, after the task completes, click Details to view results. Based on the metrics you care about, select the suitable RAG solution and download the code for that pipeline.

RagView.ai