Skip to main content
UR-2.0 provides a convenient Case Study visualization mechanism that helps researchers quickly inspect and analyze whether a constructed Pipeline is functioning as expected. After executing the Pipeline, the system automatically generates a memory log file in the output folder.
Simply run the following command to launch the Case Study visualization web page: 
python ./script/case_study.py \
  --data output/memory_nq_rag_branch_20251014_152438.json \
  --host 127.0.0.1 \
  --port 8070 \
  --title "Case Study Viewer"
Please adjust the file path, port number, and other parameters as needed.
Once started, you can open the corresponding address in your browser to access the Case Study Viewer interface.
This interface presents the inputs and outputs of each stage of the Pipeline through intuitive visualizations, making it easier to review reasoning chains and intermediate states step by step. On this page, you can navigate between different cases to visually compare the relationships among the input question, retrieval results, and model outputs, allowing you to efficiently identify potential issues, optimize Pipeline design, and verify whether the overall reasoning process behaves as intended.