NVIDIA / NVIDIA/cuvs

[BUG] cuvs_bench export fails if index was not performed

Open Beginner friendly
#2,025 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

Describe the bug
When running the benchmarks with search but not build, and then exporting them, the following error is thrown:

Error processing build file /raid/kyedwards/benchmarks/main/datasets/deep-image-96-inner/result/build/cuvs_ivf_flat,base.json: 'name'. Skipping...
Traceback (most recent call last):
  File "/raid/kyedwards/miniforge3/envs/cuvs_benchmarks_main/lib/python3.14/site-packages/cuvs_bench/run/data_export.py", line 157, in convert_json_to_csv_build
    write_csv(file, algo_name, df, skip_cols=skip_build_cols)
    ~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/raid/kyedwards/miniforge3/envs/cuvs_benchmarks_main/lib/python3.14/site-packages/cuvs_bench/run/data_export.py", line 123, in write_csv
    df["name"] = df["name"].str.split("/").str[0]
                 ~~^^^^^^^^
  File "/raid/kyedwards/miniforge3/envs/cuvs_benchmarks_main/lib/python3.14/site-packages/pandas/core/frame.py", line 4378, in __getitem__
    indexer = self.columns.get_loc(key)
  File "/raid/kyedwards/miniforge3/envs/cuvs_benchmarks_main/lib/python3.14/site-packages/pandas/core/indexes/range.py", line 525, in get_loc
    raise KeyError(key)
KeyError: 'name'

Adding the --search flag when exporting does not help.

Steps/Code to reproduce bug

  1. Run the benchmarks with search but not build.
  2. Follow the recommended instructions to export the results.

Expected behavior
The search results should be exported gracefully without the build results.

Environment details (please complete the following information):

  • Environment location: [Bare-metal, Docker, Cloud(specify cloud provider)]
  • Method of RAFT install: [conda, Docker, or from source]
    • If method of install is [Docker], provide docker pull & docker run commands used

Additional context
Add any other context about the problem here.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start in cuvs_bench/run/data_export.py, especially convert_json_to_csv_build and write_csv, where the traceback shows the missing name column is accessed. Reproduce an export from search-only benchmark results and inspect how build files are discovered or skipped. Done means search results export successfully without build results; run the repository's relevant export or benchmark tests if available.

Written by the indexing model from the issue text.

Assessment

Tech stack
pandas, python
Domain
search, tooling
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Quiet
Clarity
Clearly specified
Newbie friendliness
68/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.