NVIDIA / NVIDIA/NeMo-Retriever
[BUG]: Traceid is not propogated correctly with pdf_split_page_count
Open
Nobody has claimed this yet.
bug
- Dominant language
- Python
- Stars
- 3k
- Forks
- 349
- Avg merge
- 1d 23h
- Merged PRs (30d)
- 116
Description
Version
26.1.2
Which installation method(s) does this occur on?
No response
Describe the bug.
If we use pdf_split_page_count = 1 (any number less then the total pages in the pdf), trace IDs are not getting propagated to the subjobs.
Attaching screen shot of 1 full file sent with no pdf_split_page_count vs send with *pdf_split_page_count = 1
Minimum reproducible example
Relevant log output
Other/Misc.
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the issue with pdf_split_page_count set to 1 and compare trace IDs between an unsplit PDF and its subjobs. Trace the PDF splitting and subjob creation path to find where propagation diverges; done means each subjob retains the expected trace ID.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend, distributed-systems
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100