NVIDIA / NVIDIA/NeMo-Retriever
[FEA]: Add the capability to split and recombine job requests
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3k
- Forks
- 349
- Avg merge
- 1d 23h
- Merged PRs (30d)
- 116
Description
Is this a new feature, an improvement, or a change to existing functionality?
Improvement
How would you describe the priority of this feature request
Significant improvement
Please provide a clear description of problem this feature solves
This would be to help support pre-splitting for latency sensitive applications, prioritization of single document throughput, and parallelization across document primitives.
Describe the feature, and optionally a solution or implementation and any alternatives
This would likely result in two new stage abstractions. 1) To split and route documents at a specific stage. 2) Collect and recombine at a downstream stage.
Additional context
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 tracing the existing job-request flow and stage abstractions to understand where splitting and routing could occur. Define the two proposed abstractions—a stage that splits and routes documents, and a downstream stage that collects and recombines them—and verify they support pre-splitting, prioritization, and parallelization.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100