NVIDIA / NVIDIA/NeMo-Retriever
[FEA]: Set the recreate default to false
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
Would be nice
Please provide a clear description of problem this feature solves
Recreate are currently set to true in default. This leads to issues if user ingest documents one after another.
As we are experimenting the nv-ingest, usually will ingest file by file, or batch by batch. It will be nice to have this default as false.
I believe it is also beneficial for other developers. Drop the collection in default is really disappointed for user after they spend so much time waiting for ingestion finished and do the next ingestion.
Describe the feature, and optionally a solution or implementation and any alternatives
will attach a PR for this.
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
The issue identifies nv-ingest and the recreate default but names no files, tests, or entry points. Start by locating where this default is defined and find any existing ingestion-configuration tests. Done means the default is false while users can still explicitly request recreation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- data
- Issue type
- Feature
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100