zilliztech / zilliztech/VectorDBBench
How to reproduce filter perfermance ?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 438
- Avg merge
- 1d 4h
- Merged PRs (30d)
- 1
Description
https://github.com/zilliztech/VectorDBBench/issues
I have 3 questions, please help confirm：
- Which dataset is used, cohere 768 1M/10M?
- Has an inverted index been constructed for the fields' id 'and' label '?
- What does the filtering ratio in the legend mean? For example, 98%, do those who meet the filtering criteria account for 98% of the total, or 2%?
Contributor guide
No contributing guide indexed for this repository
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 with the VectorDBBench benchmark repository linked in the issue and inspect its benchmark configuration or documentation. Confirm the dataset, indexes, and filtering-ratio meaning shown in the screenshot; the work is done when all three questions have documented answers.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- databases, performance
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100