[FEA] Indexes to support sparse inputs
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
Larger tracking issue for all of the ANN indexes to support sparse inputs.
It's becoming more and more common that GNNs are used to create sparse embeddings, since extremely high dimensional data can be represented with many fewer elements. These sparse embeddings are then used to build and query transitional Ann indexes.
cc @jeaton32 for awareness
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
This is a larger tracking issue covering ANN indexes and sparse embeddings, but it names no files, tests, or entry points. Start by surveying the ANN index implementations and their existing input paths; the issue does not define the individual scope or acceptance criteria for considering the work done.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning, search
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100