-
Notifications
You must be signed in to change notification settings - Fork 152
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Feature Request]: Support sparse vector #1174
Labels
feature request
New feature or request
Comments
JinHai-CN
pushed a commit
that referenced
this issue
May 28, 2024
### What problem does this PR solve? 1. Create table with sparse vector column 2. Insert sparse vector 3. Import sparse vector with csv format. Issue link:#1174 ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Test cases
4 tasks
JinHai-CN
pushed a commit
that referenced
this issue
May 29, 2024
### What problem does this PR solve? 1. Fix bug: cross chunk sparse vector 2. Add: support import from jsonl & csr file 3. Add: integer data type to sparse vector type. 4. Refactor: embedding value type. TODO: 1. add bit data type support to sparse vector type. 2. Sparse vector index impl and test. Issue link:#1174 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring - [x] Test cases
2 tasks
JinHai-CN
pushed a commit
that referenced
this issue
May 29, 2024
### What problem does this PR solve? 1. Add: bit data type to sparse vector. 2. Add: default value to sparse vector. 3. Add: empty sparse vector 4. Test: more test case. Issue link:#1174 ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Test cases
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is there an existing issue for the same feature request?
Describe the feature you'd like
At present, our system uses a dense representation for vector storage. I would like to propose a feature request for the implementation of a sparse vector index within infinity. Sparse vector indexing is crucial for efficiently handling high-dimensional data, which is common in our use cases involving natural language processing and machine learning.
The text was updated successfully, but these errors were encountered: