infinity
infinity copied to clipboard
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text
### What problem does this PR solve? 1. Refactor: commit mem index commit process to a seperate file 2. Refactor: remove thread pool used by memindex committing. 3. Bug fix:...
### What problem does this PR solve? Issue link:#1490 ### Type of change - [x] Documentation Update
### What problem does this PR solve? Consider ROW_ID in KNN Sort the result by: 1. KNN distance first 2. ROW_ID (ascending order) ### Type of change - [x] Bug...
### What problem does this PR solve? Refactor: varchar storage ### Type of change - [x] Refactoring
### What problem does this PR solve? - Add uint8, float16, bfloat16 datatype support for http api knn - enable match tensor array for http api - fix http api...
### Is there an existing issue for the same feature request? - [X] I have checked the existing issues. ### Describe the feature you'd like Implement support for `abs` and...
### Describe what you'd like We need more examples to show how to use tensor data search, tensor data reranker and structured data filter. 1. Tensor data search. https://github.com/infiniflow/infinity/blob/main/example/tensor_search.py 2....
### Is there an existing issue for the same bug? - [X] I have checked the existing issues. ### Version or Commit ID v0.2.1 ### Other environment information ```Markdown centos...
### Is there an existing issue for the same feature request? - [X] I have checked the existing issues. ### Is your feature request related to a problem? _No response_...
[Question]: Why do I need to delete and rebuild the index every time you perform a full-text search?
### Is there an existing issue for the same bug? - [X] I have checked the existing issues. ### Version or Commit ID v0.3.0 ### Other environment information _No response_...