LintDB
LintDB copied to clipboard
DeployQL
Vector Database with support for late interaction and token level embeddings.
`conda install lintdb -c deployql -c conda-forge` Collecting package metadata (current_repodata.json): failed # >>>>>>>>>>>>>>>>>>>>>> ERROR REPORT
It would be helpful to have a consistent indexing method within this package. Currently, the benchmarking suite has a multithreaded indexer, but it's specific to LoTTE. We should abstract it...
Paper: https://arxiv.org/html/2404.13950v1 As an MLE, I want to use SPLATE to get the same quality of results with less latency. This will involve several tasks: 1. Create a new Index...
As a user, I want to upload binary embeddings from cohere (et al) directly into the database. This helps support the latest and greatest embedding formats, run faster, and use...
Google released XTR that uses late interaction. https://github.com/google-deepmind/xtr We should be able to support this and enable users to run this themselves.
In order to enable filtering of documents, we should be able to formulate query trees. ## What is a Query Tree A query tree should be an executable graph on...
As a user, I want to understand why certain documents are returned so that we can formulate the LLM context better. One of the benefits of late interaction is having...
As a user of LintDB, I want to be able to filter by metadata in a search so that I can more accurately retrieve my data. ### Acceptance Criteria 1....
My system is currently under pressure while training a new model. Benchmarking the search critical path, it's the coarse quantizer that takes the most time at a whopping 80%. ...
We use sgemm to run matmuls for every query. We can cut this in half by supporting float16, which MKL/OpenBLAS support. Requirements: - We need to be able to toggle...