The only Vector tooling you'll need. Star the repo and look out for an email to try out a brand new Vector Data Exploration demo! Use the universal VDF format for vector datasets to easily export and import data from all vector databases, and re-embed it using any model
This pull request introduces support for Turbopuffer, a new database integration, into our project. It includes updates to dependencies, the addition of Turbopuffer as a recognized database in our naming conventions, and the implementation of export and import functionalities specific to Turbopuffer's data handling.
Summary
Added turbopuffer[fast] to requirements.txt to include the necessary library for Turbopuffer operations.
Updated src/vdf_io/names.py to include TURBOPUFFER in the DBNames class, acknowledging it as a supported database.
Created src/vdf_io/turbopuffer.py which contains the logic for exporting to and importing from Turbopuffer databases. This includes:
Argument parsing for Turbopuffer-specific parameters.
Export functionality that iterates through indexes and yields documents.
Import functionality that batches documents for insertion into Turbopuffer.
Enhanced src/vdf_io/util.py with a method create_turbopuffer_index_class to dynamically create Python classes based on Turbopuffer index schemas, and updated the standardize_metric function to support Turbopuffer's distance metrics.
Fixes #81.
🎉 Latest improvements to Sweep:
New dashboard launched for real-time tracking of Sweep issues, covering all stages from search to coding.
Integration of OpenAI's latest Assistant API for more efficient and reliable code planning and editing, improving speed by 3x.
PR Feedback: 👎
Description
This pull request introduces support for Turbopuffer, a new database integration, into our project. It includes updates to dependencies, the addition of Turbopuffer as a recognized database in our naming conventions, and the implementation of export and import functionalities specific to Turbopuffer's data handling.
Summary
turbopuffer[fast]
torequirements.txt
to include the necessary library for Turbopuffer operations.src/vdf_io/names.py
to includeTURBOPUFFER
in theDBNames
class, acknowledging it as a supported database.src/vdf_io/turbopuffer.py
which contains the logic for exporting to and importing from Turbopuffer databases. This includes:src/vdf_io/util.py
with a methodcreate_turbopuffer_index_class
to dynamically create Python classes based on Turbopuffer index schemas, and updated thestandardize_metric
function to support Turbopuffer's distance metrics.Fixes #81.
🎉 Latest improvements to Sweep:
💡 To get Sweep to edit this pull request, you can:
This is an automated message generated by Sweep AI.