llmware-ai/llmware

Adding support for DuckDB

Open

#924 opened on Jul 6, 2024

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (2,912 forks)auto 404
good first issue

Repository metrics

Stars
 (14,817 stars)
PR merge metrics
 (PR metrics pending)

Description

DuckDB recently added support for vectors to enable similarity search and can be used for RAG.

It seems to me that it would be a very good fit for llmware as a low ceremony way to access data efficiently) even on a laptop .

Best Regards

Contributor guide

Research direction
Investigate DuckDB's vector similarity search functionality and integrate it into the llmware backend as a new database option, focusing on reading DuckDB's documentation and examples for vector operations and adapting them to the existing RAG pipeline structure.
Tech stack
python
Domain
backendaidatabase
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70