Skip to main content

lumio-lancedb

Optional LanceDB retrieval adapter for the Lumio Knowledge Base foundation. It adds indexed BM25, vector/semantic and hybrid retrieval to lumio-wiki, preserving its evidence, citation and retrieval-result contracts.

Install

Requires Python 3.14 or newer.

pip install lumio-lancedb

The adapter depends on lumio-wiki, LanceDB, PyArrow and msgspec[yaml]. The 0.5.1 adapter requires lumio-wiki>=0.5.1,<0.6.0. Installing the adapter alone does not build an index; select and configure it explicitly through the supported SDK or CLI composition.

Optional capabilities:

pip install 'lumio-lancedb[embeddings]'  # Local sentence-transformers / Torch
pip install 'lumio-lancedb[s3]'          # Remote S3-compatible index support

Torch is excluded from the base adapter. Semantic retrieval additionally requires a configured embedding implementation and a built semantic index; BM25 retrieval does not require a model. The index is derived data: canonical Markdown pages remain the Knowledge Base's source of truth.

Start with the Knowledge Base

Use the local/Git quickstart to create and publish a Knowledge Base, then follow the retrieval and CLI guide to add indexed retrieval. The SDK package guide describes the shared API, citations and explicit publication admission.

lumio-wiki works independently of this adapter and never imports it. Ariadne is also optional; see the joint tutorial for separately admitted knowledge and governed calculations.

Metadata

Release files for lumio-lancedb 0.5.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for lumio-lancedb 0.5.1
File Interpreter ABI Platform
lumio_lancedb-0.5.1-py3-none-any.whl Python 3 none any Details

Release files / lumio_lancedb-0.5.1-py3-none-any.whl

Download URL lumio_lancedb-0.5.1-py3-none-any.whl
Size 28.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f2e3eb831bdaebff756660054034c1391ec46bb9d1b2c00ac9aedb6d7bda2859
BLAKE2b-256 checksum
How to use checksums
81a8164dafa5fd1c72e7272f41832942a8165acbe84fc27824b25d575e7b6805
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Security for lumio-lancedb 0.5.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page