Skip to main content

recern-vector (Python)

Python bindings for Recern Vector, a single-file, embedded, inspectable vector database.

Prototype (0.0.x): the file format and API will change between releases.

pip install recern-vector

Wheels cover CPython 3.11+ on Linux (x86_64, aarch64), macOS (Intel, Apple silicon) and Windows (x86_64).

import numpy as np
import recern_vector as rv

with rv.Database.open_or_create("docs.rvec") as db:          # saves on clean exit
    chunks = db.create_collection("chunks", dim=384, metric="cosine")
    chunks.upsert_many(ids, np.asarray(embeddings, dtype=np.float32), metadatas)

    hits = chunks.search(query, k=5, filter={"lang": "en", "year": {"$gte": 2020}})
    report = chunks.explain(query, k=5)          # strategy, visited nodes, elapsed_ms
    recall = chunks.estimate_recall(ef_values=[16, 64, 256])
    print(chunks.stats())

float32 NumPy arrays are read through the buffer protocol without per-element conversion; plain lists and other dtypes also work. upsert_many builds index links on all cores (threads= to change it) and is atomic: if any vector is invalid, nothing is written.

Benchmarks against faiss, LanceDB and sqlite-vec: recern.net/vector/benchmarks.

Development

uv venv && uv pip install maturin pytest numpy
source .venv/bin/activate
maturin develop --release
pytest

Metadata

Release files for recern-vector 0.0.1

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

Source distribution (sdist)

Source distribution for recern-vector 0.0.1
File Size Uploaded
recern_vector-0.0.1.tar.gz 53.0 kB Details

Built distributions (wheels)

Table of built distributions (wheels) for recern-vector 0.0.1
File
recern_vector-0.0.1-cp311-abi3-win_amd64.whl CPython 3.11 abi3 Windows x86-64 Details
recern_vector-0.0.1-cp311-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl CPython 3.11 abi3 Linux glibc 2.17+ x86-64 Details
recern_vector-0.0.1-cp311-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl CPython 3.11 abi3 Linux glibc 2.17+ ARM64 Details
recern_vector-0.0.1-cp311-abi3-macosx_11_0_arm64.whl CPython 3.11 abi3 macOS 11.0+ ARM64 Details
recern_vector-0.0.1-cp311-abi3-macosx_10_12_x86_64.whl CPython 3.11 abi3 macOS 10.12+ x86-64 Details

Total release size: 2.2 MB

Release files / recern_vector-0.0.1.tar.gz

Download URL recern_vector-0.0.1.tar.gz
Size 53.0 kB
Tags Source
SHA-256 checksum
How to use checksums
f9687edd07aca1226ef2beccd010bc09e11ea9e117cef35067376b354c654054
BLAKE2b-256 checksum
How to use checksums
dfb7defee589879156f9019648a39ec7b9e55008d571e5ce73c346be77566798
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 8, 2026.

Transparency log

Release files / recern_vector-0.0.1-cp311-abi3-win_amd64.whl

Download URL recern_vector-0.0.1-cp311-abi3-win_amd64.whl
Size 343.8 kB
Tags CPython 3.11 Windows x86-64 abi3
SHA-256 checksum
How to use checksums
13ad318ad7629ca966b08f1c9171f771152e39c31dc84f5ac3d074b9d12b1b6b
BLAKE2b-256 checksum
How to use checksums
b083baf79698542c0b4f757ae286bf5918d747a8afa14f63045d654b35d3e554
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 8, 2026.

Transparency log

Release files / recern_vector-0.0.1-cp311-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL recern_vector-0.0.1-cp311-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size 478.3 kB
Tags CPython 3.11 Linux glibc 2.17+ x86-64 abi3
SHA-256 checksum
How to use checksums
d883b7d5dc62cadfdf91091ba3cfb4210dd3923e9ca828be730ada5ac48190ea
BLAKE2b-256 checksum
How to use checksums
379d8a354f90e837649279acec95ee0bd12691e8d8c251c3439783de4383b2b4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 8, 2026.

Transparency log

Release files / recern_vector-0.0.1-cp311-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

Download URL recern_vector-0.0.1-cp311-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Size 459.7 kB
Tags CPython 3.11 Linux glibc 2.17+ ARM64 abi3
SHA-256 checksum
How to use checksums
ca7b7125774b203e732085da3e5c9ebff318544d4887c4bd09696bcfd0c3d421
BLAKE2b-256 checksum
How to use checksums
17dd36fe69678b5d51466b6d7c97cd2546fa3f5857e8364ebf7260bc84a60793
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 8, 2026.

Transparency log

Release files / recern_vector-0.0.1-cp311-abi3-macosx_11_0_arm64.whl

Download URL recern_vector-0.0.1-cp311-abi3-macosx_11_0_arm64.whl
Size 420.3 kB
Tags CPython 3.11 abi3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
0413586527c5b3419e3cd635aac5735207661c37f236850f465608bddd7f920b
BLAKE2b-256 checksum
How to use checksums
037a3869233d318a293f3186d003b40b0d78ad7d915e0f5577ae9749a3dc6483
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 8, 2026.

Transparency log

Release files / recern_vector-0.0.1-cp311-abi3-macosx_10_12_x86_64.whl

Download URL recern_vector-0.0.1-cp311-abi3-macosx_10_12_x86_64.whl
Size 438.7 kB
Tags CPython 3.11 abi3 macOS 10.12+ x86-64
SHA-256 checksum
How to use checksums
31e0cd109d3e65b9131cb0cb70e048433fff8c2e802966ca434e0930a8942ee5
BLAKE2b-256 checksum
How to use checksums
5df22532a31aa1060bd769242459c74ae449a78d02a0c5f8b17bffda314b19c4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 8, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.0.1 This release

6 release files

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