Skip to main content

SQLite AI Python package

This package provides the sqlite-ai extension prebuilt binaries for multiple platforms and architectures.

SQLite-AI

SQLite-AI is an extension for SQLite that brings artificial intelligence capabilities directly into the database. It enables developers to run, fine-tune, and serve AI models from within SQLite using simple SQL queries — ideal for on-device and edge applications where low-latency and offline inference are critical. The extension is actively developed by SQLite AI, some API and features are still evolving.

More details on the official repository sqliteai/sqlite-ai.

Documentation

For detailed information on all available functions, their parameters, and examples, refer to the comprehensive API Reference.

Supported Platforms and Architectures

Platform Arch Subpackage name Binary name
Linux (CPU) x86_64/arm64 sqliteai.binaries.cpu ai.so
Linux (GPU) x86_64/arm64 sqliteai.binaries.gpu ai.so
Windows (CPU) x86_64 sqliteai.binaries.cpu ai.dll
Windows (GPU) x86_64 sqliteai.binaries.gpu ai.dll
macOS (CPU) x86_64/arm64 sqliteai.binaries.cpu ai.dylib

Usage

Note: Some SQLite installations on certain operating systems may have extension loading disabled by default.
If you encounter issues loading the extension, refer to the sqlite-extensions-guide for platform-specific instructions on enabling and using SQLite extensions.

import importlib.resources
import sqlite3

# Connect to your SQLite database
conn = sqlite3.connect("example.db")

# Load the sqlite-ai extension
# pip will install the correct binary package for your platform and architecture
# Choose between CPU or GPU variant
ext_path = importlib.resources.files("sqliteai.binaries.cpu") / "ai"

conn.enable_load_extension(True)
conn.load_extension(str(ext_path))
conn.enable_load_extension(False)


# Now you can use sqlite-ai features in your SQL queries
print(conn.execute("SELECT ai_version();").fetchone())

Metadata

Release files for sqlite-ai 1.0.10

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

Built distributions (wheels)

Table of built distributions (wheels) for sqlite-ai 1.0.10
File Actions
sqlite_ai-1.0.10-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for sqlite_ai-1.0.10-py3-none-win_amd64.whl
sqlite_ai-1.0.10-py3-none-manylinux2014_x86_64.whl Python 3 none Linux glibc 2.17+ x86-64 Details for sqlite_ai-1.0.10-py3-none-manylinux2014_x86_64.whl
sqlite_ai-1.0.10-py3-none-manylinux2014_aarch64.whl Python 3 none Linux glibc 2.17+ ARM64 Details for sqlite_ai-1.0.10-py3-none-manylinux2014_aarch64.whl
sqlite_ai-1.0.10-py3-none-macosx_11_0_arm64.whl Python 3 none macOS 11.0+ ARM64 Details for sqlite_ai-1.0.10-py3-none-macosx_11_0_arm64.whl
sqlite_ai-1.0.10-py3-none-macosx_10_9_x86_64.whl Python 3 none macOS 10.9+ x86-64 Details for sqlite_ai-1.0.10-py3-none-macosx_10_9_x86_64.whl

Total release size: 70.6 MB

Release files / sqlite_ai-1.0.10-py3-none-win_amd64.whl

Download URL sqlite_ai-1.0.10-py3-none-win_amd64.whl
Size 21.6 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
8291dbe1e44a2e38904850bb79c7a954ca780b1bddac56c634d9a7b3e50dabb8
BLAKE2b-256 checksum
How to use checksums
7d1abe008b06f7786a62018f35a92b347287887eb678545725c4cee59c04a07c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 2, 2026.

Transparency log

Release files / sqlite_ai-1.0.10-py3-none-manylinux2014_x86_64.whl

Download URL sqlite_ai-1.0.10-py3-none-manylinux2014_x86_64.whl
Size 22.1 MB
Tags Linux glibc 2.17+ x86-64 Python 3
SHA-256 checksum
How to use checksums
edba846db4c433dfc9b437270bf7a36a8431c50c49610ce5769405cc869b9fed
BLAKE2b-256 checksum
How to use checksums
8dddf197c1ce6aef8ed49acda2eda7387496b4ae980cba7e46c5f0e1780b6764
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 2, 2026.

Transparency log

Release files / sqlite_ai-1.0.10-py3-none-manylinux2014_aarch64.whl

Download URL sqlite_ai-1.0.10-py3-none-manylinux2014_aarch64.whl
Size 17.9 MB
Tags Linux glibc 2.17+ ARM64 Python 3
SHA-256 checksum
How to use checksums
c5a8ea7b6f564d93c31af3526972fa21be250830ff688c03f6c8ddc130468136
BLAKE2b-256 checksum
How to use checksums
d8d6e6f14b4b5b3d7decb759292f0b117c228bc55d63c74dd96fe3d6c07a3ef8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 2, 2026.

Transparency log

Release files / sqlite_ai-1.0.10-py3-none-macosx_11_0_arm64.whl

Download URL sqlite_ai-1.0.10-py3-none-macosx_11_0_arm64.whl
Size 4.5 MB
Tags Python 3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
10731a0d94075cdf5c6b4509d1a01893a80e3e252e34c78b24aa7925cbaefb07
BLAKE2b-256 checksum
How to use checksums
9a211391f7ae10e5547e2651f5c40f9e8d9ab0ed15e9bc8532d23ee5fee0db88
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 2, 2026.

Transparency log

Release files / sqlite_ai-1.0.10-py3-none-macosx_10_9_x86_64.whl

Download URL sqlite_ai-1.0.10-py3-none-macosx_10_9_x86_64.whl
Size 4.5 MB
Tags Python 3 macOS 10.9+ x86-64
SHA-256 checksum
How to use checksums
8f58bbd37a6ca881c47b89187c98ebf0d67f3454c010ed983f7e9787b4b4b3ad
BLAKE2b-256 checksum
How to use checksums
f9187b3e04f03eb22fe678de6f53379298e43577a1d3fe8ea6e7ac9e7f792723
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 2, 2026.

Transparency log

Security for sqlite-ai 1.0.10

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.

Full provenance

All 5 files in this release have been uploaded with provenance metadata.

Select from 5 files

Attestation for sqlite_ai-1.0.10-py3-none-win_amd64.whl

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 Nov 2, 2026.

Transparency log

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