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)
| File | Actions Reset | |||
|---|---|---|---|---|
| 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 logRelease 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 logRelease 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 logRelease 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 logRelease 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 logSecurity 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.
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 logA 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.