:Info: Check Github <https://github.com/AitoDotAI/aito-python-tools>_ for the latest source code and documentation <https://aito-python-sdk.readthedocs.io/en/latest/>__ for more information.
:Maintainer: Aito [email protected]
|PyPI| |PyPI version|
About
Predictions over your own data with $p and $why, no model training; says when Aito does not fit.
API key
AITO_URL, AITO_API_KEY, AITO_MCP_ALLOW_WRITES
ตรวจสอบล่าสุด
2026-11-16
ดาว
—
เครื่องมือ
—
อัปไทม์
—
The Aito Python SDK is an open-source library that helps you to integrate your Python application
to Aito <https://aito.ai/>_ quicker and more efficiently.
The SDK also includes the Aito Command Line Interface (CLI) <https://aito-python-sdk.readthedocs.io/en/latest/cli.html>_ that enables you to interact with Aito
using commands in your command-line shell, e.g: infer a table schema from a file or upload a file to Aito.
API versions
Each Aito API version has its own package, whose meaning never changes:
.. code-block:: python
from aito.v2 import Client # the v2 API (`from aito.v1 import Client` for v1)
# the public read-only sandbox; use your own instance URL and key in production
client = Client('https://shared.aito.ai/db/aito-demo',
'yg4rTlXkqDzm4y8gPeY75HCKaNwfbTQ2si64ONTi', env='v2')
prediction = client.predict(
from_table='invoices', where={'Description': 'cloud services'}, predict='GLCode')
print(prediction.first.value, prediction.first.probability) # E002 0.83...
aito.Client is the default version, and moves only on a major release of this package:
since aitoai 1.0 it is the v2 client (0.x: v1). Quickstarts can use it; production code
should import the version it means, aito.v1 or aito.v2, so an upgrade cannot change
the API underneath it. To stay on v1: from aito.v1 import Client, or pin aitoai<1.
The pre-0.7 paths (aito.client, aito.client.v2, aito.api) were removed in 1.0;
importing one raises an ImportError naming its replacement. The command-line tool still
talks to the v1 API in 1.x: v2 support arrives as an opt-in in a 1.x minor release, and the
CLI's default moves to v2 only in 2.0. The design is written up in
docs/versioned-namespaces.md.
pip install aitoai installs the API clients. The command-line tool, schema inference
and file conversion need the dataframe toolchain: pip install 'aitoai[cli]'.
Run Aito locally
With Docker installed, aito start runs a local Aito and stores its keys, so the client
needs no arguments:
.. code-block:: console
$ pip install aitoai
$ aito start # pulls a pinned image, listens on http://127.0.0.1:9005, prints the keys
$ python -c "import aito; print(aito.Client().get_schema())"
aito stop stops it (data and keys are kept), aito status checks it, aito keys
prints the keys again (--rotate replaces them), aito logs shows its log and
aito upgrade moves to the engine version this package pins. These work without the
[cli] extra. From Python, aito.Client() with no arguments uses AITO_URL and
AITO_API_KEY if set, else the local server's profile.
examples/v2_quickstart.py is a runnable end-to-end example that creates a collection,
loads it, predicts, explains, evaluates and drops it again.
Use Aito from an AI assistant (MCP)
pip install 'aitoai[mcp]' (Python 3.10+) adds aito-mcp, an MCP server for coding
agents and assistants. Its tools are predict, recommend, relate, match, search, query,
evaluate and schema/upload. Each tool's description says when Aito fits and when another
tool (a language model, a trained model, a search engine) is the better choice. Results
carry $p and a flattened $why. The server finds the instance the same way as
aito.Client(). It is read-only unless started with AITO_MCP_ALLOW_WRITES=1.
.. code-block:: console
$ claude mcp add aito -- aito-mcp # Claude Code; any MCP client runs `aito-mcp` over stdio
Setup for Claude Code and other assistants: Use Aito from Claude Code and other AI assistants <https://aito.ai/docs/articles/use-aito-from-claude-code-and-other-ai-assistants/>. When Aito
fits and when not: When to use Aito, and when not <https://aito.ai/docs/articles/when-to-use-aito-and-when-not/>.
claude-plugin/ is a Claude Code plugin with this server and a skill,
add-predictive-feature. The skill walks an agent through a fit check, a schema from
an existing table, a first prediction, a threshold chosen with _evaluate, and
act / assist / abstain wiring.
Support / Feedback
For issues with, questions about, or feedback, please join our support channels <https://aito.ai/join-slack/>__.
Installation
Aito Python SDK can be installed with pip <http://pypi.python.org/pypi/pip>_
.. code-block:: console
$ pip install aitoai
Check our installation guide <https://aito-python-sdk.readthedocs.io/en/latest/install.html>_ for more information
Documentation
You will need sphinx <https://www.sphinx-doc.org/en/master/>_ installed to generate the documentation.
Add unittest to the appropriate test suite (e.g: test case for Aito Schema: tests/sdk/test_aito_schema.py) or create a new test suite inside the tests folder
Add documentation:
Inline documentation if applicable
Update .rst file in docs/source folder (e.g: Add a new Client function to docs/source/sdk.rst)
Add inline doc test if applicable (e.g: inline doc test for Aito Client: tests/inline_docs/test_client_inline_docs.py)
.. note::
Remember to update the autodoc_mock_imports in conf.py file if there are additional requirements
Update the version in aito/init to e.g. '1.2.3rc1' and write release notes in docs/changelog.rst
Check CircleCI and issue a PR
Deploy to production (scripts/deploy) with the appropriate version after the PR is reviewed