Select AI for Python

Select AI for Python enables you to ask questions of your database data using natural language (text-to-SQL), get generative AI responses using your trusted content (retrieval augmented generation), generate synthetic data using large language models, and other features – all from Python. With the general availability of Select AI Python, Python developers have access to the functionality of Select AI on Oracle Autonomous Database.

Select AI for Python enables you to leverage the broader Python ecosystem in combination with generative AI and database functionality - bridging the gap between the DBMS_CLOUD_AI PL/SQL package and Python's rich ecosystem. It provides intuitive objects and methods for AI model interaction.

Installation

Install the Python package:

python3 -m pip install select_ai

Install the optional command line interface:

python3 -m pip install 'select_ai[cli]'

Documentation

See Select AI for Python documentation

Samples

Examples can be found in the /samples directory

Command Line Interface

The optional select-ai command provides an interactive chat REPL for Select AI profiles:

select-ai chat --profile OCI_AI_PROFILE

Select AI CLI demo

Basic Example

import select_ai

user = "<your_select_ai_user>"
password = "<your_select_ai_password>"
dsn = "<your_select_ai_db_connect_string>"

select_ai.connect(user=user, password=password, dsn=dsn)
profile = select_ai.Profile(profile_name="oci_ai_profile")
# run_sql returns a pandas dataframe
df = profile.run_sql(prompt="How many promotions?")
print(df.columns)
print(df)

Async Example

import asyncio

import select_ai

user = "<your_select_ai_user>"
password = "<your_select_ai_password>"
dsn = "<your_select_ai_db_connect_string>"

# This example shows how to asynchronously run sql
async def main():
    await select_ai.async_connect(user=user, password=password, dsn=dsn)
    async_profile = await select_ai.AsyncProfile(
        profile_name="async_oci_ai_profile",
    )
    # run_sql returns a pandas df
    df = await async_profile.run_sql("How many promotions?")
    print(df)

asyncio.run(main())

Help

Questions can be asked in GitHub Discussions.

Problem reports can be raised in GitHub Issues.

Contributing

This project welcomes contributions from the community. Before submitting a pull request, please review our contribution guide

Security

Please consult the security guide for our responsible security vulnerability disclosure process

License

Released under the Universal Permissive License v1.0 as shown at https://oss.oracle.com/licenses/upl/.

Metadata

Release files for select-ai 1.4.1

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

Source distribution (sdist)

Source distribution for select-ai 1.4.1
File	Size	Uploaded
select_ai-1.4.1.tar.gz	171.3 kB	Jul 31, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for select-ai 1.4.1
File	Interpreter	ABI	Platform	Reset
select_ai-1.4.1-py3-none-any.whl 65.1 kB Jul 31, 2026	Python 3	none	any	Details

Total release size: 236.4 kB

Release files / select_ai-1.4.1.tar.gz

Download URL	select_ai-1.4.1.tar.gz
Size	171.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`b75cc6566d045f8ef22bb944624dc2f2080e921db971bb7118520f1e404a3d18`
BLAKE2b-256 checksum How to use checksums	`e7b5f2b9bf6b0cc190350f7cfc8efd41d2cc0714326a103930c22a2a6e5b10da`
Upload date	Jul 31, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.13`

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.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/oracle/python-select-ai
Publishing commit: github.com/oracle/python-select-ai/tree/e8ec2d005a00338d052b34c83364daaa85680788

Workflow

Publishing configuration: github.com/oracle/python-select-ai/blob/e8ec2d005a00338d052b34c83364daaa85680788/.github/workflows/release.yaml
Publishing logs: github.com/oracle/python-select-ai/actions/runs/30598223606/attempts/2

Artifact

Subject: select_ai-1.4.1.tar.gz
SHA-256 checksum: b75cc6566d045f8ef22bb944624dc2f2080e921db971bb7118520f1e404a3d18 Verifying attestations

Release files / select_ai-1.4.1-py3-none-any.whl

Download URL	select_ai-1.4.1-py3-none-any.whl
Size	65.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`0400330e62e10549728a5fafbab22513e09e4ab89073e105eae5c9b8da9e54b9`
BLAKE2b-256 checksum How to use checksums	`404cb0c74cd37d62493487ea367e86b9557880e41b00246b4ab7d8b0cb15c209`
Upload date	Jul 31, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.13`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/oracle/python-select-ai
Publishing commit: github.com/oracle/python-select-ai/tree/e8ec2d005a00338d052b34c83364daaa85680788

Workflow

Publishing configuration: github.com/oracle/python-select-ai/blob/e8ec2d005a00338d052b34c83364daaa85680788/.github/workflows/release.yaml
Publishing logs: github.com/oracle/python-select-ai/actions/runs/30598223606/attempts/2

Artifact

Subject: select_ai-1.4.1-py3-none-any.whl
SHA-256 checksum: 0400330e62e10549728a5fafbab22513e09e4ab89073e105eae5c9b8da9e54b9 Verifying attestations