# 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
Run
```bash
python3 -m pip install select_ai
```
## Documentation
See [Select AI for Python documentation][documentation]
## Samples
Examples can be found in the [/samples][samples] directory
### Basic Example
```python
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
```python
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][ghdiscussions].
Problem reports can be raised in [GitHub Issues][ghissues].
## Contributing
This project welcomes contributions from the community. Before submitting a pull request, please [review our contribution guide][contributing]
## Security
Please consult the [security guide][security] for our responsible security vulnerability disclosure process
## License
Copyright (c) 2025 Oracle and/or its affiliates.
Released under the Universal Permissive License v1.0 as shown at
<https://oss.oracle.com/licenses/upl/>.
[contributing]: https://github.com/oracle/python-select-ai/blob/main/CONTRIBUTING.md
[documentation]: https://docs.oracle.com/en/cloud/paas/autonomous-database/serverless/pysai/
[ghdiscussions]: https://github.com/oracle/python-select-ai/discussions
[ghissues]: https://github.com/oracle/python-select-ai/issues
[samples]: https://github.com/oracle/python-select-ai/tree/main/samples
[security]: https://github.com/oracle/python-select-ai/blob/main/SECURITY.md
Raw data
{
"_id": null,
"home_page": null,
"name": "select-ai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": "Abhishek Singh <abhishek.o.singh@oracle.com>",
"keywords": "oracle, select-ai, adbs, autonomous database serverless",
"author": null,
"author_email": "Abhishek Singh <abhishek.o.singh@oracle.com>",
"download_url": "https://files.pythonhosted.org/packages/ea/47/ef019073ec79ba27403adfa85882263639918e2956c385c24dca057bd43c/select_ai-1.0.0.tar.gz",
"platform": null,
"description": "# Select AI for Python\n\n\nSelect 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 \u2013 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.\n\nSelect 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.\n\n\n## Installation\n\nRun\n```bash\npython3 -m pip install select_ai\n```\n\n## Documentation\n\nSee [Select AI for Python documentation][documentation]\n\n## Samples\n\nExamples can be found in the [/samples][samples] directory\n\n### Basic Example\n\n```python\nimport select_ai\n\nuser = \"<your_select_ai_user>\"\npassword = \"<your_select_ai_password>\"\ndsn = \"<your_select_ai_db_connect_string>\"\n\nselect_ai.connect(user=user, password=password, dsn=dsn)\nprofile = select_ai.Profile(profile_name=\"oci_ai_profile\")\n# run_sql returns a pandas dataframe\ndf = profile.run_sql(prompt=\"How many promotions?\")\nprint(df.columns)\nprint(df)\n```\n\n### Async Example\n\n```python\n\nimport asyncio\n\nimport select_ai\n\nuser = \"<your_select_ai_user>\"\npassword = \"<your_select_ai_password>\"\ndsn = \"<your_select_ai_db_connect_string>\"\n\n# This example shows how to asynchronously run sql\nasync def main():\n await select_ai.async_connect(user=user, password=password, dsn=dsn)\n async_profile = await select_ai.AsyncProfile(\n profile_name=\"async_oci_ai_profile\",\n )\n # run_sql returns a pandas df\n df = await async_profile.run_sql(\"How many promotions?\")\n print(df)\n\nasyncio.run(main())\n\n```\n## Help\n\nQuestions can be asked in [GitHub Discussions][ghdiscussions].\n\nProblem reports can be raised in [GitHub Issues][ghissues].\n\n## Contributing\n\nThis project welcomes contributions from the community. Before submitting a pull request, please [review our contribution guide][contributing]\n\n## Security\n\nPlease consult the [security guide][security] for our responsible security vulnerability disclosure process\n\n## License\n\nCopyright (c) 2025 Oracle and/or its affiliates.\n\nReleased under the Universal Permissive License v1.0 as shown at\n<https://oss.oracle.com/licenses/upl/>.\n\n[contributing]: https://github.com/oracle/python-select-ai/blob/main/CONTRIBUTING.md\n[documentation]: https://docs.oracle.com/en/cloud/paas/autonomous-database/serverless/pysai/\n[ghdiscussions]: https://github.com/oracle/python-select-ai/discussions\n[ghissues]: https://github.com/oracle/python-select-ai/issues\n[samples]: https://github.com/oracle/python-select-ai/tree/main/samples\n[security]: https://github.com/oracle/python-select-ai/blob/main/SECURITY.md\n",
"bugtrack_url": null,
"license": null,
"summary": "Select AI for Python",
"version": "1.0.0",
"project_urls": {
"Documentation": "https://docs.oracle.com/en/cloud/paas/autonomous-database/serverless/pysai/",
"Homepage": "https://github.com/oracle/python-select-ai",
"Issues": "https://github.com/oracle/python-select-ai/issues",
"Repository": "https://github.com/oracle/python-select-ai"
},
"split_keywords": [
"oracle",
" select-ai",
" adbs",
" autonomous database serverless"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "0498754c792ce43e0314c99d4a2233515bc3cd311a6b640dad5e780c1fecd288",
"md5": "f838f2d95ab555db27c3c0e95686bf78",
"sha256": "ae8365ea0fcb891960f88729ac7e735c93b3906c3c574e69a58dd8f4094dfaa2"
},
"downloads": -1,
"filename": "select_ai-1.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f838f2d95ab555db27c3c0e95686bf78",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 31500,
"upload_time": "2025-09-04T06:37:54",
"upload_time_iso_8601": "2025-09-04T06:37:54.028373Z",
"url": "https://files.pythonhosted.org/packages/04/98/754c792ce43e0314c99d4a2233515bc3cd311a6b640dad5e780c1fecd288/select_ai-1.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "ea47ef019073ec79ba27403adfa85882263639918e2956c385c24dca057bd43c",
"md5": "0eff460a857b3473a4e10114001207ec",
"sha256": "fa77aa6cb5029db69e7fdeaedf5c5c20d76616f9afc3667f0bd364a17b12ad00"
},
"downloads": -1,
"filename": "select_ai-1.0.0.tar.gz",
"has_sig": false,
"md5_digest": "0eff460a857b3473a4e10114001207ec",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 32511,
"upload_time": "2025-09-04T06:37:55",
"upload_time_iso_8601": "2025-09-04T06:37:55.009108Z",
"url": "https://files.pythonhosted.org/packages/ea/47/ef019073ec79ba27403adfa85882263639918e2956c385c24dca057bd43c/select_ai-1.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-04 06:37:55",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "oracle",
"github_project": "python-select-ai",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "select-ai"
}
JSON
