llimona-azure-openai
llimona-azure-openai is the Azure provider addon for Llimona.
It integrates Azure OpenAI as a pluggable backend provider so Llimona can expose OpenAI-compatible interfaces while forwarding requests to Azure OpenAI endpoints.
What this addon provides
- A provider addon discoverable through the
llimona.addonentry-point group (azure_openai). - A provider type:
azure_openai. - OpenAI Responses integration (
create,retrieve, andcancel). - OpenAI Models integration (
list,retrieve, anddelete). - Streaming and non-streaming response mapping into Llimona interface models.
Provider behavior
The addon builds an AsyncAzureOpenAI client from provider configuration:
base_url: Azure OpenAI endpoint base URL.credentials.api_key: API key used for authentication.api_version:v1.
For response creation, the provider:
- Validates whether the target model allows the requested service.
- Translates Llimona request fields into Azure OpenAI Responses API parameters.
- Calls Azure OpenAI.
- Maps the returned payload (including stream events) into Llimona response/event types.
Typical use cases
- Expose Azure OpenAI through a unified Llimona gateway.
- Combine Azure regions/providers behind a single routing layer.
- Reuse Llimona contexts, constraints, and sensors with Azure-backed workloads.
- Keep provider logic modular and independent from core application code.
Minimal provider example
type: azure_openai
name: azure_example
display_name: Azure Example
base_url: https://<your-resource>.openai.azure.com/openai/v1/
credentials:
api_key: <your-api-key>
services:
- type: openai_responses
- type: openai_models
models:
- name: gpt-4o-mini
allowed_services:
- openai_responses
Installation
From PyPI:
pip install llimona-azure-openai
# or
uv add llimona-azure-openai
Notes
- This addon is designed to be loaded by a Llimona app configuration via
provider_addons. - Service-level access can be constrained per model using
allowed_services. - Observability is inherited from Llimona contexts and sensors, so Azure-backed requests remain traceable and measurable.
License
This addon uses the same license as the llimona package: GNU AFFERO GENERAL PUBLIC LICENSE. See the repository LICENSE file for details.
Metadata
Release files for llimona-azure-openai 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| llimona_azure_openai-0.1.0.tar.gz | 5.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llimona_azure_openai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 10.6 kB
Release files / llimona_azure_openai-0.1.0.tar.gz
| Download URL | llimona_azure_openai-0.1.0.tar.gz |
|---|---|
| Size | 5.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
25835b3bf60968dd34993f624d671fedadefd09e6269d31c97f3b1c74f0c6013
|
|
BLAKE2b-256 checksum How to use checksums |
460c8742f4bb77ef068750666de4786b478aa3741ac622571dfc66bcd0faf455
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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 Jun 8, 2026.
Transparency logRelease files / llimona_azure_openai-0.1.0-py3-none-any.whl
| Download URL | llimona_azure_openai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a4d05401984cfa76ffd5575c8112ad6eb61eebec41eebc5119e4f9e384f42f36
|
|
BLAKE2b-256 checksum How to use checksums |
cb3a0f71e44985ddaf78df9b82a76120baeeee0c961fb73196843c727ff59fdf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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 Jun 8, 2026.
Transparency log