Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
All models deployed to Azure AI Foundry Models support the Azure AI Model Inference API and its associated family of SDKs.
To use these SDKs, connect them to the Azure AI model inference URI (usually in the form https://<resource-name>.services.ai.azure.com/models).
Azure AI Inference package
The Azure AI Inference package allows you to consume all models deployed to the Azure AI Foundry resource and easily switch the model deployment from one to another. The Azure AI Inference package is part of the Azure AI Foundry SDK.
| Language | Documentation | Package | Examples |
|---|---|---|---|
| C# | Reference | azure-ai-inference (NuGet) | C# examples |
| Java | Reference | azure-ai-inference (Maven) | Java examples |
| JavaScript | Reference | @azure/ai-inference (npm) | JavaScript examples |
| Python | Reference | azure-ai-inference (PyPi) | Python examples |
Integrations
| Framework | Language | Documentation | Package | Examples |
|---|---|---|---|---|
| LangChain | Python | Reference | langchain-azure-ai (PyPi) | Python examples |
| Llama-Index | Python | Reference | llama-index-llms-azure-inference (PyPi) llama-index-embeddings-azure-inference (PyPi) |
Python examples |
| Semantic Kernel | Python | Reference | semantic-kernel[azure] (PyPi) | Python examples |
| AutoGen | Python | Reference | autogen-ext[azure] (PyPi) | Quickstart |
Limitations
Azure AI Foundry doesn't support the Cohere SDK or the Mistral SDK.
Next step
- To see what models are currently supported, see Foundry Models and capabilities.