> Markdown versions of all pages of this connector library are available by appending `.md` to the page URL. For the full index of connectors, see [llms.txt](https://connectors.appmixer.com/llms.txt).

# Azure AI Foundry connector

- Connector: `appmixer.ai.foundry`
- Version: 1.0.0
- Components: 6 (0 triggers, 6 actions)

Use the models deployed in your own Azure AI Foundry (Microsoft Foundry, Azure OpenAI) resource: AI agents with tools and MCP servers, prompts, structured output and embeddings.

- Connector page: <https://connectors.appmixer.com/connector/appmixer.ai.foundry/1.0.0>
- Source code: <https://github.com/clientIO/appmixer-connectors/tree/dev/src/appmixer/ai/foundry>
- Download package: <https://connectors.appmixer.com/connector/appmixer.ai.foundry/1.0.0/download>

## Authentication

**Type:** API Key

**Fields:**

- `Endpoint` (text): Endpoint of your Azure AI Foundry (Azure OpenAI) resource, e.g. `https://my-resource.openai.azure.com` or `https://my-resource.services.ai.azure.com`. Find it in the Azure portal under your resource, _Keys and Endpoint_, or on the overview page of your Foundry project.
- `API Key` (password): Key 1 or Key 2 of the same resource, from _Keys and Endpoint_ in the Azure portal.

## Actions (6)

- [AI Agent](https://connectors.appmixer.com/connector/appmixer.ai.foundry/1.0.0/component/appmixer.ai.foundry.AIAgent.md) (`appmixer.ai.foundry.AIAgent`): Build an AI agent responding with contextual answers or performing contextual actions. Connect a component to the 'tools' output port to let the agent call it as a tool, and mark the fields the model should fill with the 'Model Defined Parameter' variable; components connected behind it run as further steps of the same tool. For a tool with its own description and logic (branches, loops), connect a 'Tool Start' to the 'tools' port and end every branch with 'Tool Output'. An MCP server on the 'tools' port gives the agent all of its tools.
- [Generate Embeddings](https://connectors.appmixer.com/connector/appmixer.ai.foundry/1.0.0/component/appmixer.ai.foundry.GenerateEmbeddings.md) (`appmixer.ai.foundry.GenerateEmbeddings`): Generate embeddings for text data. The text is split into chunks and embedding is returned for each chunk. The returned embeddings is an array of the form: `[{ "index": 0, "text": "chunk1", "vector": [1.1, 1.2, 1.3] }]`. TIP: use the **JSONata modifier** to convert the embeddings array into custom formats. For convenience, the component also returns the first vector in the embeddings array which is useful when querying vector databases to find relevant chunks.
- [List Models](https://connectors.appmixer.com/connector/appmixer.ai.foundry/1.0.0/component/appmixer.ai.foundry.ListModels.md) (`appmixer.ai.foundry.ListModels`): List the models available on the Azure AI Foundry resource.
- [Make Api Call](https://connectors.appmixer.com/connector/appmixer.ai.foundry/1.0.0/component/appmixer.ai.foundry.MakeApiCall.md) (`appmixer.ai.foundry.MakeApiCall`): Make an authorized call to any endpoint of the Azure AI Foundry resource of the connected account.
- [Send Prompt](https://connectors.appmixer.com/connector/appmixer.ai.foundry/1.0.0/component/appmixer.ai.foundry.SendPrompt.md) (`appmixer.ai.foundry.SendPrompt`): Send a prompt to a Large Language Model and receive a response.
- [Transform Text To J S O N](https://connectors.appmixer.com/connector/appmixer.ai.foundry/1.0.0/component/appmixer.ai.foundry.TransformTextToJSON.md) (`appmixer.ai.foundry.TransformTextToJSON`): Extract structured JSON data from text using AI.

## Changelog

### 1.0.0

- First version. AI Agent, Send Prompt, Transform Text To JSON, Generate Embeddings, List Models and Make API Call against the OpenAI compatible v1 API of an Azure AI Foundry resource. The account holds the resource endpoint and API key, so every account can use a different resource.
