> ## Documentation Index
> Fetch the complete documentation index at: https://developer.upsun.com/llms.txt
> Use this file to discover all available pages before exploring further.

# How to deploy AI

Upsun provides powerful capabilities for hosting AI applications,
agents, and services. You can deploy AI workloads using any supported runtime
and integrate with various LLM APIs and services.

<Info>
  Before you start, check out the [Upsun demo app](https://console.upsun.com/projects/create-project)
  and the main [Getting started guide](/docs/get-started/here).
  They provide all the core concepts and common commands you need to know before
  using the following materials.
</Info>

## AI applications and services

* [**AI Agents**](/docs/get-started/ai/aiagent) - Host conversational AI agents
  and chatbots using any
  supported runtime
* [**MCP Servers**](/docs/get-started/ai/deploy-mcp) - Deploy Model Context Protocol servers for
  AI tool integration
* [**Upsun MCP Server**](/docs/get-started/ai/using-the-mcp) - Use the Upsun Model Context Protocol Server
* [**Upsun performance agent**](/docs/get-started/ai/upsun-performance-agent) - Analyze Blackfire profiles, continuous profiling data, and traffic to generate a performance report
* **Vector Databases** - [Chroma](/tutorials/self-hosted/chroma), [Qdrant](/tutorials/self-hosted/qdrant)

## Supported technologies

* **Runtimes**: Python, Node.js, PHP, Ruby, Go, Java, and
  [supported runtime types](/docs/configure-apps/app-reference/single-runtime-image#type)
* **LLM APIs**: [OpenAI](https://platform.openai.com/docs),
  [Anthropic Claude](https://docs.anthropic.com/en/docs/getting-started-with-the-api),
  [Google Gemini](https://ai.google.dev/docs),
  [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/),
  [AWS Bedrock](https://docs.aws.amazon.com/bedrock/),
  and any other HTTP-based API service
* **AI Frameworks**: [LangChain](https://docs.langchain.com/oss/python/langchain/install),
  [LlamaIndex](https://docs.llamaindex.ai/), [Chainlit](https://docs.chainlit.io/),
  and custom implementations
* **Integration**: REST APIs, WebSockets, and event-driven architectures

<Info>
  <h4>API flexibility</h4>
  Upsun supports integration with **any** LLM service that provides an HTTP API.
  The services listed above are just popular examples. You can integrate with
  self-hosted models, specialized AI services, or any custom API endpoint that
  follows standard HTTP protocols.
</Info>

## Get started

1. **Choose your runtime**: Select the programming language that
   best fits your AI application needs.
2. **Configure your app**: Set up your application in the `.upsun/config.yaml` configuration file. You can use AI to [generate an initial configuration](/cli/init).
3. **Integrate LLM APIs**: Connect to your preferred AI service providers.
4. **Deploy and scale**: Push your code and let Upsun handle the infrastructure.

For detailed examples and tutorials, see the
[AI and Machine Learning tutorials on DevCenter](https://developer.upsun.com/tutorials/ai?utm_source=docs\&utm_medium=ai-section\&utm_campaign=tutorials).

Find out more about the many [languages Upsun supports](/docs/languages).