# AI Features

- [How to use on-premise Ollama with AI Connector](https://docs.frends.com/guides/ai-features/how-to-use-on-premise-ollama-with-ai-connector.md): Using your own Ollama installation to perform operations with AI.
- [How to use Azure AI Inference service with AI Connector](https://docs.frends.com/guides/ai-features/how-to-use-azure-ai-inference-service-with-ai-connector.md): Using your own Azure AI Inference service and API.
- [Using Fine-Tuned Models with Azure AI Inference in Frends](https://docs.frends.com/guides/ai-features/using-fine-tuned-models-with-azure-ai-inference-in-frends.md): How to use models tuned specifically for your use case.
- [Creating semi-deterministic AI Process](https://docs.frends.com/guides/ai-features/creating-semi-deterministic-ai-process.md): How to use AI reasoning with control flow from a Process.
- [How to create Reusable AI Agents as Frends Subprocesses](https://docs.frends.com/guides/ai-features/how-to-create-reusable-ai-agents-as-frends-subprocesses.md): Reusable AI Agents as part of your Processes.
- [How to implement a simple RAG in Frends](https://docs.frends.com/guides/ai-features/how-to-implement-a-simple-rag-in-frends.md): Retrieval-augmented generation at its simplest is a standard Frends Process with AI.
- [How to tokenize data for AI](https://docs.frends.com/guides/ai-features/how-to-tokenize-data-for-ai.md): Using regexes and field value replacement for structured data to securely use AI.
- [How to provide data to AI Connector in Frends](https://docs.frends.com/guides/ai-features/how-to-provide-data-to-ai-connector-in-frends.md): AI Connector will only receive the data you provide.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.frends.com/guides/ai-features.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.