# AI Assistant

**Digital Assistant** – built on large language models (LLM) of artificial intelligence. The AI assistant uses a **RAG (Retrieval-Augmented Generation)** system, which means it has dual intelligence, combining the creative capabilities of the LLM model with instant search functionality from a knowledge database.

**Steps to set up:**

1. **Create a Workspace**\
   Choose your AI provider (OpenAI, Anthropic, Google, etc.)
2. **Add Integration**\
   Select a text-generation model (e.g., GPT-4.1 for OpenAI)
3. **Create a Knowledge Base**\
   Upload a JSON file or manually add key-value pairs with your business data
4. **Create the Assistant**
   * Select your integration and knowledge base
   * Choose communication channels (WhatsApp, Facebook Messenger, Instagram, Telegram)
   * Enable functionalities (chat, recommendations, calls)
5. **Add System Instructions**\
   Write instructions that define your assistant’s behavior and tone


---

# 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.livecaller.io/livecaller/services/ai-assistant.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.