> For the complete documentation index, see [llms.txt](https://docs.infotopics.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.infotopics.com/trulyp/ai/getting-started.md). # Getting started To get started with AI, you will first need to connect your AI configuration to Trulyp. The first steps will take part in AI - Configuration. When you first get started with Trulyp, you will see that your AI configuration page is empty.

Click **New Configuration** in the top right corner, which leads you to the 'create new configuration page'.

Firstly, choose your AI provider from the following list, and then fill in the requested data.

{% tabs %} {% tab title="OpenAI" %} To connect with **OpenAI,** we need a **Name, API key** and **default model,** the rest of the settings are optional. To find out where to find your API key, click [here.](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key)

To get a list of all the available models, click **Fetch models & parameters.** You will then get a list of all options, from which you can select your prefered default model. #### Optional settings The **base URL** allows you to access an OpenAI API on a different location than the standard location. Use the **Organization ID** only if your OpenAI API key needs to be tied to a specific OpenAI organization. If you don’t know you need it, leave it blank. {% endtab %} {% tab title="Anthropic" %} To connect with **Anthropic,** we need a **Name, API key** and **default model,** the rest of the settings are optional. To find out where to find your API key, click [here.](https://platform.claude.com/docs/en/get-api-key)

{% endtab %} {% tab title="Azure OpenAI" %} To connect with **Azure OpenAI**, we need a **Name**, **API key**, **Endpoint** and **Deployment name**. The API version is also required. The rest of the settings are optional.

To find your **API Key** and **Endpoint**, head to the [Azure Portal](https://portal.azure.com/), search for **Azure OpenAI**, click on the resource name to which you would like to get the key, and then click **Keys and Endpoint** under Resource management.

#### Optional settings The Secondary API key can be used as a fallback key, in case the primary key stops working. {% endtab %} {% tab title="Custom / OSS" %} To connect to any self-hosted or OpenAI-compatible endpoint, you can use this provider. You will have to enter your **Authentication type**, **API Key**, **Base URL**, and **Model identifier.**

We support three types of **Authentication types**: Bearer token, Custom header, and No authentication. {% endtab %} {% endtabs %} After filling in all the required information, test your configuration.

If the test succeeds, you can set the **Authorization** and then save your AI configuration, or first optionally change the [#parameters](#parameters "mention") to fine-tune how your AI will respond. #### Authorization

By default, your AI configuration is not available for everyone within your organization that uses Trulyp. You can fine-tune who can access what configuration by assigning the **Teams** for the configuration, or allow **only admins** to use it. If you want **everyone** to be able to use this configuration, simply choose the 'Everyone' team! Now that you are finished, you can press the "Save configuration" button and start using AI in Trulyp! #### Parameters

These optional settings allow you to tweak exactly how the AI functions: **Temperature** How random the output is. Lower values give focused, predictable answers (good for factual/structured tasks); higher values give more varied, creative answers (good for brainstorming). A common starting point is about a quarter of the way up the range for factual work, and two-thirds up for creative work. **Max tokens per request** The hard cap on how long a single response can be, in tokens (roughly 4 characters each). A higher limit allows longer answers but costs more and takes longer to generate. Pick a small number (e.g. a few hundred) for lite jobs like classification, short replies, or single-field extraction; pick a larger number (several thousand, up to the model's max) for heavier jobs like long-form writing, multi-step reasoning, or generating large structured documents. **Request timeout** Minimum: 5 seconds — no fixed maximum How long the app waits for the provider to respond before giving up. Keep it low (a few seconds) for lite jobs that should return quickly; raise it (30s or more) for heavier jobs — long generations, reasoning models, or large max-token limits — that legitimately take longer. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## 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, and the optional `goal` query parameter: ``` GET https://docs.infotopics.com/trulyp/ai/getting-started.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.