> For the complete documentation index, see [llms.txt](https://yvechat.gitbook.io/wp/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://yvechat.gitbook.io/wp/getting-started/first-conversation.md).

# First Conversation

With pairing complete and a model installed, the workspace is ready.

***

### Select a model

Open the model selector. It lists the models YveChat Engine discovered through Ollama, with runtime status shown alongside.

Pick the model you downloaded in [Choose Your First Model](/wp/getting-started/choose-your-first-model.md).

If the list is empty, YveChat Engine has yet to find a model. See [Troubleshooting](/wp/getting-started/troubleshooting.md).

***

### Chat

Type a message and send it.

The first response from a newly selected model takes noticeably longer than later ones, because the model loads into memory before it generates anything. Subsequent replies in the same session start faster while the model stays loaded.

Everything in this exchange happens on your machine. The prompt goes to YveChat Engine, YveChat Engine passes it to Ollama, and the reply returns the same way. The conversation is stored locally by YveChat Engine.

{% hint style="info" %}
Switching selects a different model for the next reply. That first reply may be slower if Ollama needs to load the selected model. Ollama decides whether the previous model remains loaded according to its configuration and the machine's available memory.
{% endhint %}

***

### Web search

Web search adds current information to a conversation, and every response drawing on it carries clickable citations so you can check the source.

Search runs through a local gateway on your machine. The search query itself travels to the configured search service, which is how any web search works. Prompts and conversation history stay local. The query text is the part that leaves.

Turn search off for any conversation where the wording of your question should stay on the machine.

***

### Image Studio

Image Studio generates images locally through ComfyUI.

Image models are managed separately from language models, through a dynamic capability-aware registry. They appear in Image Studio. The language model selector lists Ollama models alone.

Image generation is demanding. Expect it to take longer than text and to use significantly more memory, particularly without a dedicated GPU.

If Image Studio reports no available models, ComfyUI is either absent or not running. See [Troubleshooting](/wp/getting-started/troubleshooting.md).

***

### What reaches whom

| Destination         | Receives                                                        |
| ------------------- | --------------------------------------------------------------- |
| The website host    | A request for the interface files. No prompts, no conversations |
| YveChat Engine      | Your prompts, your conversations, and your local profile        |
| Ollama and ComfyUI  | The prompt text and generation parameters, on your machine      |
| Web-search services | The search query, when search is enabled                        |
| Hosted providers    | Nothing, until hosted-provider support completes                |

Full detail is on the architecture pages.

***

### Where conversations live

Conversations are stored by YveChat Engine on your computer.

You control that storage because it sits on your hardware. Backing up your machine backs up your conversations, and no copy exists anywhere else.

User-configurable external storage is planned, which will let you point that storage at a location of your choosing.


---

# 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://yvechat.gitbook.io/wp/getting-started/first-conversation.md?ask=<question>&goal=<endgoal>
```

`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.