feat: promote assistant configuration
This commit is contained in:
1 parent
c0445cdca2
commit
cba2df72e2
13 files changed
+219
-23
No files matched your search
@@ -0,0 +1,76 @@
|
||||
---
|
||||
tags:
|
||||
- Assistant
|
||||
- AI
|
||||
- Administration
|
||||
- Security
|
||||
---
|
||||
|
||||
# Homarr Assistant
|
||||
|
||||
Administrators can configure the instance-wide AI assistant from **Management → Assistant**.
|
||||
It is available to signed-in users from the header, the user menu, and the `Cmd/Ctrl + K` command menu.
|
||||
`Cmd/Ctrl + Shift + K` opens it directly.
|
||||
|
||||
When the assistant is unavailable, its command-menu result remains visible but disabled and explains that
|
||||
an administrator must configure and enable it.
|
||||
|
||||
## Configure a model provider
|
||||
|
||||
Homarr includes presets for OpenRouter, OpenAI, Anthropic Claude, Google Gemini, xAI, Groq, Mistral AI,
|
||||
DeepSeek, Together AI, Ollama, and LM Studio. Provider icons make the presets easy to identify. A custom
|
||||
preset connects any other service that implements the OpenAI Chat Completions API.
|
||||
|
||||
1. Choose a provider preset or **Custom endpoint**.
|
||||
2. Confirm the API base URL. It usually ends in `/v1`.
|
||||
3. Add an API key if the service requires bearer authentication.
|
||||
4. Add any provider-specific authentication or routing headers.
|
||||
5. Save the provider connection.
|
||||
6. Refresh the model list or enter an exact model ID manually.
|
||||
7. Enable the assistant and save the configuration.
|
||||
|
||||
The model discovery path defaults to `/models` and is appended to the API base URL. Leave it blank when
|
||||
the service does not expose model discovery. A manual model ID can still be used.
|
||||
|
||||
API keys and additional header values are encrypted in the Homarr database. They are decrypted only on
|
||||
the server for discovery and model requests, and they are never returned to the browser. Changing the
|
||||
provider or base URL clears existing credentials unless replacements are submitted with the change. This
|
||||
prevents credentials for one service from being sent to another endpoint.
|
||||
|
||||
:::info Container networking
|
||||
|
||||
For a containerized Homarr installation, `localhost` refers to the Homarr container. Use a resolvable
|
||||
container name, internal DNS name, or host gateway address to reach Ollama, LM Studio, or another local
|
||||
model server.
|
||||
|
||||
:::
|
||||
|
||||
The configured endpoint must support streaming Chat Completions and structured tool calls for the full
|
||||
assistant experience. Model discovery alone does not guarantee tool support, except when OpenRouter
|
||||
explicitly advertises the model's `tools` capability.
|
||||
|
||||
The Claude preset uses Anthropic's OpenAI SDK compatibility layer. Anthropic describes that layer as
|
||||
suited to testing and comparison rather than as its full native API; unsupported OpenAI fields may be
|
||||
ignored. Streaming responses and tool calls are supported, which are the capabilities Homarr Assistant
|
||||
uses. Choose OpenRouter or another provider when you prefer a provider-neutral production endpoint.
|
||||
|
||||
## Conversations and tools
|
||||
|
||||
Conversations and messages are stored per user in the Homarr database. Users can start, revisit, archive,
|
||||
and delete conversations from the assistant panel.
|
||||
|
||||
The assistant can use the same internal tool definitions as the [Homarr MCP server](./mcp).
|
||||
Each tool call runs as the signed-in user, so normal Homarr permission checks still apply. Read-only
|
||||
procedures can run during the agent loop. Mutating procedures require an explicit approval in the
|
||||
conversation before they execute.
|
||||
|
||||
Homarr also exposes a small set of browser-only actions to the assistant. These actions can navigate to
|
||||
safe internal routes and open Homarr interfaces such as the command menu and media request search.
|
||||
They never receive provider credentials and cannot navigate to arbitrary external URLs.
|
||||
|
||||
:::warning
|
||||
|
||||
Assistant prompts and selected tool results are sent to the configured model endpoint. Review that
|
||||
service's privacy and retention terms before enabling this feature for an instance.
|
||||
|
||||
:::
|
||||
@@ -12,7 +12,7 @@ Homarr exposes a [Model Context Protocol](https://modelcontextprotocol.io) serve
|
||||
|
||||
With MCP, you can ask your AI assistant to manage apps, integrations, users, boards, Docker containers, media servers, DNS settings, and more - all through Homarr's existing tRPC API, now exposed as 50+ AI-callable tools.
|
||||
|
||||
The optional [Homarr Assistant](./settings#homarr-assistant) uses these same tool definitions internally.
|
||||
The optional [Homarr Assistant](./assistant) uses these same tool definitions internally.
|
||||
Unlike external MCP clients, it uses the current Homarr session directly and asks for in-conversation
|
||||
approval before running mutating procedures.
|
||||
|
||||
|
||||
Reference in new issue
Block a user