jeans/home-assistant.io
jeans/home-assistant.io
1
0
Fork 0
mirror of https://github.com/home-assistant/home-assistant.io.git synced 2025-07-19 15:26:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

2024.12: Process review comments

Browse Source
This commit is contained in:
Franck Nijhof 2024-12-04 18:22:37 +01:00
parent 93606fdfb8
commit 6b38875d30
No known key found for this signature in database
GPG Key ID: D62583BA8AB11CA3
1 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
source/_posts/2024-12-04-release-202412.markdown
View File

@ -84,12 +84,12 @@ waking up everyone. 😅
[@karwosts] & [@marcinbauer85] to the rescue! 🦸‍♂️ As of this release, the scene
editor has two modes. A **review mode** and an **edit mode**.
<img class="no-shadow" alt="Dialog showing the Assist pipeline configuration, showing the new option to prefer handling commands locally." src="/images/blog/2024-12/scene-review-mode.png"/>
<img class="no-shadow" alt="The improved scene editor now as a preview mode, which is shown in this screenshot." src="/images/blog/2024-12/scene-review-mode.png"/>
The review mode is the default mode, and it will show you the scene as it is
currently set up, but it will not apply it. You can then switch to the edit
mode the scene is activated allow you to adjust the actual scenery and snapshot
it again once you are happy with the changes.
The “review mode” is how your scene will open, and it will show you the scene as
it is currently set up, but it will not apply it. You can then switch to the
"edit mode"; only then will the scene activate, allowing you to adjust the
actual scenery and snapshot it again once you are happy with the changes.
Additionally, if you prefer {% term YAML %}, you can edit scenes directly from
the scene editor by selecting **“Edit in YAML”** from the three-dotted
@ -102,7 +102,7 @@ the scene editor by selecting **“Edit in YAML”** from the three-dotted
It has almost been two years since [we started our journey] into building our
very own open source voice assistants, with the goal of letting users control
their Home Assistant in their own language.
Home Assistant in their own language.
Today, we are getting even closer to the finish line. Not just with the features
that ship in this release, but you might have heard about our voice hardware
@ -124,15 +124,15 @@ But before we get there, let's dive into the features that ship in this release!
### Let your voice assistant fall back to a LLM-based agent
[Exactly 6 months ago] we bridged the gap between our default conversation agent
and the wonderful (and scary) world of [LLMs]. We allowed you to let an
LLM-based conversation agent control your home instead of relying on our
[Exactly 6 months ago], we bridged the gap between our default conversation agent
and the wonderful (and scary) world of [LLMs]. We allowed you to experiment and
let an LLM-based conversation agent control your home instead of relying on our
built-in sentences.
This choice was an interesting first step. LLMs are generally much smarter and
more knowledgeable about the world than our default agent. However, they are
often slow and/or expensive. And let’s face it: Even if the demos are cool,
90% of the commands we say in our homes are simple:
This choice was an interesting first step. LLMs are generally much better at
interpreting natural language and more knowledgeable about the world than our
default agent. However, they are often slow and/or expensive. And let’s face it:
Even if the demos are cool, 90% of the commands we say in our homes are simple:
_“Turn this on”_ or _“Turn that off”_.
Today, we're finally allowing users to **mix** these worlds. Starting from this
@ -142,7 +142,7 @@ agent if no matches are found.
<img class="no-shadow" alt="Dialog showing the Assist pipeline configuration, showing the new option to prefer handling commands locally." src="/images/blog/2024-12/llm-fallback-configuration.png"/>
This allows you to mix both worlds' pros with almost none of the cons.
This allows you to mix the pros of both worlds with almost none of the cons.
Specific known commands will be processed locally and extremely fast, and the
power of an LLM will only be used for more complex queries that Home Assistant
@ -155,8 +155,8 @@ does not natively understand.
### Language leaders are accelerating the pace
It is not a secret: our voice hardware will be revealed on 19 December 2024.
Language leaders have already gottten their hands on the device, and are working
It is no secret: our voice hardware will be revealed on 19 December 2024.
Language leaders have already got their hands on the device, and are working
extremely hard to polish support for their language.
The number of contributions to our [intents repository] (where we store the
@ -164,9 +164,9 @@ supported sentences) skyrocketed during the last month, which we all truly
appreciate. More and more languages are becoming usable or even complete!
You can follow the progress [here](https://home-assistant.github.io/intents/).
We won't list them all here, but just be aware that it is very likely that
someone is hard at work making sure your native language gets some love so
you can speak with your home.
We won’t list them all here, but rest assured, someone is likely working hard to
ensure your native language works seamlessly, so you can use it comfortably
at home.
[intents repository]: https://github.com/home-assistant/intents?tab=readme-ov-file
@ -201,7 +201,7 @@ really evolve with the rest of Home Assistant and the general expectations of
our community. It was time for a change!
Over the last few months, we have worked with the community to revise and
improve the scale. Involving not just our community developers, but also
improve the scale. Involving not just our community developers but also
documentation writers, user experience designers, and anyone interested
in the community.
@ -240,7 +240,7 @@ summary of their characteristics on our dedicated
We sincerely hope this new scale, will not just help our users, but also our
community developers to understand what is expected by providing a clear path
oto improving their integrations. To help with that, we have now
to improving their integrations. To help with that, we have now
[extensively documented every rule and requirement for each tier in our
developer documentation].
@ -554,7 +554,7 @@ starting on 27 November.
{% details "Statistics" %}
Previously the attributes was only provided when they had a non `None` value.
Previously the attributes were only provided when they had a non `None` value.
This has now changed so the attributes are always provided even with `None`
values. You might need to modify your automations or scripts depending on
whether these attributes are present or not.
@ -592,7 +592,7 @@ need to adjust those for this change.
The `this` template variable which is available in some templatable helpers was
previously based on the new state instead of the current state.
The change affects the following integrations, if templates the use the `this`
The change affects the following integrations, if templates use the `this`
variable. The user might have to update their templates to reflect the above
change using the `value` variable instead, which holds the new value.