mirror of
https://github.com/home-assistant/home-assistant.io.git
synced 2025-07-12 20:06:52 +00:00
2024.12: Iterate on the voice section
This commit is contained in:
parent
5179fe84b7
commit
e5fc70bfe4
@ -142,19 +142,20 @@ 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
|
### Let your voice assistant fall back to a LLM-based agent
|
||||||
|
|
||||||
[Exactly 6 months ago] we bridged the gap between our intent world and the
|
[Exactly 6 months ago] we bridged the gap between our default conversation agent
|
||||||
wonderful (and scary) world of LLMs. We allowed you to let an LLM agent control
|
and the wonderful (and scary) world of [LLMs]. We allowed you to let an
|
||||||
your home instead of relying on our built-in intents.
|
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
|
This choice was an interesting first step. LLMs are generally much smarter and
|
||||||
more knowledgeable about the world than our built-in intents. However, they are
|
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,
|
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:
|
90% of the commands we say in our homes are simple:
|
||||||
_“Turn this on”_ or _“Turn that off”_.
|
_“Turn this on”_ or _“Turn that off”_.
|
||||||
|
|
||||||
Today, we're finally allowing users to **mix** these worlds. Starting from this
|
Today, we're finally allowing users to **mix** these worlds. Starting from this
|
||||||
release, you can set up a voice assistant in a way that will target our fast,
|
release, you can set up a voice assistant that targets our fast,
|
||||||
community-driven, built-in intents first, and only fallback to an LLM-based
|
community-driven conversation agent first and only falls back to an LLM-based
|
||||||
agent if no matches are found.
|
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.png"/>
|
<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.png"/>
|
||||||
@ -167,45 +168,43 @@ does not natively understand.
|
|||||||
|
|
||||||
<lite-youtube videoid="vThoxRIxHyI" videotitle="Let your voice assistant fall back to a LLM-based agent" posterquality="maxresdefault"></lite-youtube>
|
<lite-youtube videoid="vThoxRIxHyI" videotitle="Let your voice assistant fall back to a LLM-based agent" posterquality="maxresdefault"></lite-youtube>
|
||||||
|
|
||||||
[Exactly 6 months ago]: https://www.home-assistant.io/blog/2024/06/05/release-20246/
|
[Exactly 6 months ago]: /blog/2024/06/05/release-20246/
|
||||||
|
[LLMs]: https://en.wikipedia.org/wiki/Language_model
|
||||||
|
|
||||||
### Language leaders are accelerating the pace
|
### Language leaders are accelerating the pace
|
||||||
|
|
||||||
It is not a secret: our voice hardware will come soon. Language leaders already
|
It is not a secret: our voice hardware will be revealed on 19 December 2024.
|
||||||
got their hands on the device, and are working extremely hard to polish support
|
Language leaders have already gottten their hands on the device, and are working
|
||||||
for their language.
|
extremely hard to polish support for their language.
|
||||||
|
|
||||||
The amount of contributions on our [intents repository] (where we store the
|
The number of contributions to our [intents repository] (where we store the
|
||||||
supported sentences) skyrocketed during the last month. It is something we all
|
supported sentences) skyrocketed during the last month, which we all truly
|
||||||
truly appreciate. More and more languages are becoming usable, or even complete!
|
appreciate. More and more languages are becoming usable or even complete!
|
||||||
You can follow the progress [here](https://home-assistant.github.io/intents/).
|
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
|
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
|
someone is hard at work making sure your native language gets some love so
|
||||||
that you can speak with your home.
|
you can speak with your home.
|
||||||
|
|
||||||
[intents repository]: https://github.com/home-assistant/intents?tab=readme-ov-file
|
[intents repository]: https://github.com/home-assistant/intents?tab=readme-ov-file
|
||||||
|
|
||||||
### A faster voice experience
|
### A faster voice experience
|
||||||
|
|
||||||
[HASSIL], our intent parser, was built from the ground up to match a sentence to
|
Our default conversation agent was built from the ground up to match a sentence
|
||||||
its underlying intention extremely fast and on cheap hardware.
|
to its underlying intention extremely fast and on cheap hardware.
|
||||||
|
|
||||||
Release after release, we added more use-cases and more sentences to
|
Release after release, we added more use cases and sentences to Home Assistant,
|
||||||
Home Assistant, and our sentence-matching logic became slower and slower. In
|
and our sentence-matching logic became slower and slower. In some languages,
|
||||||
some of the languages, a non-matching sentence could take more than 15 seconds
|
a non-matching sentence could take more than 15 seconds to process!
|
||||||
to be processed!
|
|
||||||
|
|
||||||
This release adds a lot of love to HASSIL; we completely reengineered the way
|
This release adds a lot of love to this matching logic; we completely
|
||||||
we match sentences. On top of that, language leaders spent some time reducing
|
reengineered the way we match sentences. On top of that, language leaders spent
|
||||||
the complexity of their sentences. Some languages saw a reduction of 99% in the
|
some time reducing the complexity of their sentences. Some languages saw a 99%
|
||||||
number of possible combinations!
|
reduction in the number of possible combinations!
|
||||||
|
|
||||||
The results speak for themselves:
|
The results speak for themselves:
|
||||||
|
|
||||||
<lite-youtube videoid="U_CMXL2Z5NE" videotitle="A faster voice experience with HASSIL" posterquality="maxresdefault"></lite-youtube>
|
<lite-youtube videoid="U_CMXL2Z5NE" videotitle="A faster voice experience with Our default conversation agent" posterquality="maxresdefault"></lite-youtube>
|
||||||
|
|
||||||
[HASSIL]: https://github.com/home-assistant/hassil
|
|
||||||
|
|
||||||
## Revised Integration Quality Scale
|
## Revised Integration Quality Scale
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user