Blueprint upgrades #134
Merged
Blueprint upgrades #134
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Force the automation to use single mode with suppressed warnings (see https://www.home-assistant.io/docs/automation/modes/). To implement the cooldown, add a delay as the last action in the actions. Also remove the cooldown from the automation conditions. The main difference here is that no new triggers will arrive while the automation is running. The condition is smaller now, and is limited to the content of the automation, and not managing how the automation is run. With this narrowing, it opens up the possibility of adding other conditions to the blueprint config in the future.
rappazzo
force-pushed
the
blueprint-upgrades
branch
2 times, most recently
from
af4dd16 to
2880019
Compare
|
I think I have one small error in the jinja (it doesn't support |
The frigate payload includes a label which indicates what the detected object is. This can be useful to separate llm-vision automations to react differently for different objects. For example, if a bird is detected, the ai instructions could include something like, "if you see a bird, try to identify what species it is". This discription doesn't make much sense if the detected object is a person, and including separate instructions to the ai makes it more confusing on both the human and ai side of things. Allowing for separate instructions by object will make for easier to understand automations.
rappazzo
force-pushed
the
blueprint-upgrades
branch
from
2880019 to
6d754f2
Compare
|
OK, I fixed the length issue. It tests fine and the automation seems to continue with and without objects defined in the config. Of course, I would suggest that you also test this before merging if you have a frigate instance. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is a repeat of the commit comments, which I think are pretty descriptive
Change 1: re-implement cooldown with singlemode execution and a delay
Force the automation to use single mode with suppressed warnings (see here). To implement the cooldown, add a delay as the last action in the actions. Also remove the cooldown from the automation conditions.
The main difference here is that no new triggers will arrive while the automation is running. The condition is smaller now, and is limited to the content of the automation, and not managing how the automation is run. With this narrowing, it opens up the possibility of adding other conditions to the blueprint config in the future.
Change 2: blueprint: add a filter for frigate object detection
The frigate payload includes a label which indicates what the detected object is. This can be useful to separate llm-vision automations to react differently for different objects.
For example, if a bird is detected, the ai instructions could include something like, "if you see a bird, try to identify what species it is". This discription doesn't make much sense if the detected object is a person, and including separate instructions to the ai makes it more confusing on both the human and ai side of things. Allowing for separate instructions by object will make for easier to understand automations.