As the title says, here's my OpenAI Controller for Reactor:
OpenAI Controller per Reactor. Contribute to dbochicchio/reactor-openai development by creating an account on GitHub.
It supports both OpenAI and Azure OpenAI endpoints. You'll need keys/endpoints, according to each service.
The controller supports multiple models, and each one could be mapped as an entity.
It's quite easy to use, and responses can be stored in variables, for easy access. Or sent to another action (Text To Speech, another endpoint, etc).
9013ae50-fd68-42a2-87c3-97479132e465-image.png
80a88eec-7c89-464a-8196-690b4b72d044-image.png
Have fun with LLM into your scenes!
In Home Assistant I have an integration that if I add entities to it, I will get the following error in MSR as certain entity values I'm using in expressions are null for a moment. This is more or less cosmetic issue and happens very rarely as I rarely modify that integration on the hass side.
Screenshot 2024-11-28 at 22.20.41.png
And the expression is
Screenshot 2024-11-28 at 22.38.19.png
Could I "wrap" hass-entity shown above somewhat differently to prevent this error from happening? Using build 24302.
Hello
I am trying to set up Multi System Reactor to automate routines across multiple smart home devices & platforms (e.g., Home Assistant, SmartThings, and Hubitat). While I have successfully linked the systems; I am facing issues with:
-Delays in triggering actions on secondary devices.
-Inconsistent execution of complex logic conditions.
-Synchronization of states between devices when one system updates.
Is there a recommended way to optimize performance & confirm seamless state sharing across systems?
I have checked https://smarthome.community/category/22/multi-system-reactor-msbi guide for reference but still need advice.
Any tips on debugging or log analysis to pinpoint where the issue arises would also be appreciated.
Thank you !
I've managed to use MSR UI on iOS devices to some degree*, so that although UI elements (e.g. rule sets) are not visible in portrait mode, you've seen them in landscape. Now with recents builds (24302) this does not work anymore, elements (rule sets, entities) are not anymore visible in landscape mode.
Does anyone have similar experiences? Using iOS 18 and Safari/Chrome browser.
( *Drag & drop of rule conditions have never worked on a mobile)
@toggledbits Since I have upgraded ZWaveJSController to 24293 from 24257 I am seeing entries related to registering action set_volume, but action is not defined by the capability 143 every time I restart Reactor.
The Siren seems to be doing what it is supposed to do. The volume levels are fine. Should I worry about it?
Reactor version 24302
ZWaveJSController version 24293
Z-Wave JS UI version 9.27.4
zwave-js version 14.3.4
I have the following ACL defined:
groups: admin: users: - admin applications: true api_acls: # This ACL allows users in the "admin" group to access the API - url: "/api" group: admin allow: true log: true # This ACL allows anyone/thing to access the /api/v1/alive API endpoint - url: "/api/v1/alive" allow: trueAnd I have authenticated to MSR as "admin" user. However, I'm getting "access denied" when trying to access http://*******:8111/api/v1/log
So what I'm missing, is my ACL incorrectly defined?
Using build 24302 on Docker.
Thanks to @toggledbits for adding a custom CSS. I've started doing a darker Reactor style.
Here's the file: https://gist.github.com/dbochicchio/825098ac13b7f8cac22012eae37ff7ce
A couple of things are still too bright and I'll eventually catch-up. Just place it under your /config directory, naming the file as customstyles.css. Hard refresh your browser.
Hi
I have just connected a bunch of EzloPi controllers to MSR to import some ESP based devices etc.
They all seemed to have worked and imported in to MSR apart from I have one missing device. It is a Digital Gas Sensor device.
This is how that device looks in the Ezlo API.
Devices Info:
_id: "10696001" deviceTypeId: "ezlopi" parentDeviceId: "10696000" category: "level_sensor" subcategory: "" gatewayId: "457a5069" batteryPowered: false name: "Gas Sensor Digital" type: "sensor" reachable: true persistent: true serviceNotification: false armed: false roomId: "" security: "no" ready: true status: "idle" parentRoom: true protectConfig: "default"Items Info:
_id: "20696001" deviceId: "10696001" hasGetter: true hasSetter: false name: "smoke_density" show: true valueType: "substance_amount" scale: "parts_per_million" value: 2.7472610473632812 valueFormatted: "2.75" status: "idle"There is also an Analog Gas sensor that one did import in to MSR OK.
68d63dab-b871-4f44-912b-cf6e0b9eb4c6-image.png
Devices Info:
_id: "10696000" deviceTypeId: "ezlopi" parentDeviceId: "10696000" category: "security_sensor" subcategory: "gas" gatewayId: "457a5069" batteryPowered: false name: "Gas Sensor Analog" type: "sensor" reachable: true persistent: true serviceNotification: false armed: false roomId: "" security: "no" ready: true status: "idle" parentRoom: true protectConfig: "default"Items Info:
_id: "20696000" deviceId: "10696000" hasGetter: true hasSetter: false name: "gas_alarm" show: true valueType: "token" enum: 0: "no_gas" 1: "combustible_gas_detected" 2: "toxic_gas_detected" 3: "unknown" valueFormatted: "no_gas" value: "no_gas" status: "idle"And this is how this MQ2 Gas Sensor looks like on their dashboard:
Digital
cb77dfa3-4af5-4d06-9635-89207a716a89-image.png
Analog
4fb4da1b-e946-4b89-876c-bcd9f5699b6c-image.png
They have an EzloPi website here you can create your own sensor projects using ESP boards, which is very interesting stuff!
And I just wrote on the Ezlo forum here, how to connect an EzloPi controller to MSR.
THANKS.
Build 21228 has been released. Docker images available from DockerHub as usual, and bare-metal packages here.
Home Assistant up to version 2021.8.6 supported; the online version of the manual will now state the current supported versions; Fix an error in OWMWeatherController that could cause it to stop updating; Unify the approach to entity filtering on all hub interface classes (controllers); this works for device entities only; it may be extended to other entities later; Improve error detail in messages for EzloController during auth phase; Add isRuleSet() and isRuleEnabled() functions to expressions extensions; Implement set action for lock and passage capabilities (makes them more easily scriptable in some cases); Fix a place in the UI where 24-hour time was not being displayed.A couple of things for you @toggledbits, since you mentioned that this release has new features and some tweaks are expected.
Local expressions cannot be deleted. Pushing the X button has no effect for me.
When cloning an entity action, the result is strange (first is cloned one, second is the original action):
a92ea094-9e2c-4aaa-bf47-2d07a6ffdbd0-image.png
When changing the action on the cloned element, the params are added to the original one. See screenshot:
92ac3011-83c8-466b-bd23-47d483ad7a52-image.png
Dark theme has a couple of strange contrasts. One is visible in the previous screenshots (white text on yellow background). Another one is in groups (blue text on blue background):
9b3c4988-53ef-44e6-9672-30e744cacb75-image.png
Overall, I found blue, yellow, red and green (in buttons and forms) to be too bright.
On the bright side:
I love the new script action: thank you! The dark theme is a great start to avoid getting blinded at night I promise I'll try very soon the new features around actions. Thanks!@toggledbits
I just upgraded to version MSR 24293, bare metal running on Fedora. Upon restart, I am getting a error banner:
I followed the new directions about npm
npm i --no-save --no-package-lock --omit dev
Any idea what the issue is?
Seems like switching the UI to the newly added dark mode (thank you for this) does nothing. The UI stays in light mode and only a few buttons turn into dark mode (see screenshot)
Things I have tried:
Hard refresh
Different browser
Different computer
Restarting Reactor
Failed troubleshooting attempts:
No errors in Chrome console
No relevant errors in Reactor log (can still PM the full log file)
Reactor version: latest-24293-ea42a81d
Hardware: Odroid N2+
Linux version: Ubuntu 24.04.1 LTS
3df2806f-9146-485b-9ec1-d056e91cefe5-image.png Dark mode enabled
ff823023-c079-4684-b01f-d6ac6527d31a-image.png Light mode enabled
Good morning,
I have a service MQTT service that needs a restart occasionally. The add-on (Smartbed MQTT) is for the smart bed base for my bed. It has a "safety light" that I can control from HAAS & MSR as a light entity, and also moves the head of the bed to a preset at bedtime, and then lies it back flat in the morning The problem is, from time to time, the light becomes "unavailable" Restarting from the Add-ons tab in HAAS always fixes it, but I should be able to detect when it happens when "light.tempur_pedic_safety_lights" is not true or false, i.e., unavailable.
What I don't know how to do is how to restart that service. Does anybody have experience in restarting add-ons from MSR?
Running:
Reactor (Multi-hub) latest-24212-3ce15e25 ZWaveJSController [0.1.24232]HAAS:
RPi5-64 (8GB) Core 2024.7.3 Supervisor 2024.08.0 Operating System 13.0 Frontend 20240710.0Hi!
Is it possible to generate two additional log files, the first being the replica of what is displayed on screen by the Rule History widgets and the other with Recently Changed Entities?
And could I configure the generation of one file per day, and delete the older ones? For example, store the last 5 days?
And being more ambitious, does Windget have an icon to open these TXT files in the navigated?
Well, we're approaching Christmas, so here's my request to Santa Claus @toggledbits 🙂
Hi @toggledbits
I'm working on a controller to generate llm response from a prompt in reactor. I have http response coming thru an http request action at the moment, capturing the response inside a local variable. So, it's practically sync.
I want to create a controller, so I don't have to rely on a proxy (and have a simpler architecture), and duplicate absurd http actions, but AFAIK in the current implementation, actions are async only. But if I have multiple requests going on, I cannot be sure what it's really inside an attribute. I also thought that something like a correlation id when sending the request could be used to identity multiple responses, but I wanted to double check with you before starting with something too complicated. I also noticed that some actions in home assistant (ie forecast) are sync and I'm wondering if you have any plan or hint to address this situation. Thanks.
Thanks.
@togglebits I am curious as to why the tilt_sensor.state (primary) = NULL. I believe it should show true or false. I have to use binary_sensor.state instead in my rules.
Again, not sure if this is related to Reactor/ZwaveJSController implementation or the actual Z-Wave JS UI docker version. I have copied, below, the attributes of the tilt sensor in hopes it can help.
Thanks in advance.
Reactor version 23302
ZWaveJSController version 23254
Z-Wave JS UI version 9.3.0.724519f
zwave-js version 12.2.3
[Reactor] Services with sync response
-
I don't want to use an HTTP action, but a controller one! Right now it's impossible to save entity action response to a variable, if I'm not missing something. The question is this: how to build the same flow using a controller action?
-
But you can use the entity-based action response as if it was a variable. It is in many ways better, in fact, because there's a ton more code required in Reactor to make rule conditions responsive to variables than there is to make it responsive to attributes — attributes are very efficient.
I know you don't want to use an HTTP Request, but I want to know why. I guess I'm not understanding what's inadequate about the HTTP Request for your purpose in the first place.
-
My /ai/prompt endpoint encapsulate the logic to query OpenAI. That's great for me personally (so, not really shareable with the community), but that's another moving part in the system that could potentially fail. This is a simple web API that is proxying OpenAI (in this case Azure Open AI, but that's the same). It is acting as my controller, but it's not reusable, it's prone to errors and I think an
OpenAIController
will be better than this.All that said:
But you can use the entity-based action response as if it was a variable. It is in many ways better, in fact, because there's a ton more code required in Reactor to make rule conditions responsive to variables than there is to make it responsive to attributes — attributes are very efficient.
So, you think that it's better to have two rules, one triggering the request and another looking for the response and watching the attributes (ie: response and response_id, tied to a request_id from the original prompt)?
-
I'm not understanding why you think it takes two rules.
If you run an HTTP Request and store the response in a local variable, the next step in the same Reaction has access to that local variable. And the contents of that local variable will be exactly the response to the request, not any other request (so no ID tracking is necessary). The Rule that triggers the request can be the same rule that processes it.
Are you assuming that the HTTP Request action is asynchronous when storing the result? Because it's not. It will wait for the result and store it before moving on to the next step of the Reaction. That's documented.
-
-
@therealdb said in [Reactor] Services with sync response:
No, I'm quite experienced and I know how a promise works
I'm not talking about a Promise, and of course I know well that you know how that works. I'm talking about the HTTP Request action in a Reaction. It waits for the response and stores it, so that the rest of the steps of the Reaction can work with the response received. If that doesn't address your need, I'm unclear how.
-
ok, so, here's a photoshopped version of the ideal world I'm trying to describe:
The point here is that I don't want to do an HTTP request, I want to call an entity action and capture the result, if any, in a variable. Keep in mind that I'm describing an ideal world, and I'm OK to alternative solutions that still uses a Controller (and not an HTTP Action, that's temporary and I want to move to a custom Controller), wait for a response from a service, capture it and use in the same flow, if possible.
So, more like services than entity-oriented controller.
I hope this is better explained now. Thanks!
-
OK. I think I see where you are going. I was bogged down by the HTTP part, since that's existing functionality you can solve the problem with today. You're really asking for something much bigger. You just generally want entity actions to be able to return data, which they currently don't, so you can do things like:
- Return the next upcoming event from a calendar;
- Receive a value and look it up in a table, then return the found result;
- Given the name of a playlist on a media player, return the list of media it contains.
- Given the symbol for a security or crypto coin, return its current price.
- Run a script on Home Assistant and receive whatever response it returned.
And you want this to work in-line in Reactions, without necessarily binding the result value to an attribute on the entity performing the action, or having to preconfigure an input in YAML config (e.g. the symbol for a stock or crypto asset to be fetched/polled). The result value is, in fact, typically temporary and not useful outside the context of the Reaction (although it and values derived from it can be stored otherwise by other steps of the Reaction).
Do I have it now?
-
@toggledbits yes sir. That why you're the master and I'm your humble follower
Because I know it's not trivial, I'm also asking for guidance on how to achieve something similar with what we have today. Thanks.
-
I'm on it. Sit tight.
-