OpenAI

Glad to see someone using OpenAI...

Been using and exploring ChatGPT and it's kind of creepy at a certain point what it can do....generating html code, arduino code, etc, and with more or less fiddling it almost gets there. Even creating random songs with random themes.

Hopefully we can use AI / ML in the near future to predict stuff for our smart homes and projects. That's my goal, to use AI in the future to create stuff like real life presence simulation, predict schedules, and endless possibilities.

Best regards, and happy new year

I got the image generator working. It may take longer time to generate images so I upped the timeout value. Don't know yet how to input those links it generated to a bOS browser. So just copy and paste them to the devices browser.  Http (OpenAI) (1.3).bos

Hey,

I updated the template to GPT-4-preview model - old legacy model is still there but request data for gpt4 changed a little.

Http (OpenAI) (1.4) for public.bos

Few changes: Added gpt-4o model, fine-tuning settings and disable/enable button when http driver should disconnect.

Http (OpenAI) (1.5) for public.bos

Added gpt-4o vision - Http (OpenAI) (1.6) for public.bos

Image url should have a link in it...
Input: should be text input, something the bot needs to find or look at...

Hello Jurgen! Nice job!  I tried to download the file and I set my own API key but when I run the request the HTTP connection goes offline. And the status code shows 429. I run the integration against a free account at Open AI.

Hey, Check if the free account has a balance - They give 15eur for free and then you have to pay to use the API. 429 code means that there were too many requests, not sure if it shows the same error when the balance is at 0. Also when making text requests try to keep it on one line. It may fail if you send the string on a new line from bOS client.

Right now i'm having also strange problems - I tried to make translations for bOS, and now it just crashes the webpage after about 50 translations... So not sure if they are having general troubles right now or not, yesterday it worked better for me. With gpt-4o translating about 1200 indexes(Eng to Estonian and Russian) costed me about 10 euros. 

Edit: Just tested that mine still works in bOS. Also you may need to change the timeout values if you request bigger texts.

HEMS is one of the things that will be very greatto have on Home automation .

When it comes to manage max power demand and heating EV charging etc

If we can feedin Historical data and let IA decide what time It will turn on heating or charge my car thats great

look forward for the changes this will open for CC 

So there's a new kid on the block. More info on its API can be found here: https://github.com/ollama/ollama/blob/main/docs/api.md#api
I made a quick and dirty template for it, do what ever you like with it. And it is running locally and it is able to communicate with bOS. Deepseek-r1 template v0.01

Deepseek Template for bOS: The Ultimate Guide (or at least a "decent" one)

Introduction
Congratulations! You've just acquired the legendary Deepseek template for bOS. This isn't just any template—it's the template. It seeks, it finds, and sometimes, it even works on the first try! (No guarantees, though.)

Getting Started

1. Open bOS and load the Deepseek template. If you don’t know how to do that, maybe ask Google or your friendly neighborhood smart home specialist.
2. Once loaded, take a deep breath. Everything looks complicated, but don't worry—only about 73.5% of it actually matters.

Installing Ollama on Windows (So Deepseek Can Actually Work)

1. Download the Ollama
   installer for Windows from the official site. If you end up on a shady website offering "free bonus tools," reconsider your choices.
2. Run the installer and follow the prompts. If something goes wrong, blame Windows Update.
3. Once installed, open a terminal (Command Prompt or PowerShell) and run:

   ollama pull deepseek-r1

   This will download Deepseek-r1 or what ever model you choose. Yes, it might take a while. No, you don’t need to stare at the progress bar (but we know you will).

4. After it's downloaded, start the model with:

   ollama run deepseek-r1

   If all goes well, you should see some text output instead of errors. Congrats, you’re halfway there!

Configuring Deepseek in bOS

1. Import the Template – Go to bOS config and import the template like a pro.
2. Adjust the IP Address – If Ollama is running locally, keep it on localhost and default port 11434 If it's on another machine, change the IP in the settings. (No, 192.168.1.1 is not always the right answer.)
3. Check if it shows as connected.
4. Set Parameters – Adjust the values as needed Select the correct model you downloaded, insert a prompt and hit send. If something breaks, remember the sacred IT mantra: turn it off and on again.
5. Test It! – Click the send button and watch in awe as Deepseek does its thing (or sits there doing nothing—both are possible).

Troubleshooting (a.k.a. “Why is this not working?”)

• Nothing happens? Check if the device is actually powered on. It sounds obvious, but you'd be surprised.
• Weird values appear? Congratulations! You've just discovered the joy of debugging. Start by verifying the input data, then take a coffee break—this will help maintain sanity.
• Everything’s broken? Reload the template and pretend it never happened.

Final Thoughts
You are now the proud user of the Deepseek template. Will it change your life? Probably not. But it might make bOS a little bit smarter, and that’s a win in our book.

Good luck, and may your smart home always obey your commands (eventually). Tutorial made by it's competitor ChatGPT

Http Ollama-deepseek-r1 (0.02).bos 

Fixed some errors and made a main control panel. Also added model Pull request. Still a lot to do.

Hello Jurgen,

as always, great work on the integration! Will test it out internally as well and post the example (with your credit of course) to our website for all to use!

Best regards, Support team

It's not done yet, so it's still too raw to share, but I'm happy to let anyone contribute, edit, and test it. I even forgot to add the DeepSeek-R1 model to the list, so there's still a lot of work to do. But I did include all the other DeepSeek models, making it easy to switch between them for testing.

What I love about it is that it runs locally, and it's surprisingly good at answering my stupid questions.

Also, I couldn't get chat streaming to work. It would be awesome if users could see the bot's "Thinking" process, as there's a lot of back-and-forth reasoning happening, and it's fun to watch. Is there a way to get streaming to work with the HTTP driver so it stays connected for about five minutes?

Hello Jurgen,

So right out of the bat, when i started sending out commands, the HTTP driver would automatically disconnect, i think it had issues with the model number selection list. If i ran the /api/tags, to get the model number i could get the response for the model number to be : deepseek-r1:latest.. So i created a new string with deepseek-r1:latest as value and use this in the Send command to always try to use the "latest model".

Which seemed fix the issue and all the commands seem to work ok now. It does take quite some time to get an answer (for me it's like 30s.. How's it like on your end?

Best regards.

Yep I added the model later on, didnt update the template in here tho(Edit button went missing by that time). I've only tested deepseek-r1:14b and 9b so far. I haven't timed the responses yet but it isnt that bad under 5 minutes usually(20,76s without stream with 14b) it would show its thinking part sooner if the streaming flag would be true. Ollama is running on a 5950x and 3080ti right now so it is what it is. If you run it without an GPU then it will be a lot slower.

Hello Jurgen,

Ah i see what's going on.. So the longer the response, the more time we wait. For general chatting, it's quite slow at this point, even in PowerShell... To get a full response, in some cases we wait a minute or two to finish everything..
Same goes in bOS.. If the response is very long, we wait till it finishes.. then post the response.. Which in some cases feels like it's not working.. but a minute or so later, we get a response.

For what it is at this point, it seems to work quite well! Just a bit slow :)

Best regards.

Maybe you can look into the http streaming. If streaming=true it would be faster. Here is a same prompt for a joke made 4 times. Times are different even if the prompt is the same. 

llama_new_context_with_model: KV self size = 384.00 MiB, K (f16): 192.00 MiB, V (f16): 192.00 MiB

llama_new_context_with_model: CUDA_Host output buffer size = 0.60 MiB

llama_new_context_with_model: CUDA0 compute buffer size = 307.00 MiB

llama_new_context_with_model: CUDA_Host compute buffer size = 14.01 MiB

llama_new_context_with_model: graph nodes = 1686

llama_new_context_with_model: graph splits = 2

time=2025-01-30T13:40:57.000+02:00 level=INFO source=server.go:594 msg="llama runner started in 3.26 seconds"

[GIN] 2025/01/30 - 13:40:58 | 200 | 3m41s | 192.168.1.100 | POST "/api/chat" I think this was a bug as i had it paused in PS - it calculated both jokes and sent them out together. Usually for a small joke it takes 5-7s

[GIN] 2025/01/30 - 13:40:59 | 200 | 2m20s | 192.168.1.100 | POST "/api/chat"

[GIN] 2025/01/30 - 13:41:02 | 200 | 18.1981495s | 192.168.1.100 | POST "/api/chat"

[GIN] 2025/01/30 - 13:43:50 | 200 | 52.7484304s | 192.168.1.100 | POST "/api/chat"