New version of the integration out now, it is now compatible with any other Open AI API compatible project
Text Generation WebUI#
To install it on the same device as Home Assistant (CPU only)
To install it on you own PC (Windows/Mac/Linux/WSL)
Configure the Model#
If you are using the Add-On, just click on the show Add-on button ↑, and then click on Open Web UI
If you are using the PC version, just open the web UI from the link in the console or just go to http://localhost:7860/ from the PC you installed it
If you want a simpler AI configuration using this same integration, take a look at my Ollama + Home Assistant Tutorial
List of Compatible Models#
Home 3B v3 GGUF#
acon96/Home-3B-v3-GGUF| Name | Quant method | Bits | Size | Max RAM required | Use Case |
|---|---|---|---|---|---|
| Home-3B-v3.q2_k.gguf | Q2_K | 2 | 1.08 GB | 3.50 GB | smallest, significant quality loss - not recommended for most purposes |
| Home-3B-v3.q3_k_m.gguf | Q3_K_M | 3 | 1.39 GB | 3.89 GB | very small, high quality loss |
| Home-3B-v3.q4_k_m.gguf | Q4_K_M | 4 | 1.71 GB | 4.21 GB | medium, balanced quality - recommended |
| Home-3B-v3.q5_k_m.gguf | Q5_K_M | 5 | 1.99 GB | 4.49 GB | large, very low quality loss - recommended |
| Home-3B-v3.q8_0.gguf | Q8_0 | 8 | 2.97 GB | 5.47 GB | very large, extremely low quality loss - not recommended |
Home 3B v2 GGUF#
acon96/Home-3B-v2-GGUF| Name | Quant method | Bits | Size | Max RAM required | Use Case |
|---|---|---|---|---|---|
| home-3b-v2.q2_k.gguf | Q2_K | 2 | 1.11 GB | 3.67 GB | smallest, significant quality loss - not recommended for most purposes |
| home-3b-v2.q3_k_m.gguf | Q3_K_M | 3 | 1.43 GB | 3.98 GB | very small, high quality loss |
| home-3b-v2.q4_k_m.gguf | Q4_K_M | 4 | 1.74 GB | 4.29 GB | medium, balanced quality - recommended |
| home-3b-v2.q5_k_m.gguf | Q5_K_M | 5 | 2.00 GB | 4.57 GB | large, very low quality loss - recommended |
| home-3b-v2.q8_0.gguf | Q8_0 | 8 | 2.96 GB | 5.46 GB | very large, extremely low quality loss - not recommended |
Home 1B v2 GGUF#
acon96/Home-1B-v2-GGUF| Name | Quant method | Bits | Size | Use Case |
|---|---|---|---|---|
| home-1B-v2.q2_k.gguf | Q2_K | 2 | 582 MB | smallest, significant quality loss - not recommended for most purposes |
| home-1B-v2.q3_k_m.gguf | Q3_K_M | 3 | 742 MB | very small, high quality loss |
| home-1B-v2.q4_k_m.gguf | Q4_K_M | 4 | 894 GB | medium, balanced quality - recommended |
| home-1B-v2.q5_k_m.gguf | Q5_K_M | 5 | 1.03 GB | large, very low quality loss - recommended |
| home-1B-v2.q8_0.gguf | Q8_0 | 8 | 1.51 GB | very large, extremely low quality loss - not recommended |
The above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
Llama Conversation Integration#
By acon96
Configure Assistant#
How to get better results#
My prompt
You are a helpful AI Assistant that controls the devices in a house. Complete the following task as instructed or answer the following question with the information provided only.
You can use any motion sensor to determine precense in a room.
For example: if binary_sensor.entrance_motion_sensor 'Entrance Motion Sensor' = on, then someone is at the entrance.
Current Time: {{ as_timestamp(now()) | timestamp_custom("%c %Z") }}
Service: {{ services }}
Devices:
{{ devices }}How to Trigger Automations and Scripts#
You can use this button to go to the helpers page and create a input_boolean (Toggle) using the user interface .