mirror of
https://github.com/acon96/home-llm.git
synced 2026-01-10 14:18:00 -05:00
docs: Format README for better usability (#50)
This commit is contained in:
Zeno Jiricek
209
README.md
209
README.md
@@ -1,7 +1,147 @@
|
||||
# Home LLM
|
||||
This project provides the required "glue" components to control your Home Assistant installation with a completely local Large Language Model acting as a personal assistant. The goal is to provide a drop in solution to be used as a "conversation agent" component by Home Assistant.
|
||||
|
||||
## Model
|
||||
### Home Assistant Component
|
||||
|
||||
In order to integrate with Home Assistant, we provide a `custom_component` that exposes the locally running LLM as a "conversation agent".
|
||||
|
||||
This component can be interacted with in a few ways:
|
||||
|
||||
- using a chat interface so you can chat with it.
|
||||
- integrating with Speech-to-Text and Text-to-Speech addons so you can just speak to it.
|
||||
|
||||
The component can either run the model directly as part of the Home Assistant software using llama-cpp-python, or you can run the [oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui) project to provide access to the LLM via an API interface.
|
||||
|
||||
When doing this, you can host the model yourself and point the add-on at machine where the model is hosted, or you can run the model using text-generation-webui using the provided [custom Home Assistant add-on](./addon).
|
||||
|
||||
|
||||
## Requirements
|
||||
|
||||
- Supported version of HomeAssistant. (at time of writing this is `2024.1.6`)
|
||||
- [HACs](https://hacs.xyz/docs/setup/download/) (if you want to install it that way)
|
||||
- SSH or Web Terminal access to your HomeAssistant instance: if you want to use builtin llama-cpp or perform manual install
|
||||
|
||||
## 🏃 Getting Started
|
||||
|
||||
Installing and configuration HomeLLM will involve several steps:
|
||||
|
||||
1. 💾 Install the HomeLLM component.
|
||||
2. ⚙️ Choose and Configure a Backend
|
||||
3. 🗣️ Configure the Voice Assistant
|
||||
|
||||
|
||||
### 💾 🚕 Install HomeLMM with HACs
|
||||
|
||||
> 🛑 ✋🏻 Requires HACs
|
||||
>
|
||||
> First make sure you have [HACs installed](https://hacs.xyz/docs/setup/download/)
|
||||
|
||||
Once you have HACs installed, this button will help you add the repository to HACS and open the download page
|
||||
|
||||
1. [](https://my.home-assistant.io/redirect/hacs_repository/?category=Integration&repository=home-llm&owner=acon96)
|
||||
2. Restart Home Assistant
|
||||
|
||||
A "LLaMA Conversation" device should show up in the `Settings > Devices and Services > [Devices]` tab now:
|
||||
|
||||
|
||||
|
||||
### 💾 🔨 Install HomeLMM Manually
|
||||
|
||||
1. Ensure you have either the Samba, SSH, FTP, or another add-on installed that gives you access to the `config` folder
|
||||
2. If there is not already a `custom_components` folder, create one now.
|
||||
3. Copy the `custom_components/llama_conversation` folder from this repo to `config/custom_components/llama_conversation` on your Home Assistant machine.
|
||||
4. Restart Home Assistant: `Developer Tools -> Services -> Run` : `homeassistant.restart`
|
||||
|
||||
A "LLaMA Conversation" device should show up in the `Settings > Devices and Services > [Devices]` tab now:
|
||||
|
||||
|
||||
|
||||
### ⚙️ Configuration and Setup
|
||||
|
||||
Decide if you want to have your model served by an api or not:
|
||||
|
||||
- ✖️: continue on.
|
||||
- ✔️ then follow instructions below on [`llama-cpp-python`](#llama-cpp-python)
|
||||
|
||||
1. `Settings > Devices and Services`.
|
||||
2. Click the `Add Integration` button in the bottom right of the screen.
|
||||
3. Filter the list of "brand names" for llama, and "LLaMa Conversation" should remain.
|
||||
4. Choose and configure the backend. [More info 👇](#configure-backend)
|
||||
1. Using builtin llama.cpp with hugging face
|
||||
2. Using builtin llama.cpp with existing model file
|
||||
3. using text-generation-webui api
|
||||
4. using generic openapi compatiable api
|
||||
5. using ollama api
|
||||
|
||||
### 🗣️ Configuring the component as a Conversation Agent
|
||||
|
||||
1. Navigate to `Settings` -> `Voice Assistants`
|
||||
2. Select `+ Add Assistant`
|
||||
3. Name the assistant whatever you want.
|
||||
4. Select the [conversation agent](#link-to-the-title-id-where-you-guide-the-user-in-doing-this) that we created previously.
|
||||
5. If using STT or TTS configure these now
|
||||
6. Return to the "Overview" dashboard and select chat icon in the top left.
|
||||
7. From here you can submit queries to the AI agent.
|
||||
|
||||
In order for any entities be available to the agent, you must "expose" them first.
|
||||
|
||||
1. Navigate to "Settings" -> "Voice Assistants" -> "Expose" Tab
|
||||
2. Select "+ Expose Entities" in the bottom right
|
||||
3. Check any entities you would like to be exposed to the conversation agent.
|
||||
|
||||
> 🛑 ✋🏻 Security Warning
|
||||
>
|
||||
> Any devices that you select to be exposed to the model will be added as
|
||||
> context and potentially have their state changed by the model.
|
||||
>
|
||||
> Only expose devices that you want the model modifying the state of.
|
||||
>
|
||||
> The model may occasionally hallucinate and issue commands to the wrong device!
|
||||
>
|
||||
> Use.At.Your.Own.Risk 💣
|
||||
|
||||
|
||||
## Technical Details
|
||||
|
||||
|
||||
### `llama-cpp-python`
|
||||
|
||||
This only applies to you if you don't want to spin up your own llm api server and instead just want it to be abstracted away as an implementation detail.
|
||||
|
||||
Once this is done, the backend setup process for the LLaMa.cpp options will handle installing the appropriate `*.whl` file.
|
||||
|
||||
In order to run a model directly as part of your Home Assistant installation, you will need to install one of the pre-build wheels because there are no existing musllinux wheels for the package. Compatible wheels for x86_x64 and arm64 are provided in the [dist](./dist) folder. Copy the `*.whl` files to the `custom_components/llama_conversation/` folder. They will be installed while setting up the component.
|
||||
|
||||
Obtain terminal access to the HomeAssistant instance and create some prerequisite folders. We'll download a set of prebundled python wheel files.
|
||||
|
||||
```console
|
||||
mkdir -p /config/custom_components/llama_conversation
|
||||
cd /config/custom_components/llama_conversation
|
||||
|
||||
wget https://github.com/acon96/home-llm/raw/develop/dist/llama_cpp_python-0.2.38-cp311-cp311-musllinux_1_2_aarch64.whl
|
||||
wget https://github.com/acon96/home-llm/raw/develop/dist/llama_cpp_python-0.2.38-cp311-cp311-musllinux_1_2_x86_64.whl
|
||||
```
|
||||
|
||||
> ❔ 🤔 How to get Terminal Access?
|
||||
>
|
||||
> There'll be many ways, but for the sake of simplicity you can try out these
|
||||
> addons:
|
||||
>
|
||||
> - https://github.com/hassio-addons/repository?tab=readme-ov-file#-studio-code-server
|
||||
> - https://github.com/hassio-addons/repository?tab=readme-ov-file#-advanced-ssh--web-terminal
|
||||
|
||||
|
||||
|
||||
### Constrained Grammar
|
||||
|
||||
When running the model locally with [Llama.cpp], the component also constrains the model output using a GBNF grammar.
|
||||
This forces the model to provide valid output no matter what since its outputs are constrained to valid JSON every time.
|
||||
This helps the model perform significantly better at lower quantization levels where it would previously generate syntax errors.
|
||||
|
||||
For more information See [output.gbnf](./custom_components/llama_conversation/output.gbnf) for the existing grammar.
|
||||
|
||||
|
||||
### Model
|
||||
The "Home" models are a fine tuning of the Phi model series from Microsoft. The model is able to control devices in the user's house as well as perform basic question and answering. The fine tuning dataset is a combination of the [Cleaned Stanford Alpaca Dataset](https://huggingface.co/datasets/yahma/alpaca-cleaned) as well as a [custom synthetic dataset](./data) designed to teach the model function calling based on the device information in the context.
|
||||
|
||||
The latest models can be found on HuggingFace:
|
||||
@@ -74,7 +214,7 @@ The 3B model was trained as a LoRA on an RTX 3090 (24GB) using the following set
|
||||
<details>
|
||||
<summary>Training Arguments</summary>
|
||||
|
||||
```
|
||||
```console
|
||||
python3 train.py \
|
||||
--run_name home-3b \
|
||||
--base_model microsoft/phi-2 \
|
||||
@@ -97,7 +237,7 @@ The 1B model was trained as a full fine-tuning on on an RTX 3090 (24GB). Trainin
|
||||
<details>
|
||||
<summary>Training Arguments</summary>
|
||||
|
||||
```
|
||||
```console
|
||||
python3 train.py \
|
||||
--run_name home-1b \
|
||||
--base_model microsoft/phi-1_5 \
|
||||
@@ -113,47 +253,41 @@ python3 train.py \
|
||||
</details>
|
||||
<br/>
|
||||
|
||||
## Home Assistant Component
|
||||
In order to integrate with Home Assistant, we provide a `custom_component` that exposes the locally running LLM as a "conversation agent" that can be interacted with using a chat interface as well as integrate with Speech-to-Text and Text-to-Speech addons to enable interacting with the model by speaking.
|
||||
|
||||
The component can either run the model directly as part of the Home Assistant software using llama-cpp-python, or you can run the [oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui) project to provide access to the LLM via an API interface. When doing this, you can host the model yourself and point the add-on at machine where the model is hosted, or you can run the model using text-generation-webui using the provided [custom Home Assistant add-on](./addon).
|
||||
### Backend Configuration
|
||||
|
||||
When running the model locally with Llama.cpp, the component also constrains the model output using a GBNF grammar. This forces the model to provide valid output no matter what because it is constrained to outputting valid JSON every time. This helps the model perform significantly better at lower quantization levels where it would generate syntax errors previously. See [output.gbnf](./custom_components/llama_conversation/output.gbnf) for the existing grammar.
|
||||
|
||||
|
||||
### Installing with HACS
|
||||
You can use this button to add the repository to HACS and open the download page
|
||||
When setting up the component, there are 5 different "backend" options to choose from:
|
||||
|
||||
[](https://my.home-assistant.io/redirect/hacs_repository/?category=Integration&repository=home-llm&owner=acon96)
|
||||
|
||||
### Installing Manually
|
||||
1. Ensure you have either the Samba, SSH, FTP, or another add-on installed that gives you access to the `config` folder
|
||||
2. If there is not already a `custom_components` folder, create one now.
|
||||
3. Copy the `custom_components/llama_conversation` folder from this repo to `config/custom_components/llama_conversation` on your Home Assistant machine.
|
||||
4. Restart Home Assistant using the "Developer Tools" tab -> Services -> Run `homeassistant.restart`
|
||||
5. The "LLaMA Conversation" integration should show up in the "Devices" section now.
|
||||
|
||||
### Setting up
|
||||
When setting up the component, there are 4 different "backend" options to choose from:
|
||||
1. Llama.cpp with a model from HuggingFace
|
||||
2. Llama.cpp with a locally provided model
|
||||
3. A remote instance of text-generation-webui
|
||||
4. A generic OpenAI API compatible interface; *should* be compatible with LocalAI, LM Studio, and all other OpenAI compatible backends
|
||||
a. Llama.cpp with a model from HuggingFace
|
||||
b. Llama.cpp with a locally provided model
|
||||
c. A remote instance of text-generation-webui
|
||||
d. A generic OpenAI API compatible interface; *should* be compatible with LocalAI, LM Studio, and all other OpenAI compatible backends
|
||||
e. Ollama api
|
||||
|
||||
See [docs/Backend Configuration.md](/docs/Backend%20Configuration.md) for more info.
|
||||
|
||||
**Installing llama-cpp-python for local model usage**:
|
||||
In order to run a model directly as part of your Home Assistant installation, you will need to install one of the pre-build wheels because there are no existing musllinux wheels for the package. Compatible wheels for x86_x64 and arm64 are provided in the [dist](./dist) folder. Copy the `*.whl` files to the `custom_components/llama_conversation/` folder. They will be installed while setting up the component.
|
||||
|
||||
**Setting up the Llama.cpp backend with a model from HuggingFace**:
|
||||
#### Llama.cpp Backend with a model from HuggingFace
|
||||
|
||||
This is option A
|
||||
|
||||
You need the following settings to configure the local backend from HuggingFace:
|
||||
1. Model Name: the name of the model in the form `repo/model-name`. The repo MUST contain a GGUF quantized model.
|
||||
2. Model Quantization: The quantization level to download. Pick from the list. Higher quantizations use more RAM but have higher quality responses.
|
||||
|
||||
**Setting up the Llama.cpp backend with a locally downloaded model**:
|
||||
#### Llama.cpp Backend with a locally downloaded model
|
||||
|
||||
This is option B
|
||||
|
||||
You need the following settings to configure the local backend from HuggingFace:
|
||||
1. Model File Name: the file name where Home Assistant can access the model to load. Most likely a sub-path of `/config` or `/media` or wherever you copied the model file to.
|
||||
|
||||
**Setting up the "remote" backends**:
|
||||
#### Remote Backends
|
||||
|
||||
This is effectively options C, D and E
|
||||
|
||||
You need the following settings in order to configure the "remote" backend:
|
||||
1. Hostname: the host of the machine where text-generation-webui API is hosted. If you are using the provided add-on then the hostname is `local-text-generation-webui` or `f459db47-text-generation-webui` depending on how the addon was installed.
|
||||
2. Port: the port for accessing the text-generation-webui API. NOTE: this is not the same as the UI port. (Usually 5000)
|
||||
@@ -164,23 +298,6 @@ With the remote text-generation-webui backend, the component will validate that
|
||||
**Setting up with LocalAI**:
|
||||
If you are an existing LocalAI user or would like to use LocalAI as your backend, please refer to [this](https://io.midori-ai.xyz/howtos/setup-with-ha/) website which has instructions on how to setup LocalAI to work with Home-LLM including automatic installation of the latest version of the the Home-LLM model. The auto-installer (LocalAI Manager) will automatically download and setup LocalAI and/or the model of your choice and automatically create the necessary template files for the model to work with this integration.
|
||||
|
||||
### Configuring the component as a Conversation Agent
|
||||
**NOTE: ANY DEVICES THAT YOU SELECT TO BE EXPOSED TO THE MODEL WILL BE ADDED AS CONTEXT AND POTENTIALLY HAVE THEIR STATE CHANGED BY THE MODEL. ONLY EXPOSE DEVICES THAT YOU ARE OK WITH THE MODEL MODIFYING THE STATE OF, EVEN IF IT IS NOT WHAT YOU REQUESTED. THE MODEL MAY OCCASIONALLY HALLUCINATE AND ISSUE COMMANDS TO THE WRONG DEVICE! USE AT YOUR OWN RISK.**
|
||||
|
||||
In order to utilize the conversation agent in HomeAssistant:
|
||||
1. Navigate to "Settings" -> "Voice Assistants"
|
||||
2. Select "+ Add Assistant"
|
||||
3. Name the assistant whatever you want.
|
||||
4. Select the "Conversation Agent" that we created previously
|
||||
5. If using STT or TTS configure these now
|
||||
6. Return to the "Overview" dashboard and select chat icon in the top left.
|
||||
|
||||
From here you can submit queries to the AI agent.
|
||||
|
||||
In order for any entities be available to the agent, you must "expose" them first.
|
||||
1. Navigate to "Settings" -> "Voice Assistants" -> "Expose" Tab
|
||||
2. Select "+ Expose Entities" in the bottom right
|
||||
3. Check any entities you would like to be exposed to the conversation agent.
|
||||
|
||||
### Running the text-generation-webui add-on
|
||||
In order to facilitate running the project entirely on the system where Home Assistant is installed, there is an experimental Home Assistant Add-on that runs the oobabooga/text-generation-webui to connect to using the "remote" backend option.
|
||||
|
||||
Reference in New Issue
Block a user