The series of articles by Adam Conway discusses how the author replaced cloud-based smart assistants like Alexa with a local large language model (LLM) integrated into Home Assistant, enabling more complex and private home automations.
1. **Use a Local LLM**: Set up an LLM (like Qwen) locally using tools such as Ollama and OpenWeb UI.
2. **Integrate with Home Assistant**:
- Enable Ollama integration in Home Assistant.
- Configure the IP and port of the LLM server.
- Select the desired model for use within Home Assistant.
3. **Voice Processing Tools**:
- Use **Whisper** for speech-to-text transcription.
- Use **Piper** for text-to-speech synthesis.
4. **Smart Home Automation**:
- Automate complex tasks like turning off lights and smart plugs with voice commands.
- Use data from IP cameras (via Frigate) to control external lighting based on presence.
5. **Hardware Recommendations**:
- Use Home Assistant Voice Preview speaker or DIY alternatives using ESP32 or repurposed microphones.
1. **Use a Local LLM**: Set up an LLM (like Qwen) locally using tools such as Ollama and OpenWeb UI.
2. **Integrate with Home Assistant**:
- Enable Ollama integration in Home Assistant.
- Configure the IP and port of the LLM server.
- Select the desired model for use within Home Assistant.
3. **Voice Processing Tools**:
- Use **Whisper** for speech-to-text transcription.
- Use **Piper** for text-to-speech synthesis.
4. **Smart Home Automation**:
- Automate complex tasks like turning off lights and smart plugs with voice commands.
- Use data from IP cameras (via Frigate) to control external lighting based on presence.
5. **Hardware Recommendations**:
- Use Home Assistant Voice Preview speaker or DIY alternatives using ESP32 or repurposed microphones.
A tutorial on building a private, offline Retrieval Augmented Generation (RAG) system using Ollama for embeddings and language generation, and FAISS for vector storage, ensuring data privacy and control.
1. **Document Loader:** Extracts text from various file formats (PDF, Markdown, HTML) while preserving metadata like source and page numbers for accurate citations.
2. **Text Chunker:** Splits documents into smaller text segments (chunks) to manage token limits and improve retrieval accuracy. It uses overlapping and sentence boundary detection to maintain context.
3. **Embedder:** Converts text chunks into numerical vectors (embeddings) using the `nomic-embed-text` model via Ollama, which runs locally without internet access.
4. **Vector Database:** Stores the embeddings using FAISS (Facebook AI Similarity Search) for fast similarity search. It uses cosine similarity for accurate retrieval and saves the database to disk for quick loading in future sessions.
5. **Large Language Model (LLM):** Generates answers using the `llama3.2` model via Ollama, also running locally. It takes the retrieved context and the user's question to produce a response with citations.
6. **RAG System Orchestrator:** Coordinates the entire workflow, managing the ingestion of documents (loading, chunking, embedding, storing) and the querying process (retrieving relevant chunks, generating answers).
1. **Document Loader:** Extracts text from various file formats (PDF, Markdown, HTML) while preserving metadata like source and page numbers for accurate citations.
2. **Text Chunker:** Splits documents into smaller text segments (chunks) to manage token limits and improve retrieval accuracy. It uses overlapping and sentence boundary detection to maintain context.
3. **Embedder:** Converts text chunks into numerical vectors (embeddings) using the `nomic-embed-text` model via Ollama, which runs locally without internet access.
4. **Vector Database:** Stores the embeddings using FAISS (Facebook AI Similarity Search) for fast similarity search. It uses cosine similarity for accurate retrieval and saves the database to disk for quick loading in future sessions.
5. **Large Language Model (LLM):** Generates answers using the `llama3.2` model via Ollama, also running locally. It takes the retrieved context and the user's question to produce a response with citations.
6. **RAG System Orchestrator:** Coordinates the entire workflow, managing the ingestion of documents (loading, chunking, embedding, storing) and the querying process (retrieving relevant chunks, generating answers).
This article details how the author successfully ran OpenAI's Codex CLI against a gpt-oss:120b model hosted on an NVIDIA DGX Spark, accessed through a Tailscale network. It covers the setup of Tailscale, Ollama configuration, and the process of running the Codex CLI with the remote model, including building a Space Invaders game.
Local Micro-Agents That Observe, Log and React. Build powerful micro-agents that observe your digital world, remember what matters, and react intelligently—all while keeping your data 100% private and secure.
Learn to deploy your own local LLM service using Docker containers for maximum security and control, whether you're running on CPU, NVIDIA GPU or AMD GPU.
Ollama has partnered with NVIDIA to optimize performance on the new NVIDIA DGX Spark, powered by the GB10 Grace Blackwell Superchip, enabling fast prototyping and running of local language models.
An encyclopedia where everything can be an article, and every article is generated on the spot. Articles are often full of hallucinations and nonsense, especially with lower parameter models. The project uses Ollama and Go to generate content.
This article details how to set up an email triage system using Home Assistant and a local Large Language Model (LLM) to summarize and categorize incoming emails, reducing inbox clutter and improving email management. It covers the setup of a REST command to interface with Ollama, the automation process, and the benefits of using a local LLM for privacy.
A no-install needed web-GUI for Ollama. It provides a web-based interface for interacting with Ollama, offering features like markdown rendering, keyboard shortcuts, a model manager, offline/PWA support, and an optional API for accessing more powerful models.
This article details how to set up a weather report on a Home Assistant dashboard using a local LLM (Ollama) for more user-friendly summaries and clothing suggestions, avoiding cloud-based services for privacy reasons. It covers the setup process, prompt engineering, and hardware considerations.
