Tasmotizer: Try to Flash a WiFi LED Light with a Custom FirmwareMy IOT enabled home grows sensor by sensor. In one of the last articles, I explained which new devices I want to integrate: Power switches…4d ago4d ago
Tasmotizer: How to Flash a Sonoff S26R2 Power Switch with Custom Firmwaren your smart home, controlling and access sensors and devices is an essential capability. From a functional viewpoint, smart power switches…Feb 13Feb 13
Home Assistant: Overview about Smart Light and Smart Power ProtocolsIt started with a ESP8266 board and DHT11 temperature sensor to store data in a timeseries DB. And it evolved to a Home Assistant based…Feb 3Feb 3
Home Assistant and ESP Home: How to use MQTT Integration for Dynamic Device ConfigurationAn MQTT message broker is the standard way to transfer information between different IOT devices. Home Assistant has a powerful MQTT…Jan 23Jan 23
IOT: Dynamic Deep Sleep Configuration for ESP8266 and ESP32 BoardsEspecially when running your ESP boards on battery, conserving energy is an important aspect. ESPHome controlled boards can be configured…Jan 13Jan 13
Home Assistant: How to Fix API Disconnection and False Positive Sensor Readings with ESP8266 BoardsWhen using Home Assistant to integrate with ESPHome managed devices, connection timeouts can occur. Normally this means that the device…Jan 2Jan 2
InfluxDB: Optimize your Data with Data Retention Policies and Continuous QueriesInfluxDB is a time series database that you will find in the context of IOT projects. What makes these databases time-based is the simple…Dec 23, 2024Dec 23, 2024
Universal Personal Assistant with LLMsLarge Language Models are a unique emergent technology of 2024. Its fascinating capabilities to produce coherent text influences many areas…Dec 12, 2024Dec 12, 2024
LLM Evaluation: Which LLM to use for developing a personal assistant?In my blog series, I covered several aspects of LLMs: Understanding their evolution, investigating libraries, researching, and trying how…Dec 2, 2024Dec 2, 2024
Fine-Tuning LLMs: Comparison of Collab, Kaggle and 6 other PlatformsFine-Tuning and evaluating LLMs require significant hardware resources, mostly GPUs. Building an on-premise machine learning computer is…Nov 21, 2024Nov 21, 2024
Fine Tuning LLMs: Training with Cloud ResourcesFine-Tuning LLMs with 7B or more parameters require substantial hardware resources. One option is to build and on-premise computer with…Nov 11, 2024Nov 11, 2024
LLM GUI: Custom Python Gradio InterfaceWhen using Large Language Models (LLMs) via an API or locally, a quasi-standard for representing the chat history is recognizable: A list…Oct 31, 2024Oct 31, 2024
LLM Agents: Introduction to CrewAIAgent frameworks powered by LLMs promise to catapult autonomous task solving to unprecedented levels. Instead of rigid programming, LLMs…Oct 21, 2024Oct 21, 2024
LLM Agents: Multi-Agent Chats with AutogenAn agent is a Large Language Models customized with a system prompt so that it behaves in a specific way. The prompt typically details task…Oct 10, 2024Oct 10, 2024
LLM Agents: Custom Tools in AutogenLarge Language Models used as agents promise automatic task solution and to promote LLM usage to the next level. Effectively, an agent is…Sep 30, 2024Sep 30, 2024
LLM Agents: Introduction to AutogenIn my ongoing quest to design a question-answer system, agents are the final available design. An LLM agent is an instance of an LLM with a…Sep 23, 2024Sep 23, 2024
LangChain: Building a local Chat Agent with Custom Tools and Chat HistoryThe LangChain library spearheaded agent development with LLMs. When running an LLM in a continuous loop, and providing the capability to…Sep 16, 2024Sep 16, 2024
Advanced LangChain: Memory, Tools, AgentsLarge Language Models (LLMs) are complex neural networks of the transformer architecture with millions or billions of parameters. Trained…Sep 9, 2024Sep 9, 2024
Retrieval Augmented Generation Frameworks: AutoGenWith an Retrieval Augmented Generation (RAG) framework, documents relevant for a given user query can be extracted from a database and used…Sep 2, 20241Sep 2, 20241
Retrieval Augmented Generation Frameworks: HayStackLarge Language Models need accurate and up-to-date information when generating text for specific domains or with content from private data…Aug 26, 2024Aug 26, 2024