Explore all Ollama articles on MAuToBlog: tech analysis, software development and artificial intelligence.
Loom gets an upgrade: optional hybrid semantic search (BM25 + embeddings) arrives to handle the cases where keyword search alone falls short - paraphrases and multilingual queries. On top of that, …
Loom is an open source tool written in Go that turns your files into a memory layer LLMs can query. Inspired by Karpathy’s llm-wiki pattern, but with its own architecture: precomputed summaries, …
Doc Analyzer has undergone a radical transformation: out with Gradio and ChromaDB, in with Qdrant, LLM response streaming, a pure HTML/JS interface, multi-collection management with a Memory/Persist …
Doc Analyzer evolves with support for new file formats (TXT, RTF, code, Markdown and YAML), LLM model selection, and advanced context management, while keeping your data 100% safe and local.
QwQ-32B promises performance comparable to models 20 times its size, with support for local execution. Find out how this model with just 32 billion parameters can compete with giants like DeepSeek-R1, …
A complete, up-to-date guide to installing and configuring Open WebUI with Docker and Ollama (including Windows with WSL), turning your computer into a private AI workstation: a ChatGPT-style …
Discover Doc Analyzer’s new features: multi-format support, a modular architecture, and flexibility in choosing the language model.
The up-to-date guide to installing and using DeepSeek R1 on your Mac with Ollama: which model to pick for your RAM, context length, Zed integration and troubleshooting. No compromises on privacy and a …