Loom 0.7: When the Answer Is on Page 40 of a PDF
Loom 0.7 fixes its most annoying limit with long documents: instead of the first 8000 characters, the LLM now gets the passage that actually answers the question. Plus a loom_grep MCP tool for exact …
RAG
Explore all RAG articles on MAuToBlog: tech analysis, software development and artificial intelligence.
Loom: Hybrid BM25 + Embeddings Search, Multilingual, HTTP
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: Local LLM Memory with MCP Server and CLI, No Docker
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 Reinvented: Goodbye Gradio and ChromaDB, Hello Qdrant and Streaming
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: Multi-Format Support and an Advanced Interface for Your Local AI
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.
Doc Analyzer: The New Release - More Formats, More Flexibility
Discover Doc Analyzer’s new features: multi-format support, a modular architecture, and flexibility in choosing the language model.
Doc Analyzer: Privacy-First Document Analysis with DeepSeek R1
How to build a privacy-first document analysis system using DeepSeek R1 and RAG. A complete guide to the architecture, implementation, and deployment with Docker.
AI for Everyone: Advanced Techniques Made Simple (Part 4)
From Chain of Thought to RAG, discover how to get better reasoning and answers out of AI through practical examples and everyday analogies. Part four of our guide that makes AI understandable for …
AI for Everyone: Architectures and Artificial Brains (Part 3)
From neural networks to attention mechanisms, discover how the ‘brain’ of AI works through simple and fun analogies. Part three of our guide that makes AI understandable for everyone.