Welcome to Bob’s Handbuch

This is a collection of various ROS 2 packages and nodes for natural language processing, LLM integration, and system control. They leverage ROS topics to connect NLP and LLM components seamlessly.

Key Features:

  • LLM Integration: OpenAI-compatible API interface with stateful conversations and dynamic tool calling.

  • Speech Processing: Real-time Text-to-Speech (XTTS voice cloning) and offline Speech-to-Text.

  • Vision & VLM: Visual reasoning, captioning, and Q&A via Moondream2 Vision-Language Model.

  • Image Generation: High-quality Text-to-Image and Image-to-Image generation using Stable Diffusion 3.5 and FLUX.2 large and klein.

  • Vector Database: Semantic storage and multimodal retrieval using Chroma and Qdrant.

  • Voice Assistant: Real-time Whisper-based transcription with a pluggable output system.


Packages

OTHER

#.. toctree:: # :maxdepth: 2 # :caption: Miscellaneous

# bob/bob-docker-network.md # bob/bob-portainer.md