Selbst gehostetes [Open Notebook](https://github.com/lfnovo/open-notebook) : - local Deployment per Docker Compose . - KI-gestützter Notiz-/Recherche-Assistent mit Chat, Quellenverwaltung und Podcast-Erstellung.
  • Python 44.9%
  • Shell 37.9%
  • Jinja 17.2%
Find a file
dschlueter 778f820e27 Document the num_ctx=8192 default that caused empty chat answers
esperanto's OllamaLanguageModel silently caps num_ctx at 8192 unless the
credential sets it explicitly, no matter what OLLAMA_CONTEXT_LENGTH or the
model's real context window is. Any chat context beyond that got truncated,
and because qwen3.5:27b is a thinking model, the truncated prompt usually
produced an empty final answer (swallowed by clean_thinking_content) rather
than a visible error - looked like "chat gives no answer" in the UI. Set
num_ctx=98304 on the Ollama chat credential: the largest value that still
keeps the whole model on GPU 1 (131072 spills onto CPU, 5-6x slower).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-10 23:28:12 +02:00
services Add voice cloning to the TTS wrapper, default to the owner's own voice sample 2026-07-10 22:38:03 +02:00
.env.example Initial setup: docker-compose for Open Notebook (SurrealDB + open_notebook), Ollama + OpenRouter as AI providers 2026-07-10 21:05:23 +02:00
.gitignore Add voice cloning to the TTS wrapper, default to the owner's own voice sample 2026-07-10 22:38:03 +02:00
CLAUDE.md Document the num_ctx=8192 default that caused empty chat answers 2026-07-10 23:28:12 +02:00
docker-compose.yml Initial setup: docker-compose for Open Notebook (SurrealDB + open_notebook), Ollama + OpenRouter as AI providers 2026-07-10 21:05:23 +02:00