Show HN: RAG-TUI – Visual chunking debugger for RAG pipelines in the terminal
pypi.orgI built this because I was tired of guessing chunk_size=1000 and overlap=200 in my RAG pipelines and hoping for the best.
RAG-TUI is an open-source terminal tool that lets you visualize exactly how your text is being split before you index it. It helps you tune parameters in real-time and spot issues like sentences getting cut in half.
The Stack: Built with Textual (Python) for the TUI. Chonkie for token-based chunking. Usearch for local vector search. Integrates with Ollama for entirely local/private debugging (also supports OpenAI/Groq).
Key Features: Visual Feedback: See color-coded chunks and their overlap regions instantly. Quality Indicators: The UI flags "bad chunks" (e.g., for cuts mid-sentence, for clean breaks). Batch Testing: Run a set of queries against your current settings to calculate a "hit rate" before you deploy.
Export: Generates the Python code (LangChain/LlamaIndex) for your tuned config.
It’s currently in beta (v0.0.1). I’d love feedback on the chunking visualizations and what other metrics would be useful for debugging retrieval.
Repo: https://github.com/rasinmuhammed?tab=repositories PyPI: https://pypi.org/project/rag-tui/
No comments yet.