Weaviate's open-source RAG demo turned production. Strong defaults, opinionated stack.
Editorial verdict: “Best for 'don't make me choose chunking strategy' teams. Opinionated stack works.”
Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"
Verba is for teams that want to ship an internal-doc chat app without debating chunking strategies or vector store choices. Point it at your data, pick an Ollama or OpenAI-compatible backend, and the opinionated pipeline handles ingestion, embedding, retrieval, and generation with sensible defaults. The React UI surfaces citation tracing out of the box, which makes it easier to trust answers. You'll need at least 8 GB VRAM for a Llama 3.1 8B model plus Weaviate embeddings. The tradeoff is that you're tied to Weaviate as the vector store — swapping it out requires manual work, so this isn't the right pick if you want to mix and match components freely.
Document retrieval + chat, fully offline-capable.
Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.
The full directory — filter by category, runtime, OS, privacy posture, or VRAM.
What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.
Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.