Verba

Hybrid (offline or cloud)

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.

RAG app
Free
BSD-3-Clause
4.2 / 5
GitHub ★ 7,500

Compatibility at a glance

Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"

§ Runtimes supported
ollamaopenai-compatanthropic
§ OS / platform
linuxmacoswindows
§ Hardware + model hint
Minimum VRAM
8 GB
Recommended starter model
Llama 3.1 8B + Weaviate embeddings

What it is

Verba is Weaviate's reference RAG app: ingestion → chunk → embed → store → retrieve → generate, with a clean React UI. The selling point is the opinionated stack — you don't pick a vector store, embedder, or chunking strategy, just point it at your data. Talks to Ollama, OpenAI, Cohere, Anthropic. Good for teams that want to ship internal-doc chat fast.

✓ Strengths

  • +Opinionated stack — fewer decisions
  • +Clean React UI with citation tracing
  • +Excellent default chunking + retrieval params

△ Caveats

  • Tied to Weaviate (or you do the swap yourself)
  • Less flexible than PrivateGPT if you want to swap components