# weaviate/Verba

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

Repository: https://github.com/weaviate/Verba
Canonical: https://ross.abutalabs.com/products/verba
Language: Python
License: BSD-3-Clause
License Family: permissive
Archived: true
Last push: 2026-06-08T09:25:18+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 86, release rhythm 16, longevity 80
- inputs: {"age_days": 1132, "days_push": 86, "days_rel": 415, "gap_med": 95, "n_releases_24m": 4}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7711, forks 853 (observed 2026-08-28T04:10:02.532966+00:00)

## What it is
Verba is an open-source end-to-end RAG application built on Weaviate, providing a user-friendly interface for ingesting data and chatting with it via LLMs like Ollama, OpenAI, Cohere, and Anthropic. The repository has been archived and is no longer maintained.

## Use cases
- build a chatbot over my own documents
- run a local RAG app with Ollama
- query my dataset with an LLM assistant
- set up retrieval augmented generation out of the box
- chat with PDFs using Weaviate
- self-host a question-answering assistant

## When to choose
- you want a ready-made RAG UI on top of Weaviate
- you want to fork a reference RAG implementation
- you need local-first RAG with Ollama/HuggingFace

## When to avoid
- you need active maintenance, security patches, or support
- you want a production-supported RAG stack
- you need features beyond what the archived code provides

## Facets
- artifact type: application
- maturity: abandoned
- function: rag, chatbot, search-engine, llm-inference
- domain: chatbots, large-language-models
- platform: python, self-hosted
- tags: weaviate, vector-search, ollama, openai, end-to-end-rag, retrieval-augmented-generation, docker, web-server

## Member repositories
- weaviate/Verba (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:02.532966+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:35:26.509018+00:00, confidence not recorded.
  - readme: https://github.com/weaviate/Verba (fetched 2026-08-28T04:10:02.532966+00:00, sha ffed964966f0)
- Data as of 2026-08-30T08:39:29.467469+00:00.