Verba hosting
A ready-made RAG interface built on Weaviate.
Verba hosting at AIHostBox means a dedicated, single-tenant Verba instance on our infrastructure: we install it, pin it to a reviewed release, put it behind TLS on your domain, back it up nightly and patch everything around it. Plans start at $11.99 per month and the admin account, the data and any API keys are yours.
Weaviate archived the Verba repository on 8 June 2026. There will be no new features and no upstream bug or security fixes.
We still host it for teams who depend on it: we keep the instance running, backed up and behind TLS, and patch the operating system and the services around it. We cannot fix bugs or vulnerabilities inside Verba itself, and there will be no feature updates. Order it only if you accept that; if you are starting fresh, the alternatives below are the safer choice.
Verba, nicknamed the Golden RAGtriever, is the retrieval-augmented chat application written by the Weaviate team as a reference for building on their database. Its interface covers the whole pipeline: readers for PDF, DOCX, CSV and spreadsheets, GitHub and GitLab repositories, chunkers from token and sentence to semantic, Markdown, code and JSON, a choice of embedders, and a chat view that shows which chunks an answer came from. Retrieval uses Weaviate’s hybrid search, so keyword and vector matches are combined without extra setup.
Every stage is switchable from the browser, which makes it useful for comparing retrieval settings without writing code. Upstream archived the repository in June 2026, so Verba is now a finished reference application rather than a moving project. Hosting it next to a persistent Weaviate means your imported corpus and chosen configuration survive restarts and can be reached by anyone you give the address to. That is often all a proof of concept needs before a team commits to a heavier platform.
Verba hosting plans
Every plan is a dedicated single-tenant instance with NVMe storage, nightly off-box backups, TLS and managed patching. Quarterly, semi-annual and annual terms are discounted at checkout. Model tokens are not included — you bring your own key.
How we run Verba
Two containers from the official compose file: the Verba FastAPI and Next.js app on port 8000, and a Weaviate database with its data on a persistent volume.
What we configure for you
- WEAVIATE_URL_VERBA pointing at the private Weaviate container
- OPENAI_API_KEY, COHERE_API_KEY, ANTHROPIC_API_KEY or GROQ_API_KEY as you choose
- OLLAMA_URL, OLLAMA_MODEL and OLLAMA_EMBED_MODEL for a local model plan
- GITHUB_TOKEN or GITLAB_TOKEN for private repository imports
- UNSTRUCTURED_API_KEY or FIRECRAWL_API_KEY if you use those readers
Which plan fits
Plus (4 GB) runs Verba and Weaviate for a corpus of a few thousand documents embedded through an API. Pro (8 GB) is the choice for larger imports, the SentenceTransformers embedder running locally, or several people querying at once.
The honest limits
Verba is archived upstream and has no authentication of its own. Local SentenceTransformers embedding on CPU is slow for large imports; an embedding API is faster.
What people run Verba for
Evaluate retrieval settings
Change chunking and embeddings and see the effect immediately.
Demo a RAG stack
A presentable interface without building one.
Code and repository Q&A
Import a GitHub or GitLab repository and ask questions about it with the source files shown.
Licence and version policy
| Item | Position |
|---|---|
| Upstream licence | BSD-3-Clause |
| Sold as managed hosting | Yes |
| Tenancy | Single tenant — one customer per instance |
| Patching | Critical advisories within 24 hours, high severity within 72 |
Our full position on licences, including the applications we decline to sell, is on the licensing page.
Works well with Verba
Weaviate
A vector database with hybrid search and built-in vectorization modules.
from $11.99/moDetails →
Ollama
Your private LLM server — pull a model, get an API, keep every token on your own box.
from $16.99/moDetails →
AnythingLLM
A private document workspace — drop files in, ask questions, get cited answers.
from $18.99/moDetails →More Agents & RAG we host
Dify
A visual studio for building LLM apps, agents and RAG pipelines.
from $18.99/moDetails →
Flowise
Drag-and-drop LLM flows, agents and chatbots you can embed anywhere.
from $11.99/moDetails →
Langflow
A visual builder for LangChain flows and multi-agent systems.
from $11.99/moDetails →
RAGFlow
Deep document understanding for RAG — tables, layouts and scanned pages.
from $36.99/moDetails →Verba hosting: your questions
Is Verba still maintained?
Which models and embedders can Verba use?
Where are my documents stored?
Does Verba have user accounts?
Can I connect Verba to an existing Weaviate?
Run Verba without running a server
A dedicated Verba instance, deployed and maintained by us. Month to month, cancel whenever.