Search and assistants
Operate Onyx and background services on controlled versions.
WZ-IT uses Onyx to build a searchable knowledge platform, connects approved sources and designs models, permissions and operations as one system.
The following are trademarks of their respective owners: Onyx (Onyx project contributors). WZ-IT is an independent service provider and has no business, partnership, or contractual relationship with these companies. We offer independent migration, installation, hosting, and operations services.
Onyx can index content from collaboration, file, ticket and knowledge systems and use it in search or AI answers. Quality and access protection depend on connectors and permissions.
We start with representative sources, define synchronisation and the ACL model and test answers against concrete business questions.
Source volume, change rate, file formats, API limits and permissions vary by organisation. We therefore size and price Onyx after a data and permission assessment.
Granular permission controls or other enterprise requirements may depend on the deployed edition and are reviewed in advance.
Connectors, indexing, permissions, models and source systems must be designed and monitored together.
Operate Onyx and background services on controlled versions.
Connect approved file, wiki, ticket and collaboration systems.
Process content, metadata, embeddings and source ACLs consistently.
Monitor sync, freshness, errors, search quality and resources.
WZ-IT operates and integrates the platform; source approval and business validation remain shared or customer-owned.
| Area | Responsibility | Scope and boundaries |
|---|---|---|
| Onyx platform | WZ-IT | Deployment, databases, index services, proxy, monitoring and updates. |
| Connectors and sync | WZ-IT | Technical setup, secrets, schedules and error monitoring. |
| Sources and permissions | Shared | We map supported ACLs; the customer approves systems and groups. |
| Models and retrieval | Shared | Configuration is evaluated with representative documents and questions. |
| Content and approval | Customer | The customer owns data quality, retention and responsible use. |
| Custom connectors | Optional WZ-IT service | Missing sources and downstream workflows are developed separately. |
Make approved content from multiple systems discoverable through a shared search interface.
Configure available connectors for file, knowledge, ticket and collaboration systems in a controlled way.
Use retrieved content as context for internal assistants and traceable answers.
Model source permissions and user groups depending on connector, edition and target architecture.
Connect local or approved external models according to data class, quality and load.
Assess search results, source coverage and business answers with defined test questions.
Assess existing data and configuration, migrate them in a test run and move to managed operations through a controlled cutover.
Secure SSO, roles, administrative paths and external access for the application and existing infrastructure.
Back up all stateful components consistently and document the recovery path for the agreed scope.
Monitor and update the application and its technical dependencies and operate them under the agreed service level.
A clearly defined operating scope instead of an opaque hosting flat fee.
We set up a test instance for you, usually on the next business day. No payment details required. After seven days it is deleted unless you continue.
We combine the right compute size with ongoing operations, backups, monitoring and a service level appropriate for the criticality of Onyx. High availability and recovery targets are designed separately where needed.
We also design custom hosting architectures, integrations and migrations around Onyx. Contact us for a technical assessment.
One managed standard Onyx application is included in the Starter workload. Business and higher levels add a flexible operations allowance for planned work during regular service hours. Select compute, additional applications, storage and the appropriate service level.
A workload is one compute instance with the applications agreed for it.
One standard app per workload is already included. Additional dedicated servers count as separate workloads.
€79.90 per started TB and month, including daily encrypted offsite backup with 7-day retention.
Enquiry
Briefly describe the current state and objective for Onyx. We assess infrastructure, integration, and ongoing operations.
Initial ingestion, change rate, formats, ACLs and concurrent search determine capacity.
| Usage scenario | Technical starting point | Key factors |
|---|---|---|
| Pilot with a few sources | Assessment and test corpus | Connectors, access and answer quality are tested. |
| Several teams and systems | Dedicated platform | Index, workers and storage follow volume and update rate. |
| Local models | GPU and model assessment | Model, context and concurrency determine inference. |
| Enterprise-wide search | Scaling and recovery design | Connector load, availability and index rebuild are planned. |
Edition, connectors, volume, permissions and model architecture are reviewed before a binding proposal.
Platform, models and sources can be placed together or separately.
Dedicated European platform connected to approved sources.
Deployment close to existing data and identity services.
Search, index and optional models inside your network.
Local sources with controlled search or model endpoints.
Every source receives a documented sync, permission and deletion path.
Search, chat and approved assistants.
TLS, SSO, groups and restricted administration.
Supported ACLs are transferred into search.
Connectors, indexing, retrieval, search and AI answers.
Files, wikis, tickets and approved systems.
Extracted content, embeddings, ACLs and sync state.
Embedding, reranking and answer models with measurable quality.
A connector does not guarantee complete ACL parity; concrete permission behaviour is tested before rollout.
Answers about connectors, permissions, models and operations.
Onyx supports common file, wiki, ticket and collaboration systems. Version, edition and authentication are checked per source.
That depends on the connector. We test ACL sync and results with several roles before rollout.
Yes. We can connect approved local or external endpoints and document data paths.
Connectors, document volume, indexing, model operation and permissions vary significantly.
Yes. API, data model, change handling and permissions are scoped as integration work.
As an alternative to managed hosting in the data centre, WZ-IT provides the hardware, configures Onyx, and handles hardening, monitoring, updates, backup and technical support. Access can be limited to the internal network or enabled through VPN and existing identities.
from EUR 349 excl. VAT / month · plus one-time provisioning and initial setup

08.11.2025
The use of Large Language Models (LLMs) such as GPT-4, Claude or Llama has evolved from experimental applications to mission-critical tools in recent years. However,...
09.11.2025
Local AI inference means running a language or multimodal model on owned hardware rather than through a public API. Organisations gain control over data paths,...
24.11.2025
OpenAI released GPT-OSS 120B as an open-weight reasoning model on 5 August 2025. Its native MXFP4 quantisation allows OpenAI to position the model for a...
These solutions are often used together with Onyx
These solutions offer similar functionalities and can be evaluated together
These solutions are direct alternatives with similar use cases
No risk: worst case, you leave with a clearer understanding of your project than before.


“WZ-IT's advice on our Azure migration was technically sound and completely non-binding right from the intro call - we took away a great deal.”
Whether a specific IT challenge or just an idea - we look forward to the exchange. In a brief conversation, we'll evaluate together if and how your project fits with WZ-IT.