Viaducta Documentation

Appearance

Providers and setup ​

You bring the model. The assistant works with Microsoft Foundry (Azure OpenAI) or with any server that offers an OpenAI-compatible chat completions API: vLLM, Ollama and similar servers, in the cloud or on your own GPUs. Your prompts, flows and attachments go only to the provider you configure, and the tokens are billed by that provider.

Configure the provider ​

The administrator sets the ViaductaAI section of the Manager's configuration.

json
"ViaductaAI": {
  "IsActive": true,
  "Provider": "Foundry",
  "Endpoint": "https://<resource>.openai.azure.com/openai/v1",
  "ApiKey": "<key>"
}
json
"ViaductaAI": {
  "IsActive": true,
  "Provider": "Vllm",
  "Model": "oAI_Compatible",
  "Endpoint": "http://gpu-server:8000/v1",
  "ApiKey": "<key, if the server needs one>",
  "VllmModelName": "Qwen/Qwen3-32B"
}
KeyMeaning
IsActivefalse turns the assistant off: the Viaducta AI menu, code suggestions and the agent tools for external agents disappear.
ProviderFoundry or Vllm (any OpenAI-compatible endpoint).
Endpoint, ApiKeyWhere the provider is reached and its key.
UseEntraId, EntraScopeFoundry only: sign in with the Manager's Microsoft Entra ID identity instead of a key.
VllmModelNameThe model (or Foundry deployment) everyone uses. Leave it empty to let each user choose.
EffortDefault reasoning effort: none, low, medium, high or extrahigh.
MaxContextTokensThe model's context window; chats are summarised at 70% of it. 0 turns that off.
SupportsVisionWhether the model reads images. On by default for Foundry, off for OpenAI-compatible servers.
ProductionEnvironmentPatternA regular expression for the names of production environments, where every change needs approval. Default prod.
PricingInputPerMillion, CachedInputPerMillion, OutputPerMillion and Currency, to show the cost of chats.
CompletionA separate Provider, Endpoint, ApiKey and ModelName for code suggestions in the script editors. Empty values use the main settings.

Choose the model ​

Each user picks the model in Settings › Viaducta AI: the Model (listed from the Foundry deployments or the server's model list), the Reasoning effort, the Context window, whether The model understands images, and the Code completion model. A new model applies to chats started after saving.

When the administrator sets VllmModelName, the model is fixed for everyone and the dialog shows The model is set by the administrator. With Entra ID sign-in the deployments can't be listed, so set VllmModelName there.

Where the assistant's data is kept ​

Chats, memory, skills, attachments and usage are stored on the Manager, one store per environment, with a nightly backup (seven kept by default). Administrators manage backups, retention and per-person purges on the Admin tab of the assistant.

Viaducta documentation