Skip to main content

LLM configuration

The LLM configuration connects an institute to a language model that generates exam questions and supports AI-assisted grading. There is one configuration per institute, and it is the only way to create questions for built-in SES exams.

Provider settings

FieldDescription
Provideropenai, azure_openai, mistral, anthropic, google or custom
ModelModel identifier (e.g. gpt-4o) or Azure deployment name
API keyEncrypted at rest; blank on edit keeps the existing key
Base URLAPI endpoint (auto-set for standard providers)
API versionRequired for Azure OpenAI only
Max tokensMaximum response tokens (default 4096)
Temperature0.00–9.99 (default 0.7)

Prompt settings

PromptPurpose
System promptInstructions for question generation
Negative promptThings the LLM must NOT do
Grading system promptInstructions for AI-assisted grading
Grading negative promptConstraints for AI grading

Starting a generation

  1. Open the Exam Assembly page of a SES exam
  2. Click Start AI generation
  3. Set Question count (5–100), a type mix, and a Bloom's-level distribution (each part must sum to 100%)
  4. Set a Language (nl, en, de, fr) and an optional Exam AI prompt
  5. Upload source documents (PDF, DOCX, PPTX or plain text)
  6. Save — generation runs in the background (watch it under Task status)
Keep the temperature low

For deterministic questions use a low temperature (0.7 or below). Higher values produce more varied but less predictable wording.

Background execution

Generation runs as a background task using Django's native task framework. You can monitor it under Administration → System → Task status.