open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 4 Activity

refactor(examples): replace sector-specific example material with generic, fictitious examples

Browse source 
Reference files, test fixtures, the playground demo project and one design
document now use generic, fictitious examples (buildings, energy, water,
grants, municipal services). The playground demo (17 fixtures plus the
embedded demo state) tells one consistent story: a municipal customer
chatbot that pre-screens housing-benefit applications, classified under
Annex III point 5(a). The embedded demo copies were edited in place rather
than regenerated, because they already carry newer AI Act dates than the
fixture files.

Legal text is unchanged. Test semantics are unchanged. Four dark-theme
onboarding screenshots with outdated placeholder text are removed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-23 14:03:53 +02:00
commit 544934dc57
Signed by: ktg
SSH key fingerprint: SHA256:JakMjO6FTBBzN0Bhfj9saOoEjaFxlSdYuZQQpM/lF9Q
77 changed files with 363 additions and 368 deletions
Download patch file Download diff file Expand all files Collapse all files

18
skills/ms-ai-engineering/references/data-engineering/synthetic-data-generation.md
View file

@ -57,7 +57,7 @@ simulator = Simulator(model_config=model_config)
import wikipedia
# Hent kildedokument
wiki_page = wikipedia.page("Norwegian Public Roads Administration")
wiki_page = wikipedia.page("Norway")
source_text = wiki_page.summary[:5000]
# Generer syntetiske spørsmål-svar-par
@ -123,8 +123,8 @@ completion = (
# Lag prompts for syntetisk datagenerering
prompts_df = spark.createDataFrame([
("Generer en realistisk kundehenvendelse til Direktoratet for digital tjenesteutvikling om saksbehandling-fornyelse.",),
("Generer en syntetisk trafikkrapport for E6 ved Lillehammer med kødata.",),
("Generer en realistisk kundehenvendelse til Direktoratet for digital tjenesteutvikling om status på en tilskuddssøknad.",),
("Generer en syntetisk avviksrapport fra et kommunalt vannverk med måledata.",),
("Generer et eksempel på en byggesøknad til Plan- og bygningsetaten.",),
], ["prompt"])
@ -145,7 +145,7 @@ client = AzureOpenAI(
azure_endpoint="https://<endpoint>.openai.azure.com/"
)
def generate_synthetic_records(template_schema, num_records=100, domain="trafikk"):
def generate_synthetic_records(template_schema, num_records=100, domain="vannforsyning"):
"""Generer strukturerte syntetiske poster."""
records = []
for batch_start in range(0, num_records, 10):
@ -168,18 +168,18 @@ def generate_synthetic_records(template_schema, num_records=100, domain="trafikk
records.extend(batch["records"])
return records
# Eksempel: Trafikkhendelses-data
# Eksempel: Driftshendelses-data (vannforsyning)
schema = {
"incident_id": "string (UUID)",
"road": "string (E6, E18, Rv4, etc.)",
"location_km": "float",
"incident_type": "string (ulykke, køkjøring, veiarbeid, dyr_i_veien)",
"facility": "string (vannverk, pumpestasjon, høydebasseng, etc.)",
"network_km": "float",
"incident_type": "string (lekkasje, trykkfall, forurensning, pumpestans)",
"severity": "int (1-5)",
"timestamp": "ISO datetime",
"description": "string (norsk tekst, 1-3 setninger)"
}
synthetic_incidents = generate_synthetic_records(schema, num_records=500, domain="trafikk")
synthetic_incidents = generate_synthetic_records(schema, num_records=500, domain="vannforsyning")
```
---