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

chore(ms-ai-architect): refresh KB medium-bucket — 74 files [skip-docs]

Browse source 
KB-currency refresh (medium priority, 2026-06-19) via /architect:kb-update.
74 medium-prioritets filer re-verifisert mot Microsoft Learn (MCP) — delegert
til 15 parallelle Opus-subagenter (3 bølger) gruppert etter delt kilde, med
disjunkte fil-sett. Verifisert i hovedkontekst (scope-sjekk + diff-review av
de faktatunge gruppene + tester).

Hovedendringer (faktuelle korreksjoner + currency):
- Azure AI Search semantic ranker: TILGJENGELIG PÅ ALLE TIERS (også Free/Basic
  m/ gratis månedlig kvote) — gammel KB sa feilaktig "kun S1+". Korrigert i
  tier-tabell, anti-patterns og beslutningstabell (azure-ai-search-setup).
- APIM score-threshold = DISTANSE (lavere = strengere): tuning-tabellen i
  rag-caching-optimization hadde retningen baklengs — invertert til korrekt.
- Agentic retrieval GA/preview-nyanse presisert (hovedkontekst-korreksjon mot
  agentic-retrieval-how-to-migrate): GA via REST 2026-04-01 returnerer EKSTRAKTIV
  grounding (references + activity), IKKE syntetiserte svar. Answer synthesis,
  ikke-minimal reasoning effort (LLM query planning) og multi-turn messages
  forblir preview (2026-05-01-preview). Subagent hadde overforenklet til "hele
  kjernepipelinen GA"; rettet i agentic-rag-patterns + citation-tracking.
- Copilot Studio modell-tabeller (platforms/copilot-studio): fjernet Claude Opus
  4.5 + GPT-5.2 (borte fra kilde), lagt til Claude Sonnet 4.6/Opus 4.6 (GA),
  Opus 4.7 + Mistral Medium 3.5 (experimental); GPT-5 Reasoning/Auto = preview;
  A2A GA (apr 2026).
- Computer Use (CUA): Copilot Studio GA 2026-05-07; 4 modeller m/ tier/status
  (OpenAI CUA + Sonnet 4.5 GA, Sonnet 4.6 + Opus 4.6 experimental); 5 credits/
  steg standard, 15 premium; US-only region-krav FJERNET i GA-dok; Cloud PC pool
  + Hosted browser + bring-your-own-machine.
- Azure AI Search REST API-versjoner bumpet: 2025-09-01 -> 2026-04-01 (stabil),
  2025-11-01-preview -> 2026-05-01-preview (hybrid-search, rag-security-rbac,
  chunking).
- Power Automate-integrasjon: trigger "Run a flow from Copilot" -> "When an agent
  calls the flow"; App Service innebygd MCP (preview) lagt til.
- M365 Copilot-manifest v1.26 -> v1.28 (GA, mai) / v1.29 dokumentert (juni);
  "Tenant graph grounding" -> "Work IQ".
- Speech fast transcription 2t/300MB -> 5t/500MB; multilingual 14 -> 15 locales
  (+ pt-BR). Content Understanding reasoning preview -> GA (v1.0, 2025-11-01).
- Security Copilot E5 -> E5+E7. Død Databricks-URL ci-cd/best-practices ->
  ci-cd/flows. Prompt Flow retirement (2027-04-20 -> MAF) notert der den
  presenteres som go-forward. Gateway-topologi-tabell-feil rettet.
- Alle 74 Last updated -> 2026-06-19.

Discovery ikke kjørt (historisk kun Databricks-støy) -> 389-telling uendret,
ingen resync. validate 239 PASS, kb-integrity 115/115 (262 orphan-warnings
uendret), gitleaks clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
This commit is contained in:
Kjell Tore Guttormsen 2026-06-19 14:02:18 +02:00
commit 070141f06b
74 changed files with 403 additions and 384 deletions
Download patch file Download diff file Expand all files Collapse all files

13
skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md
View file

@ -1,6 +1,6 @@
# Document Preprocessing and Pipeline Automation
**Last updated:** 2026-04 | Verified: MCP 2026-04
**Last updated:** 2026-06-19 | Verified: MCP 2026-06-19
**Status:** GA
**Category:** RAG Architecture & Semantic Search
@ -64,7 +64,8 @@ Skillsets definerer AI-berikning og transformasjoner som skal utføres på dokum
| **OCR Skill** | Innebygd | Tekstgjenkjenning fra bilder i dokumenter |
| **Document Extraction Skill** | Innebygd | Ekstraherer tekst og bilder fra embedded content (PDF, DOCX) |
| **Text Merge Skill** | Innebygd | Slår sammen OCR-output med eksisterende tekst |
| **Text Split Skill** | Innebygd | Chunker tekst basert på størrelse eller semantic boundaries |
| **Text Split Skill** | Innebygd | Chunker tekst i setninger/sider av en gitt lengde (størrelsesbasert) |
| **Azure Content Understanding Skill** | Innebygd | Semantisk, layout-bevisst chunking som respekterer avsnittsgrenser (alternativ til Text Split for integrated vectorization) |
| **Document Intelligence Layout Skill** | Innebygd | Kjører Layout-modellen for strukturutvinning |
| **Language Detection Skill** | Innebygd | Detekterer språk for språkspesifikk behandling |
| **Custom Skills** | Egendefinert | Azure Functions eller web service for custom logic |
@ -738,9 +739,9 @@ Images (JPEG/PNG)?
|------|-----|-----------|
| Indexer overview | https://learn.microsoft.com/en-us/azure/search/search-indexer-overview | Verified (2026-02) |
| Document Intelligence RAG | https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept/retrieval-augmented-generation | Verified (2026-02) |
| Skillset concepts | https://learn.microsoft.com/en-us/azure/search/cognitive-search-concept-intro | Verified (2026-02) |
| Skillset concepts | https://learn.microsoft.com/en-us/azure/search/cognitive-search-concept-intro | Verified (2026-06-19) |
| Image scenarios | https://learn.microsoft.com/en-us/azure/search/cognitive-search-concept-image-scenarios | Verified (2026-02) |
| Custom models architecture | https://learn.microsoft.com/en-us/azure/architecture/ai-ml/architecture/build-deploy-custom-models | Verified (2026-02) |
| Custom models architecture | https://learn.microsoft.com/en-us/azure/architecture/ai-ml/architecture/build-deploy-custom-models | Verified (2026-06-19) |
| Batch Functions OCR | https://learn.microsoft.com/en-us/azure/batch/tutorial-batch-functions | Verified (2026-02) |
### Kodeeksempler (Verified)
@ -749,7 +750,7 @@ Images (JPEG/PNG)?
|----------|-------|-------|-----------|
| Skillset med OCR og embedding | HTTP/JSON | https://learn.microsoft.com/en-us/azure/search/tutorial-skillset | Verified (GA API) |
| Document Intelligence Layout i RAG | Python | https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/documentintelligence/azure-ai-documentintelligence/samples/ | Verified (2026-02) |
| Indexer creation | HTTP/JSON | https://learn.microsoft.com/en-us/azure/search/search-how-to-integrated-vectorization | Verified (2025-09-01 API) |
| Indexer creation | HTTP/JSON | https://learn.microsoft.com/en-us/azure/search/search-how-to-integrated-vectorization | Verified (2026-04-01 API, 2026-06-19) |
| LangChain integration | Python | https://github.com/microsoft/Form-Recognizer-Toolkit/blob/main/SampleCode/Python/sample_rag_langchain.ipynb | Verified (2026-02) |
### Norske forhold (Baseline)
@ -778,7 +779,7 @@ Images (JPEG/PNG)?
**Konfidensnivå totalt:** 95% Verified (fra MCP), 5% Baseline (norske forhold og priser)
### Kognitiv søk — bildeprosessering (oppdatert 2026-04)
### Kognitiv søk — bildeprosessering (oppdatert 2026-06-19)
Azure AI Search støtter tre tilnærminger til bildeinnhold i RAG:
1. **Vektorisering** — Azure Vision genererer bildere presentasjoner som søkbare vektorer