Update TODO after compose stack and rename

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

CLAUDE.md

@@ -40,13 +40,13 @@ server/<hostname>/          # Host-specific docs, scripts, files
 
 ## Servers
 
-| Hostname         | IP            | Status                          |
+| Hostname         | IP            | Status                             |
-| ---------------- | ------------- | ------------------------------- |
+| ---------------- | ------------- | ---------------------------------- |
-| phy-z-srv-jira   | 192.168.66.41 | configured                      |
+| phy-z-srv-jira   | 192.168.66.41 | configured                         |
-| phy-z-srv-cloud  | 192.168.66.66 | configured (Nextcloud)          |
+| phy-z-srv-cloud  | 192.168.66.66 | configured (Nextcloud)             |
-| phy-z-srv-git    | 192.168.66.67 | configured                      |
+| phy-z-srv-git    | 192.168.66.67 | configured                         |
-| phy-z-dmz-sftp01 | 192.168.99.68 | configured                      |
+| phy-z-dmz-sftp01 | 192.168.99.68 | configured                         |
-| phy-z-srv-gpu01  | 192.168.66.69 | planned — setup is the next task|
+| phy-srv-gpu01    | 192.168.66.69 | in setup — base + GPU driver done  |
 
 ## Conventions
 

SETUP.md

@@ -10,7 +10,7 @@ Document all the steps done for the initial generic setup of the server.
 - [x] Document Server in IT-Glue configurations with all infos: IP address, SN, MAC, Hostname, Set as 'planned', ... 
 - [x] Document iLO of the Server in IT-Glue configurations: IP address, SN, MAC, Hostname, ....
 - [x] Document iLO license in TI-Glue under 'Licensing'
-- [x] Label physical server: `phy-z-srv-gpu01`
+- [x] Label physical server: `phy-srv-gpu01`
 - [x] iLO setup: Hostname, snmp (v1 disable, configure v3), license was already inserted, 
 - [x] RAID setup of server in BIOS
 - [ ] OS Install 

TODO.md

@@ -1,8 +1,8 @@
 # TODO
 
-## phy-z-srv-gpu01
+## phy-srv-gpu01
 
-Per [projektplan](server/phy-z-srv-gpu01/notes/20260710-projektplan.md) (§ references below).
+Per [projektplan](server/phy-srv-gpu01/notes/20260710-projektplan.md) (§ references below).
 Server is delivered; base setup + NVIDIA driver are done (see `SETUP.md`).
 
 ### Blocking the knowledge base (customer conversation)
@@ -22,21 +22,24 @@ Server is delivered; base setup + NVIDIA driver are done (see `SETUP.md`).
 
 ### Server / Ansible
 
+- [ ] Add the three secrets to `group_vars/secrets.yml` (`just vault edit`):
+      `vault_owui_secret_key`, `vault_owui_db_password`, `vault_ldap_bind_password`
+- [ ] Fill the real LDAP bind DN / base DN in `group_vars/phy_srv_gpu01.yml`
+- [ ] Pin `vllm_image` to a build verified on SM120, then `just compose phy_srv_gpu01`
+      and start the stack manually (see `ansible/services/phy-srv-gpu01/README.md`)
 - [ ] Role `cifs_mounts` — read-only mounts, credentials from `group_vars/secrets.yml`
-- [ ] Role `llm_stack` — docker compose: vLLM (fixed `--gpu-memory-utilization`),
+- [ ] oikb sync (share → knowledge base) once the corpus scope is decided
-      embedding server, Open WebUI + pgvector, reverse proxy, oikb timer.
-      Tag compose tasks with `compose` so `just compose` works.
 - [ ] Smoke-test a vLLM container on the server (official images may not support SM120)
       — pin the working image, then build `llm_stack`. Start model: Qwen3-32B FP8
 - [ ] OCR pipeline for ~166k scanned PDFs (§2.1) — own work block, competes with vLLM for the GPU
 - [ ] TLS: currently plain HTTP on `chat.phytron.local`; retrofit an internal CA
       certificate (AD passwords travel in clear text until then)
-- [ ] Hostname mismatch: server reports `phy-srv-gpu01`, repo/inventory/label use
+- [ ] Finish base hardening in `SETUP.md` (ssh, updates) via `just run phy_srv_gpu01`
-      `phy-z-srv-gpu01` — align
-- [ ] Finish base hardening in `SETUP.md` (ssh, updates) via `just run phy_z_srv_gpu01`
 
 ### Done
 
+- [x] Renamed host/group/folder to `phy-srv-gpu01` everywhere
+- [x] LLM compose stack written (`ansible/services/phy-srv-gpu01/`) — not deployed
 - [x] Share analysis script → `scripts/share-analysis.ps1`, run on 2026-07-14 (§2.1)
 - [x] Storage decision (§2.3) — 876 GB usable, no extra disks needed
 - [x] NVIDIA driver via role `nvidia_gpu` (595 open kernel modules)

ansible/group_vars/phy_srv_gpu01.yml

@@ -0,0 +1,41 @@
+---
+# overrides of group_vars/all.yml
+
+hostname: phy-srv-gpu01
+
+# geerlingguy.docker
+docker_users:
+  - "{{ main_username }}"
+
+# ironicbadger.docker_compose_generator
+# services/<docker_compose_hostname>/NN-<stack>/compose.yml next to run.yml
+appdata_path: "/home/{{ main_username }}/appdata"
+docker_compose_generator_output_path: "/home/{{ main_username }}/docker/"
+docker_compose_hostname: phy-srv-gpu01
+docker_compose_generator_uid: "{{ main_uid }}"
+docker_compose_generator_gid: "{{ main_gid }}"
+
+# --- LLM stack -------------------------------------------------------------
+llm_dns_name: chat.phytron.local
+
+# ⚠️ TODO: pin to a build verified on SM120 (Blackwell) before the first deploy
+vllm_image: vllm/vllm-openai:latest
+vllm_model: Qwen/Qwen3-32B-FP8
+vllm_served_model_name: qwen3-32b
+vllm_gpu_memory_utilization: "0.80"
+vllm_max_model_len: "32768"
+
+embedding_model: BAAI/bge-m3
+embedding_model_name: bge-m3
+embeddings_gpu_memory_utilization: "0.10"
+
+openwebui_image: ghcr.io/open-webui/open-webui:main
+pgvector_image: pgvector/pgvector:pg16
+
+# --- AD/LDAP ---------------------------------------------------------------
+# ⚠️ TODO: real bind DN / base DN from the customer; group llm_users is agreed
+ldap_server_host: dc.phytron.local
+ldap_server_port: "389"
+ldap_bind_dn: "CN=svc-llm,OU=Service,DC=phytron,DC=local"
+ldap_search_base: "DC=phytron,DC=local"
+ldap_search_filter: "(&(objectClass=user)(memberOf=CN=llm_users,OU=Groups,DC=phytron,DC=local))"

ansible/group_vars/phy_z_srv_gpu01.yml

@@ -1,2 +0,0 @@
----
-

ansible/hosts.ini

@@ -10,5 +10,5 @@ phy-z-srv-git ansible_host=192.168.66.67
 [phy_z_dmz_sftp01]
 phy-z-dmz-sftp01 ansible_host=192.168.99.68
 
-[phy_z_srv_gpu01]
+[phy_srv_gpu01]
-phy-z-srv-gpu01 ansible_host=192.168.66.69
+phy-srv-gpu01 ansible_host=192.168.66.69

ansible/requirements.yml

@@ -1,4 +1,7 @@
 ---
+# docker_compose_generator MUST stay pinned — its galaxy tags mix formats
+# (1.0.x uses a `containers:` data structure, 2.x uses native compose files)
+# and an unpinned install can silently change the expected layout.
 roles:
   #- name: geerlingguy.pip
   - name: geerlingguy.docker
@@ -6,3 +9,4 @@ roles:
   - name: geerlingguy.security
   - name: geerlingguy.ntp
   - name: ironicbadger.docker_compose_generator
+    version: 2.0.1

ansible/roles/nvidia_gpu/tasks/main.yml

@@ -1,5 +1,5 @@
 ---
-# Automates server/phy-z-srv-gpu01/manuals/20260714-nvidia-driver-install.md
+# Automates server/phy-srv-gpu01/manuals/20260714-nvidia-driver-install.md
 # Requires Docker (geerlingguy.docker) for the container toolkit part.
 
 - name: Check Secure Boot state

ansible/run.yml

@@ -69,7 +69,7 @@
       tags: base
 
 
-- hosts: phy_z_srv_gpu01
+- hosts: phy_srv_gpu01
   become: yes
   vars_files:
     - "group_vars/secrets.yml"
@@ -88,3 +88,8 @@
       tags: docker
     - role: nvidia_gpu
       tags: gpu
+    # renders services/phy-srv-gpu01/*/compose.yml into ~/docker/compose.yaml.
+    # It only WRITES the file — starting the stack stays a deliberate manual
+    # step (see ansible/services/phy-srv-gpu01/README.md).
+    - role: ironicbadger.docker_compose_generator
+      tags: compose

ansible/services/phy-srv-gpu01/01-vllm/compose.yml

@@ -0,0 +1,36 @@
+services:
+  vllm:
+    image: "{{ vllm_image }}"
+    container_name: vllm
+    networks:
+      - llmnet
+    ports:
+      - "8000:8000"
+    volumes:
+      # model cache on local disk — tens of GB per model
+      - "{{ appdata_path }}/models/huggingface:/root/.cache/huggingface"
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all
+      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
+      - "HUGGING_FACE_HUB_TOKEN={{ hf_token | default('') }}"
+    command:
+      - --model
+      - "{{ vllm_model }}"
+      - --served-model-name
+      - "{{ vllm_served_model_name }}"
+      # fixed VRAM share so the embedding server keeps its slice (§0: "it just works")
+      - --gpu-memory-utilization
+      - "{{ vllm_gpu_memory_utilization }}"
+      - --max-model-len
+      - "{{ vllm_max_model_len }}"
+    # vLLM needs a large shared-memory segment; without this it dies on startup
+    ipc: host
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    runtime: nvidia
+    restart: unless-stopped

ansible/services/phy-srv-gpu01/02-embeddings/compose.yml

@@ -0,0 +1,37 @@
+services:
+  # Embeddings run on a second vLLM instance rather than a separate toolchain
+  # (e.g. text-embeddings-inference): whatever vLLM build works on SM120 then
+  # covers embeddings too, instead of having to solve Blackwell support twice.
+  embeddings:
+    image: "{{ vllm_image }}"
+    container_name: embeddings
+    networks:
+      - llmnet
+    ports:
+      - "8001:8000"
+    volumes:
+      - "{{ appdata_path }}/models/huggingface:/root/.cache/huggingface"
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all
+      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
+      - "HUGGING_FACE_HUB_TOKEN={{ hf_token | default('') }}"
+    command:
+      - --model
+      - "{{ embedding_model }}"
+      - --served-model-name
+      - "{{ embedding_model_name }}"
+      - --task
+      - embed
+      # small fixed slice — the chat model gets the rest
+      - --gpu-memory-utilization
+      - "{{ embeddings_gpu_memory_utilization }}"
+    ipc: host
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    runtime: nvidia
+    restart: unless-stopped

ansible/services/phy-srv-gpu01/03-openwebui/compose.yml

@@ -0,0 +1,62 @@
+services:
+  openwebui:
+    image: "{{ openwebui_image }}"
+    container_name: openwebui
+    networks:
+      - llmnet
+    ports:
+      # plain HTTP for now — no TLS yet (projektplan §2.2). Put a reverse proxy
+      # in front (new stack 04-proxy) once an internal CA certificate exists.
+      - "80:8080"
+    depends_on:
+      - vllm
+      - owui-db
+    volumes:
+      - "{{ appdata_path }}/apps/open-webui:/app/backend/data"
+    environment:
+      - "WEBUI_URL=http://{{ llm_dns_name }}"
+      - "WEBUI_SECRET_KEY={{ vault_owui_secret_key }}"
+
+      # --- inference: vLLM speaks the OpenAI API, Ollama stays off ---
+      - OPENAI_API_BASE_URL=http://vllm:8000/v1
+      - OPENAI_API_KEY=dummy
+      - ENABLE_OLLAMA_API=false
+
+      # --- vector store: pgvector rather than the default chroma, which does
+      #     not scale to the corpus sizes discussed in §2.6 ---
+      - VECTOR_DB=pgvector
+      - "PGVECTOR_DB_URL=postgresql://openwebui:{{ vault_owui_db_password }}@owui-db:5432/openwebui"
+
+      # --- RAG embeddings from the second vLLM instance ---
+      - RAG_EMBEDDING_ENGINE=openai
+      - RAG_OPENAI_API_BASE_URL=http://embeddings:8000/v1
+      - RAG_OPENAI_API_KEY=dummy
+      - "RAG_EMBEDDING_MODEL={{ embedding_model_name }}"
+
+      # --- AD/LDAP login (group llm_users) ---
+      # NOTE: verify these variable names against the Open WebUI docs for the
+      # tag actually deployed — they have changed between releases.
+      - ENABLE_LDAP=true
+      - LDAP_SERVER_LABEL=Phytron AD
+      - "LDAP_SERVER_HOST={{ ldap_server_host }}"
+      - "LDAP_SERVER_PORT={{ ldap_server_port }}"
+      - "LDAP_APP_DN={{ ldap_bind_dn }}"
+      - "LDAP_APP_PASSWORD={{ vault_ldap_bind_password }}"
+      - "LDAP_SEARCH_BASE={{ ldap_search_base }}"
+      - "LDAP_SEARCH_FILTER={{ ldap_search_filter }}"
+      - LDAP_ATTRIBUTE_FOR_USERNAME=sAMAccountName
+      - LDAP_USE_TLS=false
+    restart: unless-stopped
+
+  owui-db:
+    image: "{{ pgvector_image }}"
+    container_name: owui-db
+    networks:
+      - llmnet
+    volumes:
+      - "{{ appdata_path }}/databases/openwebui-pgdata:/var/lib/postgresql/data"
+    environment:
+      - POSTGRES_DB=openwebui
+      - POSTGRES_USER=openwebui
+      - "POSTGRES_PASSWORD={{ vault_owui_db_password }}"
+    restart: unless-stopped

ansible/services/phy-srv-gpu01/99-network/compose.yml

@@ -0,0 +1,7 @@
+# network definition (leading comment required: the compose generator
+# indents the first line of each fragment; networks: must stay top-level)
+networks:
+  llmnet:
+    driver: bridge
+    driver_opts:
+      com.docker.network.bridge.name: br-llm

ansible/services/phy-srv-gpu01/README.md

@@ -0,0 +1,39 @@
+# Compose stacks for phy-srv-gpu01
+
+Rendered by `ironicbadger.docker_compose_generator` (pinned to 2.0.1) into
+`{{ docker_compose_generator_output_path }}/compose.yaml` on the host.
+The fragments here are **Jinja2 templates**, not plain compose files — Ansible
+variables are substituted at render time.
+
+| Stack | Contains |
+| --- | --- |
+| `01-vllm` | vLLM, serves the chat model on port 8000 (OpenAI API) |
+| `02-embeddings` | second vLLM instance, embedding model on port 8001 |
+| `03-openwebui` | Open WebUI (port 80) + pgvector Postgres |
+| `99-network` | the shared `llmnet` bridge — must sort last |
+
+Ordering comes from the `NN-` prefix; `99-network` keeps `networks:` at the
+bottom of the generated file. The leading comment in `99-network/compose.yml`
+is load-bearing: the role indents only the first line of each fragment, and the
+comment absorbs that indentation so `networks:` stays top-level.
+
+## Deploy
+
+```sh
+just compose phy_srv_gpu01     # renders ~/docker/compose.yaml on the host
+```
+
+The role only **writes** the file. Bringing the stack up is deliberate:
+
+```sh
+ssh sbxadmin@192.168.66.69 'cd ~/docker && docker compose up -d'
+```
+
+## Before the first run
+
+- Secrets must exist in `group_vars/secrets.yml` (`just vault edit`):
+  `vault_owui_secret_key`, `vault_owui_db_password`, `vault_ldap_bind_password`
+- LDAP parameters in `group_vars/phy_srv_gpu01.yml` need the real bind DN and
+  base DN from the customer
+- `vllm_image` must point at a build that works on SM120 (Blackwell) — verify
+  before deploying, the official image is not guaranteed to work

server/phy-srv-gpu01/README.md

@@ -1,11 +1,11 @@
-# phy-z-srv-gpu01
+# phy-srv-gpu01
 
 GPU server for AI/ML workloads. Hardware is ordered/assessed; OS setup and configuration are the next step.
 
 | | |
 | - | - |
 | IP | 192.168.66.69 (planned) |
-| Ansible group | `phy_z_srv_gpu01` |
+| Ansible group | `phy_srv_gpu01` |
 | Status | planned — not yet configured |
 
 ## Hardware

server/phy-srv-gpu01/notes/20260710-projektplan.md

@@ -1,4 +1,4 @@
-# Projektplan — Setup phy-z-srv-gpu01 (LLM-Server mit SMB-Wissensbasis)
+# Projektplan — Setup phy-srv-gpu01 (LLM-Server mit SMB-Wissensbasis)
 
 Date: 2026-07-10 (Stand-Update: 2026-09-03)
 Status: **In Umsetzung** — Server geliefert, Basis-Setup + GPU-Treiber fertig
@@ -93,24 +93,33 @@ GPU-Server nötig). Zu erheben:
 Ergebnis bestimmt: Korpus-Umfang (→ §1-Trigger), OCR-Pipeline ja/nein,
 Index-Größe (→ Storage-Check §2.3), Erst-Indexierungsdauer.
 
-**Ergebnis (Lauf 2026-07-14, Skript `scripts/share-analysis.ps1` auf `D:` des
+**Ergebnis (Lauf 2026-09-03, Skript `scripts/share-analysis.ps1` auf `D:` des
-Fileservers Z-FILESERVER):**
+Fileservers Z-FILESERVER; Zahlen ggü. dem Erstlauf 2026-07-14 leicht gewachsen):**
 
 | Kennzahl | Wert | Konsequenz |
 |---|---|---|
-| Gesamt | **3.322.175 Dateien, 2.224 GB** | Scan lief über `D:` gesamt, nicht je Share → Obergrenze, enthält evtl. nicht freigegebene Daten |
+| Gesamt | **3.338.643 Dateien, 2.231 GB** | Scan lief über `D:` gesamt, nicht je Share → Obergrenze, enthält evtl. nicht freigegebene Daten |
-| `office` (extrahierbar) | **1.258.642 Dateien, 587 GB** | **12× über der §1-Schwelle** → Eingrenzung zwingend (§2.6) |
+| `office` (extrahierbar) | **1.271.467 Dateien, 591 GB** | **12× über der §1-Schwelle** → Eingrenzung zwingend (§2.6) |
-| `other` (unklassifiziert) | 1.575.752 Dateien, 934 GB | größter Block, **noch unidentifiziert** → `D-file-types.csv` auswerten |
+| `other` (unklassifiziert) | 1.576.747 Dateien, 919 GB | größter Block, **noch unidentifiziert** → `D-file-types.csv` auswerten |
 | Bilder / CAD / Archive / Medien | 403k / 60k / 12,6k / 6,2k Dateien | nicht extrahierbar → Erwartungsmanagement |
-| PDFs | **924.076**, davon ~**18 % ohne Textlayer** (Stichprobe 200) | ≈ **166.000 Scan-PDFs → OCR**; eigener Zeit-/GPU-Aufwand, konkurriert mit vLLM |
+| PDFs | **935.186**, davon ~**22 % ohne Textlayer** (Stichprobe 200) | ≈ **200.000 Scan-PDFs → OCR**; eigener Zeit-/GPU-Aufwand, konkurriert mit vLLM |
 | Änderungsrate | 94 % älter als 1 Jahr; nur ~158k in den letzten 365 Tagen | Sync-Frequenz unkritisch; **Alter ≠ Irrelevanz** (Datenblätter, Normen) → Filter primär ordner-/inhaltsbasiert, Aktualität nur sekundär |
-| Duplikat-/Altversions-Muster | 33.179 Dateien | Filterregeln |
+| Duplikat-/Altversions-Muster | 33.378 Dateien | Filterregeln |
-| Pfade > 240 Zeichen | 25.169 | Extraktions-Toolchain gezielt testen |
+| Pfade > 240 Zeichen | 25.866 | Extraktions-Toolchain gezielt testen |
-| Nicht-ASCII-Dateinamen | 126.111 | UTF-8 durchgängig (CIFS-Mount-Optionen → Extraktion → Index) |
+| Nicht-ASCII-Dateinamen | 126.899 | UTF-8 durchgängig (CIFS-Mount-Optionen → Extraktion → Index) |
 
-**Noch auszuwerten** (CSVs liegen auf dem Fileserver, noch nicht gesichtet):
+**Bug im Erstlauf:** Beim Lauf über `D:` wurden **keine CSVs geschrieben**
-`D-toplevel-folders.csv` (Größe/Anzahl je Top-Level-Ordner — die Grundlage für
+(`Export-Csv` scheiterte an `D:` im Dateinamen). Behoben am 2026-09-03; für die
-die Include-/Exclude-Liste) und `D-file-types.csv` (Auflösung der `other`-Kategorie).
+Ordner-Aufschlüsselung neu laufen lassen mit:
+
+```powershell
+.\share-analysis.ps1 -Paths "D:" -OutDir .\file-analysis -FolderDepth 2
+```
+
+`-FolderDepth 2` liefert Größe/Anzahl je `Abteilungen\<Share>` — genau die
+Granularität der Freigaben (s. §2.7) und die Grundlage für die Include-/
+Exclude-Liste. Ebenfalls auszuwerten: `D-file-types.csv` zur Auflösung der
+`other`-Kategorie (1,58 Mio. Dateien, größter unidentifizierter Block).
 
 ### 2.2 Mit dem Kunden zu klären (Checkliste) — Stand 2026-09-03
 
@@ -144,7 +153,7 @@ und Indexgröße (§2.6).
 
 ### 2.4 Ansible vorbereiten (im Repo, testbar ohne GPU)
 
-- `run.yml`: Play für `phy_z_srv_gpu01` ergänzen
+- `run.yml`: Play für `phy_srv_gpu01` ergänzen
 - Rollen-Skelett unter `ansible/roles/` (Details erst bei Umsetzung):
   - `nvidia_gpu` — Treiber (≥ 580), Container Toolkit, optional MIG, DCGM
   - `cifs_mounts` — ro-Mounts, Credentials aus `group_vars/secrets.yml`
@@ -152,7 +161,7 @@ und Indexgröße (§2.6).
     Embedding-Server, Open WebUI + pgvector, Reverse Proxy (TLS), oikb-Timer
   - Bestehendes nachnutzen: `geerlingguy.security` (Basis-Härtung),
     `geerlingguy.docker`
-- `group_vars/phy_z_srv_gpu01.yml`: nur Overrides (Modellname, VRAM-Quote,
+- `group_vars/phy_srv_gpu01.yml`: nur Overrides (Modellname, VRAM-Quote,
   Share-Liste, LDAP-Parameter)
 - Alles außer GPU-Rolle ist vorab in einer Wegwerf-VM testbar (`just run`-Pfad)
 
@@ -206,11 +215,41 @@ lautete sinngemäß „unsere Dokumente auslesen". Realistisch ist „ein kurati
 Teil unserer Dokumente, dafür mit guten Antworten". Das früh sagen — nicht erst,
 wenn der Vollindex schlechte Treffer liefert.
 
+### 2.7 Freigaben-Inventar (Stand 2026-09-03)
+
+`scripts/list-shares.ps1` auf Z-FILESERVER: **30 Freigaben, alle unterhalb `D:`**,
+kein DFS. Vorschlag als *Gesprächsgrundlage* — die Zuordnung der Kürzel muss der
+Kunde bestätigen, ebenso die endgültige Auswahl:
+
+| Freigabe | Pfad | Vorschlag | Begründung |
+|---|---|---|---|
+| QM | `D:\Abteilungen\QM` | **rein** | Qualitätsmanagement — Normen, Prüfvorschriften: Kern der Wissensbasis |
+| Arbeitssicherheit | `D:\Arbeitssicherheit` | **rein** | Vorschriften, Betriebsanweisungen |
+| Competence Center | `D:\Abteilungen\Competence Center` | **rein** | Name deutet auf kuratiertes Wissen |
+| EDV | `D:\Abteilungen\EDV` | **rein** | IT-Doku |
+| Produktion | `D:\Produktion` | **prüfen** | vermutlich groß; ggf. nur Unterordner mit Doku |
+| Projekte | `D:\Projekte` | **prüfen** | vermutlich der größte Block; nur mit Unterordner-Filter sinnvoll |
+| Lagerlogistik, Marketing, Kalkulationen, Controlling, Immobilie | div. | **prüfen** | fachlich abhängig, eher zweite Welle |
+| AA, AZ, BU, EE, EF, EK, ME, MF, MM, PL, SG, VT | `D:\Abteilungen\*` | **klären** | Abteilungskürzel — Bedeutung und Inhalt vom Kunden bestätigen lassen |
+| Zeichnungen | `D:\Abteilungen\Zeichnungen` | **raus** | CAD/Zeichnungen — nicht extrahierbar (s. `cad`/`image` in §2.1) |
+| Datenbank | `D:\Datenbank` | **raus** | Datenbank-Dateien, kein Fließtext |
+| Tempwork | `D:\Tempwork` | **raus** | temporär, per Definition kein Wissensbestand |
+| Benutzer | `D:\Benutzer` | **raus** | persönliche Ablagen — Datenschutz, kein geteiltes Wissen |
+| **Personal** | `D:\Abteilungen\Personal` | **raus** | **HR — explizit ausgeschlossen** (§0: „alle sehen alles" gilt nur ohne Personaldaten) |
+| **GF** | `D:\Abteilungen\GF` | **raus** | Geschäftsführung — vertraulich |
+| **BR** | `D:\Abteilungen\BR` | **raus (klären)** | falls Betriebsrat: besonders schutzwürdig, auf keinen Fall indizieren |
+
+⚠️ **Wichtig:** Weil alle Nutzer alles sehen (§0), ist jede indizierte Freigabe für
+alle 25 Nutzer lesbar — unabhängig von den NTFS-Rechten auf dem Fileserver. Die
+Ausschlüsse oben sind deshalb keine Kosmetik, sondern die einzige Zugriffskontrolle.
+`list-shares.ps1` gibt die NTFS-Gruppen je Freigabe mit aus: Alles, was heute nur
+einem eingeschränkten Personenkreis offensteht, gehört **nicht** in den Index.
+
 ## 3. Phasen ab Server-Lieferung
 
 | Phase | Inhalt | Ergebnis/Abnahme |
 |---|---|---|
-| **1. Basis** (Woche 1) | Rack/Strom (600-W-GPU!), iLO, Firmware, RAID, Ubuntu 24.04 LTS, Eintrag in Ansible-Basis-Setup (Security, Pakete, Nutzer) | `just run phy_z_srv_gpu01` läuft grün |
+| **1. Basis** (Woche 1) | Rack/Strom (600-W-GPU!), iLO, Firmware, RAID, Ubuntu 24.04 LTS, Eintrag in Ansible-Basis-Setup (Security, Pakete, Nutzer) | `just run phy_srv_gpu01` läuft grün |
 | **2. GPU-Stack** (Woche 1–2) | Rolle `nvidia_gpu`: Treiber, Container Toolkit, DCGM; **Burn-in unter Dauerlast** (SM120-Risiken, Deep Dive §1.6); MIG erst mal **aus** | `nvidia-smi` ok, 48 h-Lasttest ohne Reset |
 | **3. Inference** (Woche 2) | vLLM-Container (NVIDIA-Build) mit gewähltem Modell, feste VRAM-Quote, Embedding-Server daneben; Benchmark mit Eval-Set | deutsche Antworten ok, Ziel-Parallelität erreicht |
 | **4. UI + Auth** (Woche 2–3) | Open WebUI + pgvector, LDAP-Login, Reverse Proxy + TLS, vorkonfigurierter „Phytron-Assistent" | Login mit AD-Konto, Chat läuft |

server/phy-srv-gpu01/scripts/list-shares.ps1

@@ -16,8 +16,20 @@
     .\list-shares.ps1
 
 .EXAMPLE
-    # remote, and with size per share (slow on large shares)
+    # with size per share — run this ON the file server, it then walks the local
-    .\list-shares.ps1 -ComputerName Z-FILESERVER -WithSize
+    # paths instead of the UNC paths (far faster). Still minutes to hours on
+    # millions of files; progress is printed every 50k files.
+    .\list-shares.ps1 -WithSize
+
+.NOTES
+    Faster alternative when all shares live under one drive (as on Z-FILESERVER,
+    where everything sits under D:): run share-analysis.ps1 once with a matching
+    folder depth instead of measuring every share separately, e.g.
+
+        .\share-analysis.ps1 -Paths "D:" -FolderDepth 2
+
+    That produces size/count per D:\Abteilungen\<Share> in a single pass over
+    the disk, which is what the share list here maps onto.
 #>
 param(
     [string]$ComputerName = $env:COMPUTERNAME,
@@ -55,13 +67,28 @@ $result = foreach ($sh in $shares) {
 
     $sizeGB = $null; $fileCount = $null
     if ($WithSize) {
-        Write-Host "    measuring size ..." -ForegroundColor DarkGray
+        # Walk the LOCAL path when we are on the server itself — going through
-        try {
+        # the UNC path (\\server\share) routes every single file through the SMB
-            $m = Get-ChildItem -LiteralPath "\\$ComputerName\$($sh.Name)" -Recurse -File -Force -ErrorAction SilentlyContinue |
+        # stack and is slower by orders of magnitude on large shares.
-                 Measure-Object -Property Length -Sum
+        $scanPath = if ($ComputerName -eq $env:COMPUTERNAME -and $sh.Path) {
-            $sizeGB    = [Math]::Round($m.Sum / 1GB, 2)
+            $sh.Path
-            $fileCount = $m.Count
+        } else {
-        } catch { }
+            "\\$ComputerName\$($sh.Name)"
+        }
+
+        $sw = [System.Diagnostics.Stopwatch]::StartNew()
+        $n = 0L; $bytes = 0L
+        Get-ChildItem -LiteralPath $scanPath -Recurse -File -Force -ErrorAction SilentlyContinue |
+            ForEach-Object {
+                $n++; $bytes += $_.Length
+                if ($n % 50000 -eq 0) {
+                    Write-Host ("    ... {0:N0} files, {1:N1} GB ({2:N0}s)" -f $n, ($bytes / 1GB), $sw.Elapsed.TotalSeconds) -ForegroundColor DarkGray
+                }
+            }
+        $sw.Stop()
+        $sizeGB    = [Math]::Round($bytes / 1GB, 2)
+        $fileCount = $n
+        Write-Host ("    {0:N0} files, {1:N1} GB in {2:N0}s" -f $n, ($bytes / 1GB), $sw.Elapsed.TotalSeconds) -ForegroundColor DarkGray
     }
 
     [PSCustomObject]@{

server/phy-srv-gpu01/scripts/share-analysis.ps1

@@ -26,7 +26,11 @@ param(
     [string]$OutDir = (Join-Path (Get-Location) ("share-analysis-" + (Get-Date -Format "yyyyMMdd-HHmmss"))),
 
     # PDFs sampled per share for the text-layer check
-    [int]$PdfSampleSize = 200
+    [int]$PdfSampleSize = 200,
+
+    # How many folder levels to aggregate in the *-toplevel-folders.csv.
+    # 1 = D:\Abteilungen, 2 = D:\Abteilungen\AA (matches the share layout here).
+    [int]$FolderDepth = 1
 )
 
 $ErrorActionPreference = 'Continue'
@@ -80,7 +84,17 @@ function Test-PdfTextLayer {
 # --- per-share pass ----------------------------------------------------------
 
 foreach ($root in $Paths) {
+    # Label used for the output filenames. Must not contain characters that are
+    # illegal in a filename — e.g. -Paths "D:" would otherwise produce
+    # "D:-file-types.csv" and Export-Csv fails with "path format not supported".
     $shareName = ($root.TrimEnd('\') -split '[\\/]')[-1]
+    if (-not $shareName) { $shareName = 'root' }
+    foreach ($c in [System.IO.Path]::GetInvalidFileNameChars()) {
+        $shareName = $shareName.Replace($c, '_')
+    }
+    $shareName = $shareName.TrimEnd('_', '.', ' ')
+    if (-not $shareName) { $shareName = 'root' }
+
     Write-Host "=== Analyzing '$root' ..." -ForegroundColor Cyan
 
     if (-not (Test-Path -LiteralPath $root)) {
@@ -118,9 +132,15 @@ foreach ($root in $Paths) {
             $extStats[$ext].Count++
             $extStats[$ext].Bytes += $_.Length
 
-            # top-level folder relative to the share root
+            # folder relative to the share root, aggregated at -FolderDepth levels
             $rel = $_.FullName.Substring($rootLen).TrimStart('\')
-            $top = if ($rel.Contains('\')) { $rel.Split('\')[0] } else { '(root)' }
+            $parts = $rel.Split('\')
+            if ($parts.Count -le 1) {
+                $top = '(root)'
+            } else {
+                $n = [Math]::Min($FolderDepth, $parts.Count - 1)
+                $top = ($parts[0..($n - 1)] -join '\')
+            }
             if (-not $topStats.ContainsKey($top)) { $topStats[$top] = @{ Count = 0L; Bytes = 0L } }
             $topStats[$top].Count++
             $topStats[$top].Bytes += $_.Length