infra-phytron/TODO.md

TODO

phy-z-srv-gpu01

Per projektplan (§ references below). Server is delivered; base setup + NVIDIA driver are done (see SETUP.md).

Blocking the knowledge base (customer conversation)

• Scope the corpus (§2.6) — share analysis found 1.26M extractable documents, ~12× the planning threshold. Decide with the customer which shares/folders actually form the knowledge base. Everything in Phase 5 depends on this.
• Evaluate the two CSVs still sitting on the file server: D-toplevel-folders.csv (basis for the include/exclude list) and D-file-types.csv (resolve the 1.58M unidentified other files)
• Run scripts/list-shares.ps1 on Z-FILESERVER — map shares → local paths, so the analysis of D: can be tied to actual shares
• Data protection / works council: are chat logs stored? (§2.2) — before rollout
• AD details still needed: bind service account + base DN (group llm_users and the read-only SMB account are agreed)
• German eval set (§2.5): 20–30 Q&A with the customer — acceptance criterion

Server / Ansible

• Role cifs_mounts — read-only mounts, credentials from group_vars/secrets.yml
• Role llm_stack — docker compose: vLLM (fixed --gpu-memory-utilization), 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 phy-z-srv-gpu01 — align
• Finish base hardening in SETUP.md (ssh, updates) via just run phy_z_srv_gpu01

Done

• Share analysis script → scripts/share-analysis.ps1, run on 2026-07-14 (§2.1)
• Storage decision (§2.3) — 876 GB usable, no extra disks needed
• NVIDIA driver via role nvidia_gpu (595 open kernel modules)