rbsetiawan
/
LDAPWeb
1
0
Fork 0
Code Issues 2 Pull Requests Projects Releases Wiki Activity
GeoNetAgent, LDAPWeb, server-audit, server-connection
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
43 Commits
1 Branch
0 Tags
19 MiB
 
 
 
 
 
 
Tree: c958b343ed
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'c958b343ed'
${ noResults }
LDAPWeb/Ollama/docs/todo.md

3.2 KiB
Raw Blame History

TODO — Ollama

Last updated: 2026-07-06

High Priority

Fase 1 — GPU Node (PC-Multimedia) ✅ SELESAI

  • CUDA 12.9 sudah tersedia via driver 576.88 (tidak perlu install terpisah)
  • Install Ollama v0.31.1 di Windows (OllamaSetup.exe)
  • Set OLLAMA_MODELS=T:\ollama\models + OLLAMA_HOST=0.0.0.0:11434 via setx /M
  • Autostart via Task Scheduler (SYSTEM, AtStartup) — script PC-Multimedia/scripts/install-ollama-task.ps1
  • Firewall rule OllamaVLAN: TCP 11434 dari 10.100.1.0/24 only
  • Pull qwen2.5-coder:14b (9.0 GB) + nomic-embed-text (274 MB) → T:\ollama\models
  • Verified: API http://10.100.1.14:11434 reachable, VRAM 11.5 GB / 16 GB saat loaded

Fase 2 — pgvector + Codebase Index ✅ SELESAI

  • pgvector Docker di 10.100.1.24:5433 (pgvector 0.8.4 / pg16)
  • DB geonet_project_search + tabel code_chunks + user_memory + index HNSW
  • Script indexer Ollama/indexer/indexer.py — 1.784 chunks dari 1.031 files, 18 repo
  • Verified: similarity search akurat (query → FeedbackController.php sebagai top result)

Fase 3 — Integrasi geonet-console ✅ SELESAI

  • OLLAMA_BASE_URL=http://10.100.1.14:11434 di geonet-console .env
  • AiChatService — embed query → pgvector similarity search → inject context → Ollama chat
  • AiChatController — POST /api/v1/ai/chat + GET /api/v1/ai/status
  • config/pgvector.php — config PGVECTOR_HOST/PORT/DB/USER/PASS
  • Verified end-to-end: 5 context chunks retrieved, jawaban akurat tentang route feedback
  • User memory: simpan pola interaksi per user (next iteration)

VM .26 (tetap jalan sebagai fallback)

  • Tetap running qwen2.5:7b + nomic-embed-text sebagai fallback CPU inference
  • SMB read-only mount QNAP 10.100.1.10 di VM .26 (indexer background)

Medium Priority

  • UI chat di Super Apps PWA — window chat terintegrasi
  • User memory / RAG: retrieve pola kebiasaan user saat generate response
  • Deploy agent (Fase 4): tool calling SSH + docker exec untuk bantu deploy
  • Healthcheck / monitoring (Zabbix atau cron ollama ps)
  • Optimasi VM .26: Ubuntu Desktop → Server atau matikan GUI (hemat RAM)

Low Priority

  • Fine-tuning LoRA untuk template spesifik organisasi (butuh 1000+ contoh data)
  • Evaluasi model deepseek-coder-v2:16b untuk coding tasks
  • Backup /data/ollama/models ke QNAP
  • Dokumentasi troubleshooting inference timeout
  • Migrasi model ke VM .26 jika PC-Multimedia tidak bisa 24/7

Selesai (Sesi Ini)

  • Audit live VM 10.100.1.26 — Ollama + model verified
  • Bootstrap dokumentasi repo Ollama/ (AI-Agent-Standards)
  • Daftar di Workspace-Context.md
  • Audit hardware PC-Multimedia via DxDiag — Core Ultra 7 265K, 64 GB, RTX 5060 Ti
  • Diskusi arsitektur AI onprem: Context Injection → RAG/Memory → Fine-tuning
  • Diskusi AI coding assistant + deploy agent on-premise
  • Fase 1 GPU Node PC-Multimedia — Ollama v0.31.1, GPU inference aktif, verified dari laptop
  • Fase 2 pgvector — Docker 10.100.1.24:5433, 1.784 chunks, similarity search verified
  • Fase 3 integrasi — POST /api/v1/ai/chat live, RAG end-to-end verified di geonet-console