# AnythingLLM × Persona RAG Integration

28 persona workspace'i olan, kitap kütüphanesinden beslenen RAG sistemi. Her persona kendi uzmanlık alanındaki dokümanlarla vektör embed edilmiş durumda.

## Mimari

- **AnythingLLM Desktop** — `http://localhost:3001`
- **LLM:** Ollama local (qwen3:14b)
- **Embedding:** Google Gemini (gemini-embedding-001)
- **Vector DB:** LanceDB
- **OCR:** ocrmypdf (tur+eng)
- **Kitap Kaynağı:** `/mnt/storage/Common/Books/`

## Personalar (5 Cluster)

| Cluster | Personalar |
|---------|-----------|
| Intel | Frodo, Echo, Ghost, Oracle, Wraith, Scribe, Polyglot |
| Cyber | Neo, Bastion, Sentinel, Specter, Phantom, Cipher, Vortex |
| Military | Marshal, Centurion, Corsair, Warden, Medic |
| Humanities | Chronos, Tribune, Arbiter, Ledger, Sage, Herald, Scholar, Gambit |
| Engineering | Forge, Architect |

## Kullanım

```bash
# Durum kontrolü
python3 setup.py --status

# Workspace oluştur / güncelle
python3 setup.py --create-workspaces

# Tam pipeline (upload + OCR + embed)
python3 setup.py --upload-documents --resume

# Tek cluster veya persona
python3 setup.py --upload-documents --cluster cyber --resume
python3 setup.py --upload-documents --persona neo --priority 1 --resume

# Önizleme
python3 setup.py --upload-documents --dry-run
```

## Pipeline

```
Phase A: Text dosyaları upload
Phase B: Scanned PDF'leri OCR (ocrmypdf)
Phase C: OCR'lı dosyaları upload
Final:   Workspace'lere assign/embed
```

## Recovery

Vektör DB silinirse:
1. `upload_progress.json`'da `workspace_docs` → `{}` sıfırla
2. `python3 setup.py --upload-documents --resume` (sadece re-embed yapar)

## Dosyalar

- `setup.py` — Ana entegrasyon scripti (upload, OCR, workspace assignment)
- `config.yaml` — Persona-klasör eşlemeleri, API config, batch ayarları
- `upload_progress.json` — Upload/atama state tracker (gitignore'd)