Initial commit: AnythingLLM persona RAG integration

28 persona workspace with document upload, OCR pipeline, and vector embedding
assignment via AnythingLLM API. Supports 5 clusters (intel, cyber, military,
humanities, engineering) with batch processing and resume capability.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
salvacybersec
2026-04-06 23:07:44 +03:00
commit 9e9b75e0b3
4 changed files with 1178 additions and 0 deletions

425
config.yaml Normal file
View File

@@ -0,0 +1,425 @@
# AnythingLLM × Persona Library Integration Config
# Maps personas to book folders for workspace-based RAG
#
# Usage: python3 setup.py [--dry-run] [--persona <name>] [--upload-documents]
anythingllm:
base_url: "http://localhost:3001/api/v1"
api_key: "SXQGXH3-AQ64B8E-KQNMDWC-WZBQAFW"
storage:
book_library: "/mnt/storage/Common/Books"
personas_dir: "/home/salva/Documents/personas/personas"
# AnythingLLM copies uploaded originals to direct-uploads/
# This symlink sends them to HDD so SSD stays clean
hdd_storage: "/mnt/storage/anythingllm"
embedding:
primary:
engine: "gemini"
model: "gemini-embedding-001"
fallback:
engine: "ollama"
base_path: "http://127.0.0.1:40114/olla/ollama"
model: "nomic-embed-text"
# Batch processing — avoid API rate limits
processing:
batch_size: 50 # files per batch
delay_between_batches: 5 # seconds
max_concurrent: 3 # parallel uploads
skip_extensions: # don't process these
- ".bin"
- ".gz"
- ".zip"
- ".html"
- ".php"
- ".jpg"
- ".pptx"
- ".ppt"
- ".doc"
# ─────────────────────────────────────────────────────────────
# PERSONA → BOOK FOLDER MAPPINGS
# ─────────────────────────────────────────────────────────────
# priority: 1=core (always load), 2=extended (load if capacity allows)
# max_files: cap per folder to keep workspace focused
workspaces:
# ══════════════════════════════════════════════════════════
# INTELLIGENCE CLUSTER
# ══════════════════════════════════════════════════════════
frodo:
name: "Frodo — Stratejik İstihbarat"
persona_file: "frodo/general.md"
folders:
- path: "Istihbarat/TeoriVeAnaliz"
priority: 1
- path: "Istihbarat/Arastirmalar"
priority: 1
- path: "UluslararasiIliskiler"
priority: 1
- path: "GuvenlikStratejileri"
priority: 1
- path: "SETA"
priority: 2
- path: "ORSAM"
priority: 2
- path: "Istihbarat/TurkIstihbarati"
priority: 2
- path: "Istihbarat/RusIstihbarati"
priority: 2
echo:
name: "Echo — SIGINT/COMINT"
persona_file: "echo/general.md"
folders:
- path: "SiberGuvenlik/FOIA-IA-NSA-SIGINT"
priority: 1
- path: "SiberGuvenlik/ElektronikGuvenlik"
priority: 1
- path: "Istihbarat/FOIA-CIA-SogukSavas"
priority: 2
- path: "SiberGuvenlik/FOIA-SiberSavas"
priority: 2
ghost:
name: "Ghost — PSYOP & Bilgi Savaşı"
persona_file: "ghost/general.md"
folders:
- path: "SiberGuvenlik/BilgiSavasi"
priority: 1
- path: "Istihbarat/SorguTeknikleri"
priority: 1
- path: "GuvenlikStratejileri"
priority: 2
oracle:
name: "Oracle — OSINT & Dijital İstihbarat"
persona_file: "oracle/general.md"
folders:
- path: "SiberGuvenlik/OSINT"
priority: 1
- path: "Istihbarat/Arastirmalar"
priority: 2
wraith:
name: "Wraith — HUMINT & Karşı İstihbarat"
persona_file: "wraith/general.md"
folders:
- path: "Istihbarat/TeoriVeAnaliz"
priority: 1
- path: "Istihbarat/BiyografiVeAnilar"
priority: 1
- path: "Istihbarat/TurkIstihbarati"
priority: 1
- path: "Istihbarat/RusIstihbarati"
priority: 1
- path: "Istihbarat/SorguTeknikleri"
priority: 2
- path: "Istihbarat/IstihbaratTarihi"
priority: 2
scribe:
name: "Scribe — FOIA Arşivci"
persona_file: "scribe/general.md"
folders:
- path: "FOIA"
priority: 1
- path: "Istihbarat/CIA"
priority: 1
- path: "Istihbarat/FOIA-CIA-OrtaDogu"
priority: 1
- path: "Istihbarat/FOIA-CIA-SogukSavas"
priority: 1
- path: "Istihbarat/FOIA-CIA-Turkey"
priority: 1
- path: "Istihbarat/FOIA-FBI-COINTELPRO"
priority: 2
- path: "Istihbarat/FOIA-FBI-Vault"
priority: 2
- path: "Istihbarat/FOIA-IA-CIA-SogukSavas"
priority: 2
- path: "Istihbarat/FOIA-IA-CIA-Kuba-OrtaDogu"
priority: 2
- path: "Istihbarat/FOIA-IA-FBI"
priority: 2
- path: "Istihbarat/FOIA-IA-WWII"
priority: 2
- path: "SiberGuvenlik/FOIA-CyberWarfare"
priority: 2
- path: "SiberGuvenlik/FOIA-IA-NSA-SIGINT"
priority: 2
polyglot:
name: "Polyglot — Dilbilim & LINGINT"
persona_file: "polyglot/general.md"
folders:
- path: "Egitim"
priority: 1
# ══════════════════════════════════════════════════════════
# CYBERSECURITY CLUSTER
# ══════════════════════════════════════════════════════════
neo:
name: "Neo — Red Team & Exploit Dev"
persona_file: "neo/general.md"
folders:
- path: "SiberGuvenlik/PenetrasyonTesti"
priority: 1
- path: "SiberGuvenlik/SaldiriTeknikleri"
priority: 1
- path: "SiberGuvenlik/ZafiyetArastirmasi"
priority: 1
- path: "SiberGuvenlik/WebGuvenligi"
priority: 2
bastion:
name: "Bastion — Blue Team & DFIR"
persona_file: "bastion/general.md"
folders:
- path: "SiberGuvenlik/AdliBilisim"
priority: 1
- path: "SiberGuvenlik/GenelGuvenlik"
priority: 1
- path: "SiberGuvenlik/AgGuvenligi"
priority: 2
- path: "SiberGuvenlik/WindowsGuvenligi"
priority: 2
sentinel:
name: "Sentinel — Siber Tehdit İstihbaratı"
persona_file: "sentinel/general.md"
folders:
- path: "SiberGuvenlik/TehditIstihbarati"
priority: 1
- path: "SiberGuvenlik/SiberSavas"
priority: 1
- path: "SiberGuvenlik/SiberGuvenlikStratejisi"
priority: 1
- path: "SiberGuvenlik/FOIA-CyberWarfare"
priority: 2
specter:
name: "Specter — Zararlı Yazılım & Tersine Mühendislik"
persona_file: "specter/general.md"
folders:
- path: "SiberGuvenlik/ZararliYazilimAnalizi"
priority: 1
- path: "SiberGuvenlik/TersineMuhendislik"
priority: 1
- path: "SiberGuvenlik/KernelGuvenligi"
priority: 2
phantom:
name: "Phantom — Web Uygulama Güvenliği"
persona_file: "phantom/general.md"
folders:
- path: "SiberGuvenlik/WebGuvenligi"
priority: 1
- path: "SiberGuvenlik/PenetrasyonTesti"
priority: 2
- path: "SiberGuvenlik/BulutGuvenligi"
priority: 2
cipher:
name: "Cipher — Kriptografi"
persona_file: "cipher/general.md"
folders:
- path: "SiberGuvenlik/Kriptografi"
priority: 1
- path: "SiberGuvenlik/BilgiGuvenligi"
priority: 2
vortex:
name: "Vortex — Ağ Operasyonları"
persona_file: "vortex/general.md"
folders:
- path: "SiberGuvenlik/AgGuvenligi"
priority: 1
- path: "SiberGuvenlik/DonaninGuvenligi"
priority: 2
- path: "SiberGuvenlik/IoT"
priority: 2
# ══════════════════════════════════════════════════════════
# MILITARY CLUSTER
# ══════════════════════════════════════════════════════════
marshal:
name: "Marshal — Askeri Doktrin & Strateji"
persona_file: "marshal/general.md"
folders:
- path: "AskeriDoktrin"
priority: 1
- path: "NATO/Doktrin"
priority: 1
- path: "GuvenlikStratejileri"
priority: 1
- path: "NATO/Tatbikat"
priority: 2
centurion:
name: "Centurion — Askeri Tarih"
persona_file: "centurion/general.md"
folders:
- path: "AskeriTarih"
priority: 1
- path: "AskeriDoktrin"
priority: 2
- path: "DunyaTarihi"
priority: 2
corsair:
name: "Corsair — Özel Harekat & Düzensiz Savaş"
persona_file: "corsair/general.md"
folders:
- path: "AskeriDoktrin"
priority: 1
- path: "Istihbarat/TerorMucadele"
priority: 1
- path: "GuvenlikStratejileri"
priority: 2
warden:
name: "Warden — Savunma Analizi & Silah Sistemleri"
persona_file: "warden/general.md"
folders:
- path: "AskeriDoktrin"
priority: 1
- path: "NATO/Teknik"
priority: 1
- path: "GuvenlikStratejileri"
priority: 2
- path: "Istihbarat/SavunmaBakanligiRaporlari"
priority: 2
medic:
name: "Medic — Biyomedikal & KBRN"
persona_file: "medic/general.md"
folders:
- path: "Biyomedikal"
priority: 1
- path: "Istihbarat/KBRN"
priority: 1
- path: "BilimVeArastirma"
priority: 2
# ══════════════════════════════════════════════════════════
# HUMANITIES & ANALYSIS CLUSTER
# ══════════════════════════════════════════════════════════
chronos:
name: "Chronos — Dünya Tarihi & Medeniyet"
persona_file: "chronos/general.md"
folders:
- path: "DunyaTarihi"
priority: 1
- path: "OsmanliTarihi"
priority: 1
- path: "CumhuriyetTarihi"
priority: 1
- path: "RusyaTarihi"
priority: 1
- path: "YahudiTarihi"
priority: 2
- path: "AskeriTarih"
priority: 2
tribune:
name: "Tribune — Siyaset Bilimi & Rejim Analizi"
persona_file: "tribune/general.md"
folders:
- path: "UluslararasiIliskiler"
priority: 1
- path: "SETA"
priority: 1
- path: "ORSAM"
priority: 1
- path: "CumhuriyetTarihi"
priority: 2
arbiter:
name: "Arbiter — Uluslararası Hukuk"
persona_file: "arbiter/general.md"
folders:
- path: "Hukuk"
priority: 1
- path: "UluslararasiIliskiler"
priority: 2
- path: "NATO/Idari"
priority: 2
ledger:
name: "Ledger — Ekonomik İstihbarat & FININT"
persona_file: "ledger/general.md"
folders:
- path: "EkonomiVeFinans"
priority: 1
sage:
name: "Sage — Felsefe & İktidar Teorisi"
persona_file: "sage/general.md"
folders:
- path: "FelsefeVeEdebiyat"
priority: 1
herald:
name: "Herald — Medya Analizi & Stratejik İletişim"
persona_file: "herald/general.md"
folders:
- path: "SETA"
priority: 1
- path: "ORSAM"
priority: 2
- path: "UluslararasiIliskiler"
priority: 2
scholar:
name: "Scholar — Akademik Araştırma"
persona_file: "scholar/general.md"
folders:
- path: "BilimVeArastirma"
priority: 1
- path: "Egitim"
priority: 1
- path: "UluslararasiIliskiler"
priority: 2
gambit:
name: "Gambit — Satranç & Stratejik Düşünce"
persona_file: "gambit/general.md"
folders:
- path: "Satranc"
priority: 1
# ══════════════════════════════════════════════════════════
# ENGINEERING CLUSTER
# ══════════════════════════════════════════════════════════
forge:
name: "Forge — Yazılım & AI/ML"
persona_file: "forge/general.md"
folders:
- path: "AI"
priority: 1
- path: "Teknoloji"
priority: 1
- path: "SiberGuvenlik/Programlama"
priority: 2
- path: "SiberGuvenlik/YapayZekaGuvenligi"
priority: 2
architect:
name: "Architect — DevOps & Altyapı"
persona_file: "architect/general.md"
folders:
- path: "Teknoloji"
priority: 1
- path: "SiberGuvenlik/Linux"
priority: 2
- path: "SiberGuvenlik/BulutGuvenligi"
priority: 2