48c839d927
This is the snapshot the production landing site (nibiru-framework.com) is deployed from. Brings together the recent splash + docs migration to the v4 "Cosmos" design system, the new in-framework AI module, and the framework groundwork that backs the framework-reference extraction. What lands: - docs/: Astro + Starlight site with the v4 dark cosmic palette, GalaxyHero canvas constellation, Mission Control chat (wired to /api/oracle → api.neuronetz.ai via providers.mjs Ollama), 5-panel MMVC stage (Model · AI · Module · Controller · View), translated EN/DE/JA/ES/FR content, PWA + sitemap + llms.txt + Umami analytics. - docs/design-system/: canonical mockup bundle (source/index-v2.html for splash, source/docs-system.html + preview/ for docs, SPEC.md, tokens). - docs/scripts/extraction/framework-reference-v2.md: deep framework reference (~1.6k lines, file:line citations, every public factory and idiom — basis for the LoRA training corpus. - application/module/ai/: AI module with chat / embed / RAG / agent plugins, plus pdoQuery / httpGet / fileRead tools and Modelfile + smoke-test in training/. - application/module/users/: user / ACL / form-factory traits used as the reference plugin pattern for the framework docs. - application/settings/config/database/: schema + seed migrations including the AI module tables (200–203). - Form factory + autogenerator changes the framework-reference-v2 covers. Production secrets stay out: docs/.env, settings.production.ini and ai.production.ini are all gitignored (.example files are in tree). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
42 lines
1.7 KiB
Plaintext
42 lines
1.7 KiB
Plaintext
; =====================================================================
|
|
; Per-environment override for the AI module.
|
|
;
|
|
; Copy to ai.production.ini on the production host and fill in real
|
|
; values. The Registry will prefer this file over ai.ini when
|
|
; APPLICATION_ENV=production.
|
|
;
|
|
; This file IS gitignored (or should be — add /application/module/ai/
|
|
; settings/ai.production.ini to .gitignore). Never commit production
|
|
; endpoints or model names to a public repo.
|
|
; =====================================================================
|
|
|
|
[AI]
|
|
; Point at YOUR Ollama. Self-hosted, behind a reverse proxy, or local —
|
|
; whatever you run. Leave the default localhost in ai.ini and override
|
|
; here for production.
|
|
ollama.base_url = "https://your-ollama.example.com"
|
|
ollama.timeout = 90
|
|
|
|
; If you've registered the Nibiru-flavoured model on your Ollama, point
|
|
; chat.model at it. Otherwise the fallback covers you.
|
|
chat.model = "nibiru-coder:1.0"
|
|
chat.fallback_model = "qwen2.5-coder:14b"
|
|
|
|
; In production prefer the larger / better embedding model if you've
|
|
; pulled it. mxbai-embed-large > nomic-embed-text for quality.
|
|
embed.model = "nomic-embed-text"
|
|
|
|
; Tighten the ask budget in production — fewer tokens = faster + cheaper.
|
|
chat.max_tokens = 800
|
|
|
|
; RAG storage in production: switch to database to share a collection
|
|
; across multiple app instances behind a load balancer.
|
|
; "json" — single JSON file per collection (default, in cache/rag/)
|
|
; "database" — uses ai_rag_collection / ai_rag_chunk tables
|
|
rag.storage = "database"
|
|
|
|
; Optional fallbacks. The framework module ships without these — set
|
|
; them only if you want to swap providers temporarily.
|
|
; anthropic.api_key = "sk-ant-..."
|
|
; openai.api_key = "sk-..."
|