f4ccc45a3b
The Ollama URL was leaking via:
- prose in /en/, /de/, /ja/, /es/, /fr/ docs (oracle, deployment,
local-testing, ai/module/{overview,embed,training})
- code blocks teaching users to curl the host directly
- .env.example, Dockerfile, docker-compose.yml defaults
- providers.mjs, translate-docs.mjs, build-oracle-index.mjs defaults
- LandingScripts.astro comment
- lora-runbook.md prose + SSH host
- the GET handler at /api/oracle which echoed `ollamaUrl` back to public callers
- the "Oracle is silent" fallback message at /api/oracle POST
Replacements:
- prose: "neuronetz.ai" → "your Ollama instance"
- example URLs in code blocks: https://api.neuronetz.ai → https://your-ollama-host.example
- code-level defaults: → http://localhost:11434 (Ollama's standard local port)
- GET /api/oracle: dropped the `ollamaUrl` field; provider + model still exposed
- runbook SSH host: neuronetz@cloud.neuronetz.ai → <gpu-user>@<gpu-host>
Production chat is unaffected: docs/.env (gitignored) on the production
host still pins OLLAMA_BASE_URL=https://api.neuronetz.ai. The only
change in the running container is that the GET handler no longer
echoes the URL.
analytics.neuronetz.ai (Umami tracking) is intentionally left intact —
it's a public, brand-owned subdomain meant to be visible.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
41 lines
1.4 KiB
Plaintext
41 lines
1.4 KiB
Plaintext
# Copy to .env on the host and fill in the values you actually need.
|
|
# .env is gitignored.
|
|
#
|
|
# DEFAULT MODE: Ollama on your-ollama-host.example
|
|
# The Oracle uses your own GPU-backed Ollama by default — no paid API keys
|
|
# required. Just make sure the chat + embedding models are pulled (see
|
|
# below) and you're done.
|
|
|
|
# === Default Ollama backend (used when LLM_PROVIDER and EMBED_PROVIDER are
|
|
# 'ollama' — which they are by default) ===
|
|
|
|
# LLM_PROVIDER=ollama
|
|
OLLAMA_BASE_URL=http://localhost:11434
|
|
OLLAMA_CHAT_MODEL=qwen2.5-coder:14b
|
|
OLLAMA_EMBED_MODEL=nomic-embed-text
|
|
|
|
# Pull these once on your Ollama host:
|
|
# curl https://your-ollama-host.example/api/pull -d '{"name":"qwen2.5-coder:14b"}'
|
|
# curl https://your-ollama-host.example/api/pull -d '{"name":"nomic-embed-text"}'
|
|
|
|
# === Oracle behaviour ===
|
|
ORACLE_TOP_K=6
|
|
ORACLE_MAX_TOKENS=800
|
|
|
|
# === Let's Encrypt / nginx-proxy ===
|
|
LETSENCRYPT_EMAIL=stephan.kasdorf@bittomine.com
|
|
|
|
# ===========================================================================
|
|
# OPTIONAL FALLBACKS — only set these if you want to switch off Ollama.
|
|
# ===========================================================================
|
|
|
|
# To use Claude as the answering model:
|
|
# LLM_PROVIDER=anthropic
|
|
# ANTHROPIC_API_KEY=sk-ant-...
|
|
# ANTHROPIC_MODEL=claude-haiku-4-5-20251001
|
|
|
|
# To use OpenAI for embeddings (build time + runtime):
|
|
# EMBED_PROVIDER=openai
|
|
# OPENAI_API_KEY=sk-...
|
|
# OPENAI_EMBED_MODEL=text-embedding-3-small
|