# 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