diff --git a/config/llm.yaml.example b/config/llm.yaml.example new file mode 100644 index 0000000..b0fcbe5 --- /dev/null +++ b/config/llm.yaml.example @@ -0,0 +1,74 @@ +# Kiwi — LLM backend configuration +# +# Copy to ~/.config/circuitforge/llm.yaml (shared across all CF products) +# or to config/llm.yaml (Kiwi-local, takes precedence). +# +# Kiwi uses LLMs for: +# - Expiry prediction fallback (unknown products not in the lookup table) +# - Meal planning suggestions +# +# Local inference (Ollama / vLLM) is the default path — no API key required. +# BYOK (bring your own key): set api_key_env to point at your API key env var. +# cf-orch trunk: set CF_ORCH_URL env var to allocate cf-text on-demand via +# the coordinator instead of hitting a static URL. + +backends: + ollama: + type: openai_compat + enabled: true + base_url: http://localhost:11434/v1 + model: llama3.2:3b + api_key: ollama + supports_images: false + + vllm: + type: openai_compat + enabled: false + base_url: http://localhost:8000/v1 + model: __auto__ # resolved from /v1/models at runtime + api_key: '' + supports_images: false + + # ── cf-orch trunk services ────────────────────────────────────────────────── + # These allocate via cf-orch rather than connecting to a static URL. + # cf-orch starts the service on-demand and returns its live URL. + # Set CF_ORCH_URL env var or fill in url below; leave enabled: false if + # cf-orch is not deployed in your environment. + + cf_text: + type: openai_compat + enabled: false + base_url: http://localhost:8008/v1 # fallback when cf-orch is not available + model: __auto__ + api_key: any + supports_images: false + cf_orch: + service: cf-text + # model_candidates: leave empty to use the service's default_model, + # or specify a catalog alias (e.g. "qwen2.5-3b"). + model_candidates: [] + ttl_s: 3600 + + # ── Cloud / BYOK ─────────────────────────────────────────────────────────── + + anthropic: + type: anthropic + enabled: false + model: claude-haiku-4-5-20251001 + api_key_env: ANTHROPIC_API_KEY + supports_images: false + + openai: + type: openai_compat + enabled: false + base_url: https://api.openai.com/v1 + model: gpt-4o-mini + api_key_env: OPENAI_API_KEY + supports_images: false + +fallback_order: + - cf_text + - ollama + - vllm + - anthropic + - openai