39 lines
1.1 KiB
YAML
39 lines
1.1 KiB
YAML
# LiteLLM config for inference.coop
|
|
# TEST config: Ollama Cloud (existing subscription) — plumbing smoke test
|
|
# Uses Ollama Cloud's OpenAI-compatible endpoint (/v1) via LiteLLM's openai/ provider.
|
|
# Provider key set via environment variable OLLAMA_API_KEY.
|
|
|
|
model_list:
|
|
# DeepSeek V4 Flash — default model
|
|
- model_name: deepseek-v4-flash
|
|
litellm_params:
|
|
model: openai/deepseek-v4-flash:0731
|
|
api_base: https://ollama.com/v1
|
|
api_key: os.environ/OLLAMA_API_KEY
|
|
|
|
# GPT-OSS 120B — lightweight fallback
|
|
- model_name: gpt-oss-120b
|
|
litellm_params:
|
|
model: openai/gpt-oss:120b
|
|
api_base: https://ollama.com/v1
|
|
api_key: os.environ/OLLAMA_API_KEY
|
|
|
|
# Fallback: if DeepSeek is down, use GPT-OSS
|
|
router_settings:
|
|
num_retries: 2
|
|
timeout: 30
|
|
fallbacks:
|
|
- deepseek-v4-flash:
|
|
- gpt-oss-120b
|
|
|
|
general_settings:
|
|
master_key: os.environ/LITELLM_MASTER_KEY
|
|
database_url: os.environ/DATABASE_URL
|
|
store_model_in_db: true
|
|
|
|
litellm_settings:
|
|
salt_key: os.environ/LITELLM_SALT_KEY
|
|
drop_params: true
|
|
num_threads: 4
|
|
request_timeout: 30
|