litellm / config.yaml
zhengr's picture
init
df054a5
raw
history blame
775 Bytes
model_list:
- model_name: gollama-mistral-7b
litellm_params:
model: ollama/mistral:7b
api_base: https://zhengr-ollama.hf.space
litellm_settings: # module level litellm settings - https://github.com/BerriAI/litellm/blob/main/litellm/__init__.py
drop_params: True
success_callback: ["langfuse"] # OPTIONAL - if you want to start sending LLM Logs to Langfuse. Make sure to set `LANGFUSE_PUBLIC_KEY` and `LANGFUSE_SECRET_KEY` in your env
general_settings:
master_key: sk-1234 # [OPTIONAL] Only use this if you to require all calls to contain this key (Authorization: Bearer sk-1234)
alerting: ["slack"] # [OPTIONAL] If you want Slack Alerts for Hanging LLM requests, Slow llm responses, Budget Alerts. Make sure to set `SLACK_WEBHOOK_URL` in your env