mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-11 03:38:38 +00:00
undo changes to docker file
This commit is contained in:
parent
f9e3a2782f
commit
64e363b3d3
2 changed files with 1 additions and 25 deletions
|
|
@ -73,4 +73,4 @@ EXPOSE 4000/tcp
|
|||
ENTRYPOINT ["litellm"]
|
||||
|
||||
# Append "--detailed_debug" to the end of CMD to view detailed debug logs
|
||||
CMD ["--port", "4000", "--config", "stable_config.yaml"]
|
||||
CMD ["--port", "4000"]
|
||||
|
|
|
|||
|
|
@ -1,24 +0,0 @@
|
|||
general_settings:
|
||||
store_model_in_db: true
|
||||
database_connection_pool_limit: 20
|
||||
|
||||
model_list:
|
||||
- model_name: fake-openai-endpoint
|
||||
litellm_params:
|
||||
model: openai/my-fake-model
|
||||
api_key: my-fake-key
|
||||
api_base: https://exampleopenaiendpoint-production.up.railway.app/
|
||||
router_settings:
|
||||
routing_strategy: "latency-based-routing"
|
||||
routing_strategy_args: {"ttl": 100} # Average the last 10 calls to compute avg latency per model
|
||||
allowed_fails: 1
|
||||
num_retries: 3
|
||||
retry_after: 5 # seconds to wait before retrying a failed request
|
||||
cooldown_time: 30 # seconds to cooldown a deployment after failure
|
||||
enable_pre_call_checks: true
|
||||
litellm_settings:
|
||||
return_response_headers: true
|
||||
callbacks: ["prometheus"]
|
||||
cache: true
|
||||
cache_params:
|
||||
type: "redis"
|
||||
Loading…
Add table
Reference in a new issue