mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-07 07:58:09 +00:00
ab78459097
Response transformation crashed with TypeError when counting tokens for multimodal (dict-shaped) embedding inputs, since encoding.encode() was called directly on the dict instead of its text parts. Also removed a dead, equally-buggy duplicate of the same loop in _transform_response. Separately, the embeddings guardrail handler silently skipped multimodal dict inputs instead of scanning them, letting prohibited text/image content bypass the configured guardrail. It now extracts and scans the text parts while leaving image parts untouched.
12 lines
256 B
YAML
12 lines
256 B
YAML
services:
|
|
- type: web
|
|
name: openai-proxy
|
|
runtime: image
|
|
image:
|
|
url: ghcr.io/berriai/litellm:main-stable
|
|
envVars:
|
|
- key: PORT
|
|
value: 4000
|
|
numInstances: 1
|
|
healthCheckPath: /health/liveliness
|
|
autoDeploy: true
|