Add LiteLLM proxy service and config#374
Merged
Merged
Conversation
Introduce an OpenAI-compatible LiteLLM proxy: add llm_proxy service to .docker/compose.controller.yaml (port 8080, depends on llm_server, mounts config file, uses LITELLM_MASTER_KEY for client auth and LLM_API_KEY for backend auth). Add LLM_API_KEY and LITELLM_MASTER_KEY to .docker/.env-template (with generation hint). Add .docker/llm/litellm_config.yaml listing model_name -> backend mappings and general master_key/setting entries to route requests to various llm_server endpoints.
NoorChasib
requested review from
Bottle7,
antsand and
dbarkowsky
as code owners
Rename the LLM service identifier from 'llm_server' to 'llm-server' across Docker config and scripts. Updated .docker/compose.controller.yaml comments and service name, adjusted dependency for llm_proxy, changed example usages in .docker/.env-template, updated api_base URLs in .docker/llm/litellm_config.yaml, and updated printed endpoints/health URLs in .docker/llm/entrypoint.sh. Also remove .docker/llm/Caddyfile and .docker/llm/models.json (static reverse-proxy and model list files) as part of this cleanup.
Standardize the LLM service name by renaming llm-server to llm_server across Docker files and scripts. Changes include: - .docker/.env-template: update comment to reference llm_server. - .docker/compose.controller.yaml: update example usage, service key, and llm_proxy depends_on entry to llm_server. - .docker/llm/entrypoint.sh: update printed API and health endpoints to use host llm_server. This ensures consistent service naming for compose, networking, and scripts.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Introduce an OpenAI-compatible LiteLLM proxy: add llm_proxy service to .docker/compose.controller.yaml (port 8080, depends on llm_server, mounts config file, uses LITELLM_MASTER_KEY for client auth and LLM_API_KEY for backend auth). Add LLM_API_KEY and LITELLM_MASTER_KEY to .docker/.env-template (with generation hint). Add .docker/llm/litellm_config.yaml listing model_name -> backend mappings and general master_key/setting entries to route requests to various llm_server endpoints.
🎯 Summary
ZUBA-
🔰 Checklist