[Feature] Auto Resolve Vector Store Embedding Model Config

[yuneng-jiang]

Relevant issues

The Milvus vector store requires these fields to be defined in the litellm_params: litellm_embedding_model and litellm_embedding_config.

Currently the UI allows the users to only choose an embedding model, but since we already have the config stored, we should automatically resolve the config for the user. This PR implements this feature

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

CI (LiteLLM team)

CI status guideline:

• 50-55 passing tests: main is stable with minor issues.
• 45-49 passing tests: acceptable but needs attention
• <= 40 passing tests: unstable; be careful with your merges and assess the risk.

• Branch creation CI run
  Link: https://app.circleci.com/pipelines/github/BerriAI/litellm/52027

• CI run for the last commit
  Link: https://app.circleci.com/pipelines/github/BerriAI/litellm/52028

• Merge / cherry-pick CI run
  Links:

Type

🆕 New Feature
✅ Test

Changes

Now queries through test vector store no longer throw a 500 while using milvus:

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
litellm	Ready	Preview, Comment	Dec 18, 2025 6:02am