fix: litellm embedding dimension adapts

[MaojiaSheng]

No description provided.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ MaojiaSheng
❌ openviking

---

openviking seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[github-actions]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 2 🔵🔵⚪⚪⚪

🏅 Score: 90

🧪 No relevant tests

🔒 No security concerns identified

✅ No TODO sections

🔀 No multiple PR themes

⚡ Recommended focus areas for review Edge Case Handling The current code only truncates vectors longer than the target dimension. If the embedding model returns a vector shorter than the configured dimension, downstream code expecting exactly dimension elements may break. Consider either padding with zeros or raising an explicit error in this case. def _truncate_vector(self, vector: List[float]) -> List[float]: """Truncate vector to target dimension if needed. Args: vector: Input vector from API Returns: Truncated vector if dimension is set and smaller than input, otherwise original vector """ if self.dimension is not None and len(vector) > self.dimension: return vector[: self.dimension] return vector

[github-actions]

PR Code Suggestions ✨

No code suggestions found for the PR.