search

BerriAI / litellm

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
https://docs.litellm.ai/docs/
Other
14.07k stars 1.66k forks source link

(Feat) DB Schema change - add `custom_llm_provider` in SpendLogs #6823

Closed ishaan-jaff closed 13 hours ago

ishaan-jaff commented 2 days ago

Title

Relevant issues

Type

🆕 New Feature 🐛 Bug Fix 🧹 Refactoring 📖 Documentation 🚄 Infrastructure ✅ Test

Changes

[REQUIRED] Testing - Attach a screenshot of any new tests passing locall

If UI changes, send a screenshot/GIF of working UI fixes

vercel[bot] commented 2 days ago

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

Name Status Preview Comments Updated (UTC)
litellm ✅ Ready (Inspect) Visit Preview 💬 Add feedback Nov 20, 2024 4:28am
krrishdholakia commented 1 day ago

@ishaan-jaff is this necessary?

We log the 'model_id' which should allow us to get the custom_llm_provider for any specific log

Asking as i believe we should be trying to minimize size of table

ishaan-jaff commented 13 hours ago

Asking as i believe we should be trying to minimize size of table

Yeah I agree with your feedback, I don't think this is necessary. Will wait for the user to complain if this is really something they need. Since they can track this on prometheus already