v1.90.1 - Vertex Batch Uploads & Key Redaction
Deploy this version​
- Docker
- Pip
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
docker.litellm.ai/berriai/litellm:1.90.1
pip install litellm==1.90.1
v1.90.1 is a patch release on top of v1.90.0. It backports three fixes onto the 1.90.x line: Vertex AI batch-file uploads switch to a single media upload so large uploads no longer fail with 499 errors, OpenAI→Vertex batch JSONL uploads stream instead of buffering in memory, and the API key is redacted from /key/info client error messages. The bundled litellm-enterprise package is bumped to 0.1.43.post1.
What's Changed​
- fix(vertex_ai/files): single media upload for batch files to fix 499s on large uploads - PR #31653
- fix(vertex/files): stream OpenAI->Vertex batch JSONL uploads - PR #31036
- fix(proxy/client): redact api key from key/info client error messages - PR #31342
Full Changelog​
https://github.com/BerriAI/litellm/compare/v1.90.0...v1.90.1