Releases: BerriAI/litellm
Releases · BerriAI/litellm
v1.30.1
docs(team_based_routing.md): add docs on team based routing by @krrishdholakia
fix(proxy_server.py): fix model alias map + add back testing by @krrishdholakia
Full Changelog: v1.30.0...v1.30.1
v1.30.0
What's Changed
- feat(proxy_server.py): team based model aliases by @krrishdholakia in #2377
Full Changelog: v1.29.7...v1.30.0
v1.29.7
⚡️LiteLLM Proxy 100+ LLMs, Track Number of Requests, Avg Latency Per Model Deployment
🛠️ High Traffic Fixes - Fix for DB connection limit hits when model fallbacks occur
🚀 High Traffic Fixes - /embedding - bug "Dictionary changed size during iteration"
⚡️ High Traffic Fixes - Switch off --detailed_debug in default Dockerfile. Users will need to opt in to viewing --detailed_debug logs. (This led to a 5% decrease in avg latency across 1K concurrent calls)
📖 Docs - Fixes for /user/new on LiteLLM Proxy Swagger (show how to set tpm/rpm limits per user) https://docs.litellm.ai/docs/proxy/virtual_keys#usernew
⭐️ Admin UI - separate latency, num requests graphs for model deployments https://docs.litellm.ai/docs/proxy/ui
What's Changed
- (Fix) High Traffic Fix - handle litellm circular ref error by @ishaan-jaff in #2363
- (feat) admin UI show model avg latency, num requests by @ishaan-jaff in #2367
- (fix) admin UI swagger by @ishaan-jaff in #2371
- [FIX] 🐛 embedding - "Dictionary changed size during iteration" Debug Log by @ishaan-jaff in #2378
- [Fix] Switch off detailed_debug in default docker by @ishaan-jaff in #2375
- feat(proxy_server.py): retry if virtual key is rate limited by @krrishdholakia in #2347
- fix(caching.py): add s3 path as a top-level param by @krrishdholakia in #2379
Full Changelog: v1.29.4...v1.29.7
v1.29.5
What's Changed
- [Fix] Fix Batch Updating User DB by @ishaan-jaff in #2340
- [FIX] pydantic warnings by @ishaan-jaff in #2343
- (fix) bug importing litellm on python 3.8 by @ishaan-jaff in #2344
- [Fix] Better debugging with alerts by @ishaan-jaff in #2341
- (fix) Update Team DB by @ishaan-jaff in #2345
Full Changelog: v1.29.3...v1.29.5
v1.29.4
What's Changed
- [Fix] Fix Batch Updating User DB by @ishaan-jaff in #2340
- [FIX] pydantic warnings by @ishaan-jaff in #2343
- (fix) bug importing litellm on python 3.8 by @ishaan-jaff in #2344
- [Fix] Better debugging with alerts by @ishaan-jaff in #2341
- (fix) Update Team DB by @ishaan-jaff in #2345
Full Changelog: v1.29.3...v1.29.4
v1.29.3
What's Changed
- Claude 3 bedrock access by @krrishdholakia in #2326
- Disable special token restriction for claude ai by @xihajun in #2310
New Contributors
Full Changelog: v1.29.1...v1.29.3
v1.29.1
Claude-3 Live NOW (with Tool calling + Vision)
LiteLLM Proxy - Track Avg latency + num requests per model deployment on Admin UI
Admin UI: https://docs.litellm.ai/docs/proxy/ui

What's Changed
- claude 3 bedrock integrations by @krrishdholakia in #2325
- fix(anthropic.py): Support Claude 3 Vision + Tool Calling by @krrishdholakia in #2320
- Proxy - show api base on Admin UI by @ishaan-jaff in #2323
- [Fix] Maintain Claude-2, Claude-Instant-1 by @ishaan-jaff in #2321
Full Changelog: v1.28.13...v1.29.1
v1.28.13
New Models
Anthropic Claude-3, Docs here: https://docs.litellm.ai/docs/providers/anthropic

What's Changed
- Add support for Bedrock Mistral models by @ti3x in #2290
- [FEAT]- add claude 3 by @ishaan-jaff in #2315
New Contributors
Full Changelog: v1.28.11...v1.28.13
v1.28.11
What's Changed
- feat(proxy_server.py): enable
/organizations/new,/organization/infoand/budget/infoendpoints by @krrishdholakia in #2300 - fix(proxy_server.py): actual implementation of slack soft budget alerting by @krrishdholakia in #2305
Full Changelog: v1.28.10...v1.28.11
v1.28.10
Budget Alerts
Alerts when a project will exceed it’s planned limit
Set Budget Alerts here: https://docs.litellm.ai/docs/proxy/budget_alerts
What's Changed
- [FEAT] set soft_budgets on keys by @ishaan-jaff in #2302
- [FEAT] Admin UI - set soft budgets on Admin UI by @ishaan-jaff in #2303
- [FEAT] test slack alerts on LiteLLM UI by @ishaan-jaff in #2304
Full Changelog: v1.28.9...v1.28.10

