v1.20.8

What's Changed

• [Feat] Add Admin UI on Proxy Server (Static Web App) by @ishaan-jaff in #1726
• [Fix-UI] If user is already logged in using SSO, set allow_user_auth: True by @ishaan-jaff in #1728
• feat: add langfuse cost tracking by @maxdeichmann in #1704
• [Fix] UI - Use jwts by @ishaan-jaff in #1730
• fix(utils.py): support checking if user defined max tokens exceeds model limit by @krrishdholakia in #1729

Full Changelog: v1.20.7...v1.20.8

v1.20.7

What's Changed

• [Feat-UI] Make SSO Optional by @ishaan-jaff in #1697
• fix(proxy_server.py): speed up proxy startup time by @krrishdholakia in #1696
• feat(proxy_server.py): enable cache controls per key + no-store cache flag by @krrishdholakia in #1700
• fix(proxy_server.py): don't log sk-.. as part of logging object by @krrishdholakia in #1720
• [Feat] Langfuse log embeddings by @ishaan-jaff in #1722
  

Full Changelog: v1.20.6...v1.20.7

v1.20.6

What's Changed

• [Fix] Graceful rejection of token input for AWS Embeddings API by @ishaan-jaff in #1685
• fix(main.py): register both model name and model name with provider by @krrishdholakia in #1690
• [Feat] LiteLLM Proxy: MSFT SSO Login by @ishaan-jaff in #1691
• Fixes for model cost check and streaming by @krrishdholakia in #1693

[Feat] Set OpenAI organization for litellm.completion, Proxy Config by @ishaan-jaff in #1689

Full Changelog: v1.20.5...v1.20.6

v1.20.5

What's Changed

• [Feat-UI] Add form for /key/gen params by @ishaan-jaff in #1678
• build(proxy_cli.py): make running gunicorn an optional cli arg by @krrishdholakia in #1675
• Change quota project to the correct project being used for the call by @eslamkarim in #1657

New Contributors

• @eslamkarim made their first contribution in #1657

Full Changelog: v1.20.3...v1.20.5

v1.20.3

What's Changed

• Fix mistral's prompt template by @sa- in #1661
• [UI] Improve LiteLLM admin UI by @ishaan-jaff in #1669
• [Feat] return litellm version in health/readiness by @ishaan-jaff in #1673
• [Fix]Litellm patch dynamoDB by @ishaan-jaff in #1676

New Contributors

• @sa- made their first contribution in #1661

Full Changelog: v1.20.2...v1.20.3

v1.20.2

LiteLLM Proxy UI 2.0 Launch

• Team members Create, delete proxy API Keys
• Team members sign in using Google SSO

Doc on Setting Up Admin UI: https://docs.litellm.ai/docs/proxy/ui
Link to Admin UI: https://litellm-dashboard.vercel.app/

UI Demo

• feat(main.py): support auto-infering mode if not set by @krrishdholakia in #1652
• build(ui/litellm-dashboard): initial commit of litellm dashboard by @krrishdholakia in #1649

Full Changelog: v1.20.1...v1.20.2

v1.20.1

What's Changed

[Feat] add google login to litellm proxy by @ishaan-jaff in #1650

[BETA] SSO Google Login to your Proxy through LiteLLM UI, View, Manage Proxy API Keys

• Allow optional usage of the tls encryption for SMTP by @scampion in #1648
  Full Changelog: v1.20.0...v1.20.1

v1.20.0

What's Changed

• feat(proxy_server.py): save abbreviated key name if allow_user_auth enabled by @krrishdholakia in #1642
• Litellm image gen cost tracking proxy by @krrishdholakia in #1646

Full Changelog: v1.19.6...v1.20.0

v1.19.6

What's Changed

• fix(utils.py): fix sagemaker cost tracking for streaming by @krrishdholakia in #1618
• [FIX] print verbose take only one argument by @scampion in #1630
• [Fix] SpendLogs stop logging model params by @ishaan-jaff in #1634
• [Feat] support dimensions OpenAI embedding param by @ishaan-jaff in #1635
• [FIX] Fixes Bug where Keys could cross their Key max_budget by @ishaan-jaff in #1640
• [Feat] Improve alert formats for Key budgets by @ishaan-jaff in #1644
• feat(utils.py): support region based pricing for bedrock + use bedrock's token counts if given by @krrishdholakia in #1641

New Contributors

• @scampion made their first contribution in #1630

Full Changelog: v1.19.4...v1.19.6

v1.19.4

What's Changed

New OpenAI Models

text-embedding-3-large,

text-embedding-3-small

gpt-4-0125-preview

Usage - New Embedding models

response = litellm.embedding(
    model="text-embedding-3-large",
    input=["good morning from litellm", "this is another item"],
    metadata={"anything": "good day"},
)

response = litellm.embedding(
    model="text-embedding-3-small",
    input=["good morning from litellm", "this is another item"],
    metadata={"anything": "good day"},
)

Usage - gpt-4-0125-preview

response = litellm.completion(
    model="gpt-4-0125-preview",
    messages=messages,
    max_tokens=10,
)

• fix(main.py): allow vertex ai project and location to be set in completion() call by @krrishdholakia in #1623
• [UI] Admin UI improvements by @ishaan-jaff in #1625

Full Changelog: v1.19.3...v1.19.4