v1.22.8

What's Changed

• [Fix] UI - Security - Litellm UI Keys meant for litellm-dashboard shouldn't be allowed to make non-management related requests by @ishaan-jaff in #1836
• Fix admin UI title and description by @ushuz in #1842
• fix(langfuse.py): support logging failed llm api calls to langfuse by @krrishdholakia in #1837
• [Feat] Proxy set upperbound params for key/generate by @ishaan-jaff in #1844
• build(requirements.txt): update the proxy requirements.txt by @krrishdholakia in #1846

Full Changelog: v1.22.5...v1.22.8

v1.22.5

What's Changed

• Re-raise exception in async ollama streaming by @vanpelt in #1750
• Add a Helm chart for deploying LiteLLM Proxy by @ShaunMaher in #1602
• Update Perplexity models in model_prices_and_context_window.json by @toniengelhardt in #1826
• (feat) Add sessionId for Langfuse. by @Manouchehri in #1828
• [Feat] Sync model_prices_and_context_window.json and litellm/model_prices_and_context_window_backup.json by @ishaan-jaff in #1834

New Contributors

• @vanpelt made their first contribution in #1750

Full Changelog: v1.22.3...v1.22.5

v1.22.3

What's Changed

• feat(utils.py): support cost tracking for openai/azure image gen models by @krrishdholakia in #1805

Full Changelog: v1.22.2...v1.22.3

v1.22.2

Admin UI 🤠

• view spend, budget for signed in user
• view daily spend, top users for a key
  

What's Changed

• Litellm vertex ai gecko support by @krrishdholakia in #1794
• [Feat] Allow setting user roles for UserTable by @ishaan-jaff in #1795
• fix(vertex_ai.py): add async embedding support for vertex ai by @krrishdholakia in #1797
• [UI] Show UserID, user_role on UI by @ishaan-jaff in #1800
• feat(bedrock.py): add stable diffusion image generation support by @krrishdholakia in #1799
• [UI] view role on ui by @ishaan-jaff in #1801
• [Feat] UI view spend / budget per user by @ishaan-jaff in #1803
• fix(vertex_ai.py): treat vertex ai high-traffic error as a rate limit error - allows user-controlled backoff logic to work here by @krrishdholakia in #1802
• [UI] View Key Spend Reports 🤠 by @ishaan-jaff in #1807
• Support caching individual items in embedding list (Async embedding only) by @krrishdholakia in #1809

Full Changelog: v1.21.7...v1.22.2

v1.21.7

Full Changelog: v1.21.6...v1.21.7

v1.21.6

What's Changed

• Litellm cost tracking caching fixes (should be 0.0) by @krrishdholakia in #1786
• [Fix] /key/delete + add delete cache keys by @ishaan-jaff in #1788

Full Changelog: v1.21.5...v1.21.6

v1.21.5

What's Changed

⭐️ [Feat] Show correct provider in exceptions - for Mistral API, PerplexityAPI, Anyscale, XInference by @ishaan-jaff in #1765, #1776

(Thanks @dhruv-anand-aintech for the issue/help)
Exceptions for Mistral API, PerplexityAPI, Anyscale, XInference now show the correct provider name, before they would show OPENAI_API_KEY is missing when using PerplexityAI

exception:  PerplexityException - Traceback (most recent call last):
  File "/Users/ishaanjaffer/Github/litellm/litellm/llms/perplexity.py", line 349, in completion
    raise e
  File "/Users/ishaanjaffer/Github/litellm/litellm/llms/perplexity.py", line 292, in completion
    perplexity_client = perplexity(
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/perplexity/_client.py", line 98, in __init__
    raise perplexityError(
perplexity.perplexityError: The api_key client option must be set either by passing api_key to the client or by setting the PERPLEXITY_API_KEY environment variable

• fix(view_key_table_tsx): show abbreviated key name instead of hashed token by @krrishdholakia in #1782
• fix(main.py): for health checks, don't use cached responses by @krrishdholakia in #1785

Full Changelog: v1.21.4...v1.21.5

v1.21.4

What's Changed

• (feat) langfuse set generation_id to chatcmpl-response ID by @ishaan-jaff in #1780

* s3 logger - Improve filename to allow easier sorting by @Manouchehri in https://github.com//pull/1766 * fix(utils.py): override default success callbacks with dynamic callbacks if set by @krrishdholakia in https://github.com//pull/1761 * Litellm security fix allow user auth by @krrishdholakia in https://github.com//pull/1781

Full Changelog: v1.21.1...v1.21.4

v1.21.1

What's Changed

• Allow to specify user email created via /user/new by @scampion in #1759

Full Changelog: v1.21.0...v1.21.1

v1.21.0

What's Changed

• Set OpenAPI API version metadata by @ushuz in #1733
• fix(router.py): support http and https proxys by @krrishdholakia in #1497
• (fix) UI Proxy - Fix accidental redirect by @Manouchehri in #1744
• [Feat-UI] Quick spin Up - remove proxyBaseUrl by @ishaan-jaff in #1746
• (ui) allow auth without sso by @ishaan-jaff in #1747
• [Fix] user_custom_auth fixes when user passed bad api_keys by @ishaan-jaff in #1748
• Update model_prices_and_context_window.json - added gpt-3.5-turbo-0125 by @7flash in #1752
• feat(utils.py): Set team id specific params in config.yaml by @krrishdholakia in #1754
• feat(vertex_ai.py): vertex ai model garden support by @krrishdholakia in #1749

New Contributors

• @ushuz made their first contribution in #1733
• @7flash made their first contribution in #1752

Full Changelog: v1.20.9...v1.21.0