Litellm

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

New Contributors
* scampion made their first contribution in https://github.com/BerriAI/litellm/pull/1630

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.19.4...v1.19.6

What's Changed
New OpenAI Models
`text-embedding-3-large`,
`text-embedding-3-small`
`gpt-4-0125-preview`
Usage - New Embedding models
python
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`
python
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 https://github.com/BerriAI/litellm/pull/1623
* [UI] Admin UI improvements by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1625


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.19.3...v1.19.4

What's Changed
* [Feat] Alerts for Proxy Budgets by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1615
Alerts for Proxy Budget

15% of Total proxy budget left
<img width="473" alt="Screenshot 2024-01-25 at 11 36 17 AM" src="https://github.com/BerriAI/litellm/assets/29436595/bd792cc1-6a53-41b8-9f03-6e8d82ef0970">

Proxy Total Budget Crossed
<img width="313" alt="Screenshot 2024-01-25 at 11 36 10 AM" src="https://github.com/BerriAI/litellm/assets/29436595/46ba1138-a5b4-47b2-8503-e600abe1478b">



**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.19.2...v1.19.3

What's Changed
* [Feat] Add cache_key in SpendLogs Table by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1604
* [Feat] Proxy - Spend Tracking, Set Global Budget For the Proxy + Reset the budget by krrishdholakia in https://github.com/BerriAI/litellm/pull/1603
* [Fix] fix(ollama_chat.py): fix default token counting for ollama chat


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.19.0...v1.19.2

What's Changed
* [Feat] Proxy Admin UI - View Spend Per User by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1588
* [Feat] Proxy - Improve Slack Alerting by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1601
<img width="607" alt="Screenshot 2024-01-24 at 4 42 15 PM" src="https://github.com/BerriAI/litellm/assets/29436595/dacd9701-15c4-47b7-ad64-f493fb4e57c9">

* [Test] Proxy - writing spend logs table by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1591
* [Fix] SpendLogs stop logging messages, response in SpendLogs by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1597
* feat(proxy_server.py): enable returning spend logs by api key by krrishdholakia in https://github.com/BerriAI/litellm/pull/1590
* feat(proxy_server.py): support global budget and resets by krrishdholakia in https://github.com/BerriAI/litellm/pull/1600



**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.18.13...v1.19.0

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.18.12...v1.18.13

Fixes [Bug]: Strange Behavior in HuggingChat (Chat-UI) https://github.com/BerriAI/litellm/issues/1222 nigh8w0lf gururise can you confirm it's fixed for TogetherAI ?