Litellm

What's Changed
* nit: added urls to pyproject.toml by ErikBjare in https://github.com/BerriAI/litellm/pull/1536
* ✨ Refresh Helm chart structure by Lunik in https://github.com/BerriAI/litellm/pull/2018
* [FIX] UI - fix method not allowed error by ishaan-jaff in https://github.com/BerriAI/litellm/pull/2041

* [FEAT] Set FastAPI root path by ishaan-jaff in https://github.com/BerriAI/litellm/pull/2039
> [!IMPORTANT]
> In a Kubernetes deployment, it's possible to utilize a shared DNS to host multiple applications by modifying the virtual service

👉 Set `SERVER_ROOT_PATH` in your .env and this will be set as your server root path
Docs here: https://docs.litellm.ai/docs/proxy/deploy#advanced-deployment-settings

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.25.0...v1.25.1

What's Changed
* feat(llama_guard.py): add llama guard support for content moderation + new `async_moderation_hook` endpoint by krrishdholakia in https://github.com/BerriAI/litellm/pull/2031
* fix for importllib compatibility issue for python 3.8 by sorokine in https://github.com/BerriAI/litellm/pull/2017


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.24.6...v1.25.0

What's Changed
* [Docs] Show how to use litellm GHCR as a base image by ishaan-jaff in https://github.com/BerriAI/litellm/pull/2019
* ✨ Allow to configure scopes in generic SSO by Lunik in https://github.com/BerriAI/litellm/pull/2020
* [FEAT] Generic SSO - allow user to specify attribute names by ishaan-jaff in https://github.com/BerriAI/litellm/pull/2021
* fix(utils.py): support image gen logging to langfuse by krrishdholakia in https://github.com/BerriAI/litellm/pull/2025
* [FEAT] Track spend per tag by ishaan-jaff in https://github.com/BerriAI/litellm/pull/2004
* [FEAT] View spend per tag by ishaan-jaff in https://github.com/BerriAI/litellm/pull/2012





Usage - Tracking Spend Per Tag

Step 1. Tag your /chat/completions request to litellm proxy
curl
curl --location 'http://0.0.0.0:8000/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"messages": [
{
"role": "user",
"content": "what llm are you"
}
],
"metadata": {"tags": ["model-anthropic-claude-v2.1", "app-ishaan-prod"]}
}'


Step 2. View spend per tag

curl
curl -X GET "http://0.0.0.0:4000/spend/tags" \
-H "Authorization: Bearer sk-1234"


json
[
{
"individual_request_tag": "model-anthropic-claude-v2.1",
"log_count": 6,
"total_spend": 0.000672
},
{
"individual_request_tag": "app-ishaan-local",
"log_count": 4,
"total_spend": 0.000448
},
{
"individual_request_tag": "app-ishaan-prod",
"log_count": 2,
"total_spend": 0.000224
}
]



New Contributors
* Lunik made their first contribution in https://github.com/BerriAI/litellm/pull/2020

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.24.5...v1.24.6

What's Changed
* feat(langfuse.py): support langfuse prompt management by krrishdholakia in https://github.com/BerriAI/litellm/pull/1995
* chore: update NLP Cloud model pricing by toniengelhardt in https://github.com/BerriAI/litellm/pull/2007
* Update NLP Cloud max_tokens by toniengelhardt in https://github.com/BerriAI/litellm/pull/2009

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.24.3...v1.24.5

What's Changed
[FEAT] Track LLM spend per team by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1996
<img width="556" alt="Screenshot 2024-02-15 at 10 51 54 PM" src="https://github.com/BerriAI/litellm/assets/29436595/1101385e-f230-4cfa-a449-769cbff33788">

[FEAT] Proxy - use custom API endpoints as callbacks by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1986
docs: https://docs.litellm.ai/docs/proxy/logging#custom-callback-apis-async

[FEAT] Track team_id in langfuse tags, callback metadata by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1993
<img width="1003" alt="Screenshot 2024-02-15 at 8 58 29 PM" src="https://github.com/BerriAI/litellm/assets/29436595/2135ebcc-4cf0-43e3-9d4c-178bdb80f71b">

[Fix] Admin UI Chat Tab by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1997
* feat(proxy_server.py): support key-level permissions for pii masking by krrishdholakia in https://github.com/BerriAI/litellm/pull/1991


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.24.1...v1.24.3

What's Changed
* feat(proxy_server.py): `/team/new` and `/team/info` endpoints for team management by krrishdholakia in https://github.com/BerriAI/litellm/pull/1979
* Implements aioboto3 for sagemaker by krrishdholakia in https://github.com/BerriAI/litellm/pull/1952
* Update utils.py: switched from pkg_resources to importlib.resources for `filename` stored in the `os.environ(TIKTOKEN_CACHE_DIR)` by sorokine in https://github.com/BerriAI/litellm/pull/1947
* fix(redis.py): fix instantiating redis client from url by krrishdholakia in https://github.com/BerriAI/litellm/pull/1989
* Add support for Vertex AI custom models deployed on private endpoint by RenaLu in https://github.com/BerriAI/litellm/pull/1916

New Contributors
* sorokine made their first contribution in https://github.com/BerriAI/litellm/pull/1947
* RenaLu made their first contribution in https://github.com/BerriAI/litellm/pull/1916

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.23.16...v1.24.1