Litellm

What's Changed
https://docs.litellm.ai/docs/simple_proxy
* [Feat] Proxy - Access Key metadata in callbacks by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1484
- Access Proxy Key metadata in callbacks
- Access Endpoint URL in calbacks - you can see if /chat/completions, /embeddings, /image/generation etc is called
- Support for Langfuse Tags, We log request metadata as langfuse tags

PS. no keys leaked - these are keys to my local proxy
<img width="529" alt="Screenshot 2024-01-17 at 6 10 10 PM" src="https://github.com/BerriAI/litellm/assets/29436595/991744d2-2d83-49a0-bf31-c76d9d7bdaf4">

Support for model access groups
Use this if you have keys with access to specific models, and you want to give all them access to a new model.

You can now assign keys access to model groups, and add new models to that group via the config.yaml - https://docs.litellm.ai/docs/proxy/users#grant-access-to-new-model

bash
curl --location 'http://localhost:8000/key/generate' \
-H 'Authorization: Bearer <your-master-key>' \
-H 'Content-Type: application/json' \
-d '{"models": ["beta-models"], 👈 Model Access Group
"max_budget": 0,}'


Langfuse Tags logged:
<img width="949" alt="Screenshot 2024-01-17 at 6 11 36 PM" src="https://github.com/BerriAI/litellm/assets/29436595/a28af993-7414-405a-b5f3-63562caecd40">
* feat(proxy_server.py): support model access groups by krrishdholakia in https://github.com/BerriAI/litellm/pull/1483



**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.17.18...v1.18.0

What's Changed
* [Feat] Proxy - Access Key metadata in callbacks by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1484
* feat(proxy_server.py): support model access groups by krrishdholakia in https://github.com/BerriAI/litellm/pull/1483


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.17.18...v1.18.0

What's Changed
* [Fix+Test] /key/delete functions by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1482 Added extensive testing + improved swagger


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.17.17...v1.17.18

What's Changed
* [Test] Proxy - Unit Test proxy key gen by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1478

Testing + fixes for: https://docs.litellm.ai/docs/proxy/virtual_keys

1. Generate a Key, and use it to make a call
2. Make a call with invalid key, expect it to fail
3. Make a call to a key with invalid model - expect to fail
4. Make a call to a key with valid model - expect to pass
5. Make a call with key over budget, expect to fail
6. Make a streaming chat/completions call with key over budget, expect to fail
7. Make a call with an key that never expires, expect to pass
8. Make a call with an expired key, expect to fail


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.17.16...v1.17.17

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.17.15...v1.17.16

What's Changed
* [Feat] Support Azure GPT-4 Vision Enhancements by ishaan-jaff in https://github.com/BerriAI/litellm/pull/1475

Usage - with Azure Vision enhancements
Docs: https://docs.litellm.ai/docs/providers/azure#usage---with-azure-vision-enhancements

Note: **Azure requires the `base_url` to be set with `/extensions`**

Example
python
base_url=https://gpt-4-vision-resource.openai.azure.com/openai/deployments/gpt-4-vision/extensions
base_url="{azure_endpoint}/openai/deployments/{azure_deployment}/extensions"


**Usage**
python
import os
from litellm import completion

os.environ["AZURE_API_KEY"] = "your-api-key"

azure call
response = completion(
model="azure/gpt-4-vision",
timeout=5,
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "Whats in this image?"},
{
"type": "image_url",
"image_url": {
"url": "https://avatars.githubusercontent.com/u/29436595?v=4"
},
},
],
}
],
base_url="https://gpt-4-vision-resource.openai.azure.com/openai/deployments/gpt-4-vision/extensions",
api_key=os.getenv("AZURE_VISION_API_KEY"),
enhancements={"ocr": {"enabled": True}, "grounding": {"enabled": True}},
dataSources=[
{
"type": "AzureComputerVision",
"parameters": {
"endpoint": "https://gpt-4-vision-enhancement.cognitiveservices.azure.com/",
"key": os.environ["AZURE_VISION_ENHANCE_KEY"],
},
}
],
)


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.17.14...v1.17.15

Fixes bug for mistral ai api optional param mapping

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.17.13...v1.17.14