fix(main.py): use model_api_key determined from get_api_key

[nobu007]

Title

fix(main.py): use model_api_key determined from get_api_key

Relevant issues

None

Type

🧹 Refactoring

Changes

• set model_api_key as api_key

Testing

1. export ANTHROPIC_API_KEY=XXX
2. use litellm.completion() without api_key.

import os
from litellm import completion

model="anthropic/claude-3-haiku-20240307"
messages = [{"role": "user", "content": "Hey! how's it going?"}]
response = completion(model=model, messages=messages)
print(response)

Notes

I thought this fix made it possible to read ANTHROPIC_API_KEY, but I can no longer reproduce it.
Perhaps one of the following would have worked:
In any case, I think it is better to include processing using model_api_key.

• LITELLM_LOCAL_MODEL_COST_MAP="True"
• It depends on message length or someting.

Pre-Submission Checklist (optional but appreciated):

• I have included relevant documentation updates (stored in /docs/my-website)

OS Tests (optional but appreciated):

• Tested on Windows
• Tested on MacOS
• Tested on Linux

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
litellm	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 6, 2024 8:47am