phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

docs update

Browse source
This commit is contained in:
ishaan-jaff 2023-08-25 21:26:54 -07:00
parent f969916498
commit c01709ad72
1 changed files with 17 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

17
cookbook/llm-ab-test-server/readme.md
View file

@ -39,6 +39,23 @@ llm_dict = {
} }
``` ```
All models defined can be called with the same Input/Output format using litellm `completion`
```python
from litellm import completion
# SET API KEYS in .env
# openai call
response = completion(model="gpt-3.5-turbo", messages=messages)
# cohere call
response = completion(model="command-nightly", messages=messages)
# anthropic
response = completion(model="claude-2", messages=messages)
```
After running the server all completion resposnes, costs and latency can be viewed on the LiteLLM Client UI
### LiteLLM Client UI
Litellm simplifies I/O with all models, the server simply makes a `litellm.completion()` call to the selected model Litellm simplifies I/O with all models, the server simply makes a `litellm.completion()` call to the selected model