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

simplify setup

Browse source
This commit is contained in:
ishaan-jaff 2023-08-31 08:27:59 -07:00
parent e725b926e1
commit 48968b896d
1 changed files with 0 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

29
docs/my-website/docs/tutorials/ab_test_llms.md
View file

@ -52,35 +52,6 @@ git clone https://github.com/BerriAI/litellm/
cd litellm/cookbook/llm-ab-test-server cd litellm/cookbook/llm-ab-test-server
``` ```
### Define LLMs with their A/B test ratios
In main.py set select the LLMs you want to AB test in `llm_dict` (and remember to set their API keys in the .env)!
We support 5+ providers and 100+ LLMs: https://docs.litellm.ai/docs/completion/supported
```python
llm_dict = {
"gpt-4": 0.2,
"together_ai/togethercomputer/llama-2-70b-chat": 0.4,
"claude-2": 0.2,
"claude-1.2": 0.2
}
```
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 - https://docs.litellm.ai/docs/completion/supported
os.environ["OPENAI_API_KEY"] = ""
os.environ["TOGETHERAI_API_KEY"] = ""
os.environ["ANTHROPIC_API_KEY"] = ""
# openai call
response = completion(model="gpt-3.5-turbo", messages=messages)
# cohere call
response = completion(model="together_ai/togethercomputer/llama-2-70b-chat", messages=messages)
# anthropic
response = completion(model="claude-2", messages=messages)
```
### Run the Server ### Run the Server
``` ```