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

Update README.md

Browse source
This commit is contained in:
Ishaan Jaff 2023-11-20 12:52:10 -08:00 • committed by GitHub
parent c1620fb775
commit 32a0ae5eb2
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 38 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

38
README.md
View file

@ -79,6 +79,44 @@ for chunk in result:
print(chunk['choices'][0]['delta']) print(chunk['choices'][0]['delta'])
``` ```
# Router - load balancing([Docs](https://docs.litellm.ai/docs/routing))
LiteLLM allows you to load balance between multiple deployments (Azure, OpenAI). It picks the deployment which is below rate-limit and has the least amount of tokens used.
```python
from litellm import Router
model_list = [{ # list of model deployments
"model_name": "gpt-3.5-turbo", # model alias
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-v-2", # actual model name
"api_key": os.getenv("AZURE_API_KEY"),
"api_version": os.getenv("AZURE_API_VERSION"),
"api_base": os.getenv("AZURE_API_BASE")
}
}, {
"model_name": "gpt-3.5-turbo",
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-functioncalling",
"api_key": os.getenv("AZURE_API_KEY"),
"api_version": os.getenv("AZURE_API_VERSION"),
"api_base": os.getenv("AZURE_API_BASE")
}
}, {
"model_name": "gpt-3.5-turbo",
"litellm_params": { # params for litellm completion/embedding call
"model": "gpt-3.5-turbo",
"api_key": os.getenv("OPENAI_API_KEY"),
}
}]
router = Router(model_list=model_list)
# openai.ChatCompletion.create replacement
response = await router.completion(model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hey, how's it going?"}])
print(response)
```
## OpenAI Proxy - ([Docs](https://docs.litellm.ai/docs/simple_proxy)) ## OpenAI Proxy - ([Docs](https://docs.litellm.ai/docs/simple_proxy))
**If you want to use non-openai models in an openai code base**, you can use litellm proxy. Create a server to call 100+ LLMs (Huggingface/Bedrock/TogetherAI/etc) in the OpenAI ChatCompletions & Completions format **If you want to use non-openai models in an openai code base**, you can use litellm proxy. Create a server to call 100+ LLMs (Huggingface/Bedrock/TogetherAI/etc) in the OpenAI ChatCompletions & Completions format