phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs(reliable_completions.md): improve headers for easier searching

Browse source
This commit is contained in:
Krrish Dholakia 2024-06-26 08:09:14 -07:00
parent f9407aaefc
commit 09f4eb7617
2 changed files with 11 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

14
docs/my-website/docs/completion/reliable_completions.md
View file

@ -31,9 +31,15 @@ response = completion(
) )
``` ```
## Fallbacks ## Fallbacks (SDK)
### Context Window Fallbacks :::info
[See how to do on PROXY](../proxy/reliability.md)
:::
### Context Window Fallbacks (SDK)
```python ```python
from litellm import completion from litellm import completion
@ -43,7 +49,7 @@ messages = [{"content": "how does a court case get to the Supreme Court?" * 500,
completion(model="gpt-3.5-turbo", messages=messages, context_window_fallback_dict=ctx_window_fallback_dict) completion(model="gpt-3.5-turbo", messages=messages, context_window_fallback_dict=ctx_window_fallback_dict)
``` ```
### Fallbacks - Switch Models/API Keys/API Bases ### Fallbacks - Switch Models/API Keys/API Bases (SDK)
LLM APIs can be unstable, completion() with fallbacks ensures you'll always get a response from your calls LLM APIs can be unstable, completion() with fallbacks ensures you'll always get a response from your calls
@ -69,7 +75,7 @@ response = completion(model="azure/gpt-4", messages=messages, api_key=api_key,
[Check out this section for implementation details](#fallbacks-1) [Check out this section for implementation details](#fallbacks-1)
## Implementation Details ## Implementation Details (SDK)
### Fallbacks ### Fallbacks
#### Output from calls #### Output from calls

2
litellm/llms/azure.py
View file

@ -902,7 +902,7 @@ class AzureChatCompletion(BaseLLM):
}, },
) )
if aembedding == True: if aembedding is True:
response = self.aembedding( response = self.aembedding(
data=data, data=data,
input=input, input=input,