tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-23 22:27:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs update

Browse Source
This commit is contained in:
ishaan-jaff
2023-08-29 10:09:46 -07:00
parent 1bf5302117
commit 85543ac0da
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/my-website/docs/tutorials/fallbacks.md
+2 -2
View File
@@ -8,12 +8,12 @@ To use fallback models with `completion()`, specify a list of models in the `fal
The `fallbacks` list should include the primary model you want to use, followed by additional models that can be used as backups in case the primary model fails to provide a response.
```python
response = completion(model="bad-model", messages=messages, fallbacks=["gpt-3.5-turbo" "command-nightly"])
response = completion(model="bad-model", fallbacks=["gpt-3.5-turbo" "command-nightly"], messages=messages)
```
## How does `completion_with_fallbacks()` work
The `completion_with_fallbacks()` function attempts a completion call using the primary model. If the primary model fails or encounters an error, it automatically tries the fallback models in the specified order. This ensures a response even if the primary model is unavailable.
The `completion_with_fallbacks()` function attempts a completion call using the primary model specified as `model` in `completion()`. If the primary model fails or encounters an error, it automatically tries the fallback models in the specified order. This ensures a response even if the primary model is unavailable.
### Output from calls
```