Skip to content

Commit 2939658

Browse files
Update README.md
Co-authored-by: Wei-Lin Chiang <[email protected]>
1 parent e8f6bae commit 2939658

File tree

1 file changed

+1
-3
lines changed

1 file changed

+1
-3
lines changed

README.md

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -241,9 +241,7 @@ If the models do not show up, try to reboot the gradio web server.
241241

242242
Currently, Chatbot Arena is powered by FastChat. Here is how you can launch an instance of Chatbot Arena locally.
243243

244-
To support an API-based model, consider using the existing OpenAI api code for example.
245-
If the model is compatible with OpenAI APIs, then only modifying the configuration file is required without any additional code.
246-
For custom protocols, implementation of a streaming generator in [fastchat/serve/api_provider.py](https://github.com/lm-sys/FastChat/blob/main/fastchat/serve/api_provider.py) is required, following the provided examples. Currently, FastChat is compatible with OpenAI, Anthropic, Google Vertex AI, Mistral, Nvidia NGC, YandexGPT and Reka. For more information about model support, please refer to the model support [Doc](./docs/model_support.md).
244+
FastChat supports popular API-based models such as OpenAI, Anthropic, Gemini, Mistral and more. To add a custom API, please refer to the model support [doc](./docs/model_support.md). Below we take OpenAI models as an example.
247245

248246
Create a JSON configuration file `api_endpoint.json` with the api endpoints of the models you want to serve, for example:
249247
```

0 commit comments

Comments
 (0)