The-Cluster-LLM-API.md

@@ -3,7 +3,7 @@ To facilitate the use of Large Language Models we now have an API service which
 **Usage**
 
 * POST requests to the API are to be JSON-encoded strings requiring a text field and allowing for the flexible addition of any other keyword arguments that can be added to the vLLM sampling params found [here](https://github.com/vllm-project/vllm/blob/main/vllm/sampling_params.py)
-* Additionally output can be streamed with the boolean kwarg 'stream' and logits can be returned using the boolean kwarg 'include_logits'
+* Additionally output can be streamed with the boolean kwarg 'stream' and logits can be returned using the  kwarg 'include_logits', the value should be the number of top-k logits to return a la OpenAI
 * For completion tasks you can prepend the prompt used with the boolean kwarg 'include_prompt'
 * A convenience function as well as default sampling configurations can be found in [this repository](https://github.com/Parry-Parry/idaLLM/tree/main/idallm)
 * Using the request function of the idaLLM package you can easily send single or batched prompts