update cache API

Author: hahuyhoang411

docs/openapi/NitroAPI.yaml

@@ -437,6 +437,10 @@ components:
               default: true
               nullable: true
               description: Determines if output generation is in a streaming manner.
+            cache_prompt:
+              type: boolean
+              default: true
+              description: Optimize performance in repeated or similar requests.
             temp:
               type: number
               default: 0.7
@@ -577,7 +581,10 @@ components:
           min: 0
           max: 1
           description: Set probability threshold for more relevant outputs
-
+        cache_prompt:
+          type: boolean
+          default: true
+          description: Optimize performance in repeated or similar requests.
     ChatCompletionResponse:
       type: object
       description: Description of the response structure