fix typo

Author: hahuyhoang411

docs/docs/new/architecture.md

@@ -4,8 +4,6 @@ title: Architecture
 
 ![Nitro Architecture](img/architecture.drawio.png)
 
-### Details element example
-
 ## Key Concepts
 
 ## Inference Server

docs/openapi/NitroAPI.yaml

@@ -167,7 +167,7 @@ paths:
       operationId: createChatCompletion
       tags:
         - Chat Completion
-      summary: Create an chat with the model.
+      summary: Create a chat with the model.
       requestBody:
         content:
           application/json:
@@ -544,23 +544,23 @@ components:
         stream:
           type: boolean
           default: true
-          description: Enables continuous output generation, allowing for streaming of model responses.
+          description: Enables continuous output generation, allowing for streaming of model responses
         model:
           type: string
           example: "gpt-3.5-turbo"
-          description: Specifies the model being used for inference or processing tasks.
+          description: Specifies the model being used for inference or processing tasks
         max_tokens:
           type: number
           default: 2048
           description: The maximum number of tokens the model will generate in a single response
         stop:
           type: arrays
           example: ["hello"]
-          description: Defines specific tokens or phrases at which the model will stop generating further output.
+          description: Defines specific tokens or phrases at which the model will stop generating further output
         frequency_penalty:
           type: number
           default: 0
-          description: Adjusts the likelihood of the model repeating words or phrases in its output.
+          description: Adjusts the likelihood of the model repeating words or phrases in its output
         presence_penalty:
           type: number
           default: 0
@@ -570,7 +570,7 @@ components:
           default: 0.7
           min: 0
           max: 1
-          description: Controls the randomness of the model's output.
+          description: Controls the randomness of the model's output
         top_p:
           type: number
           default: 0.95