api: Update the API description

README.md

@@ -33,7 +33,7 @@ Cortex currently supports two inference engines:
 
 Before installation, ensure that you have installed the following:
 
-- **Node.js**: Required for running the installation.
+- **Node.js**: version 18 and above is required to run the installation.
 - **NPM**: Needed to manage packages.
 - **CPU Instruction Sets**: Available for download from the [Cortex GitHub Releases](https://github.com/janhq/cortex/releases) page.
 

cortex-js/README.md

@@ -32,8 +32,7 @@ Cortex
 ### **Dependencies**
 
 Before installation, ensure that you have installed the following:
-
-- **Node.js**: Required for running the installation.
+- **Node.js**: version 18 and above is required to run the installation.
 - **NPM**: Needed to manage packages.
 - **CPU Instruction Sets**: Available for download from the [Cortex GitHub Releases](https://github.com/janhq/cortex/releases) page.
 

cortex-js/src/infrastructure/controllers/embeddings.controller.ts

@@ -10,8 +10,8 @@ export class EmbeddingsController {
   constructor(private readonly chatService: ChatUsecases) {}
 
   @ApiOperation({
-    summary: 'Embedding vector for text',
-    description: 'Creates an embedding vector representing the input text..',
+    summary: 'Create embedding vector',
+    description: 'Creates an embedding vector representing the input text.',
   })
   @HttpCode(200)
   @ApiResponse({

cortex-js/src/infrastructure/dtos/chat/embeddings-response.dto.ts

@@ -3,25 +3,25 @@ import { UsageDto } from './usage.dto';
 
 export class EmbeddingsResponseDto {
   @ApiProperty({
-    description: 'Result object type.',
+    description: 'Type of the result object.',
     type: String,
   })
   object: string;
 
   @ApiProperty({
-    description: 'ID of the model used for embeddings',
+    description: 'Identifier of the model utilized for generating embeddings.',
     type: String,
   })
   model: string;
 
   @ApiProperty({
-    description: 'The embedding vector, which is a list of floats. ',
+    description: 'The embedding vector represented as an array of floating-point numbers. ',
     type: [Number],
   })
   embedding: [number];
 
   @ApiProperty({
-    description: 'Returns prompt_tokens and total_tokens usage ',
+    description: 'Details of token usage, including prompt_tokens and total_tokens.',
     type: UsageDto,
   })
   usage: UsageDto;

cortex-js/src/infrastructure/dtos/embeddings/embeddings-request.dto.ts

@@ -3,29 +3,29 @@ import { ApiProperty } from '@nestjs/swagger';
 
 export class CreateEmbeddingsDto {
   @ApiProperty({
-    description: 'Embedding model',
+    description: 'The name of the embedding model to be used.',
     type: String,
   })
   model: string;
 
   @ApiProperty({
     description:
-      'Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays.',
+      'The text or token array(s) to be embedded. This can be a single string, an array of strings, or an array of token arrays to embed multiple inputs in one request.',
     type: [String],
   })
   input: string | string[];
 
   @ApiProperty({
     description:
-      'Encoding format for the embeddings. Supported formats are float and int.',
+      'Specifies the format for the embeddings. Supported formats include `float` and `int`. This field is optional.',
     type: String,
   })
   @Optional()
   encoding_format?: string;
 
   @ApiProperty({
     description:
-      'The number of dimensions the resulting output embeddings should have. Only supported in some models.',
+      'Defines the number of dimensions for the output embeddings. This feature is supported by certain models only. This field is optional.',
     type: Number,
   })
   @Optional()

cortex-js/src/main.ts

@@ -53,6 +53,10 @@ async function bootstrap() {
       'Threads',
       'These endpoints handle the creation, retrieval, updating, and deletion of conversation threads.',
     )
+    .addTag(
+      'Embeddings',
+      'Endpoint for creating and retrieving embedding vectors from text inputs using specified models.',
+    )
     .addServer('http://localhost:1337')
     .addServer('http://localhost:1337/v1')
     .build();