0.4.2

changelog.md

@@ -1,5 +1,38 @@
 # Changelog
 
+## 2025-02-25 - 0.4.2 - fix(core)
+Fix OpenAI chat streaming and PDF document processing logic.
+
+- Updated OpenAI chat streaming to handle new async iterable format.
+- Improved PDF document processing by filtering out empty image buffers.
+- Removed unsupported temperature options from OpenAI requests.
+
+## 2025-02-25 - 0.4.1 - fix(provider)
+Fix provider modules for consistency
+
+- Updated TypeScript interfaces and options in provider modules for better type safety.
+- Modified transform stream handlers in Exo, Groq, and Ollama providers for consistency.
+- Added optional model options to OpenAI provider for custom model usage.
+
+## 2025-02-08 - 0.4.0 - feat(core)
+Added support for Exo AI provider
+
+- Introduced ExoProvider with chat functionalities.
+- Updated SmartAi class to initialize ExoProvider.
+- Extended Conversation class to support ExoProvider.
+
+## 2025-02-05 - 0.3.3 - fix(documentation)
+Update readme with detailed license and legal information.
+
+- Added explicit section on License and Legal Information in the README.
+- Clarified the use of trademarks and company information.
+
+## 2025-02-05 - 0.3.2 - fix(documentation)
+Remove redundant badges from readme
+
+- Removed Build Status badge from the readme file.
+- Removed License badge from the readme file.
+
 ## 2025-02-05 - 0.3.1 - fix(documentation)
 Updated README structure and added detailed usage examples
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@push.rocks/smartai",
-  "version": "0.3.1",
+  "version": "0.4.2",
   "private": false,
   "description": "A TypeScript library for integrating and interacting with multiple AI models, offering capabilities for chat and potentially audio responses.",
   "main": "dist_ts/index.js",
@@ -14,24 +14,24 @@
     "buildDocs": "(tsdoc)"
   },
   "devDependencies": {
-    "@git.zone/tsbuild": "^2.1.84",
-    "@git.zone/tsbundle": "^2.0.5",
-    "@git.zone/tsrun": "^1.2.49",
-    "@git.zone/tstest": "^1.0.90",
-    "@push.rocks/qenv": "^6.0.5",
-    "@push.rocks/tapbundle": "^5.3.0",
-    "@types/node": "^22.5.5"
+    "@git.zone/tsbuild": "^2.2.1",
+    "@git.zone/tsbundle": "^2.2.5",
+    "@git.zone/tsrun": "^1.3.3",
+    "@git.zone/tstest": "^1.0.96",
+    "@push.rocks/qenv": "^6.1.0",
+    "@push.rocks/tapbundle": "^5.5.6",
+    "@types/node": "^22.13.5"
   },
   "dependencies": {
-    "@anthropic-ai/sdk": "^0.27.3",
-    "@push.rocks/smartarray": "^1.0.8",
-    "@push.rocks/smartfile": "^11.0.21",
+    "@anthropic-ai/sdk": "^0.37.0",
+    "@push.rocks/smartarray": "^1.1.0",
+    "@push.rocks/smartfile": "^11.2.0",
     "@push.rocks/smartpath": "^5.0.18",
-    "@push.rocks/smartpdf": "^3.1.6",
-    "@push.rocks/smartpromise": "^4.0.4",
-    "@push.rocks/smartrequest": "^2.0.22",
+    "@push.rocks/smartpdf": "^3.2.2",
+    "@push.rocks/smartpromise": "^4.2.3",
+    "@push.rocks/smartrequest": "^2.0.23",
     "@push.rocks/webstream": "^1.0.10",
-    "openai": "^4.62.1"
+    "openai": "^4.85.4"
   },
   "repository": {
     "type": "git",
@@ -66,5 +66,10 @@
     "audio responses",
     "text-to-speech",
     "streaming chat"
-  ]
+  ],
+  "pnpm": {
+    "onlyBuiltDependencies": [
+      "puppeteer"
+    ]
+  }
 }

readme.md

@@ -1,8 +1,6 @@
 # @push.rocks/smartai
 
-[![npm version](https://badge.fury.io/js/%40push.rocks%2Fsmartai.svg)](https://www.npmjs.com/package/@push.rocks/smartai)  
-[![Build Status](https://github.com/push.rocks/smartai/workflows/CI/badge.svg)](https://github.com/push.rocks/smartai/actions)  
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+[![npm version](https://badge.fury.io/js/%40push.rocks%2Fsmartai.svg)](https://www.npmjs.com/package/@push.rocks/smartai)
 
 SmartAi is a comprehensive TypeScript library that provides a standardized interface for integrating and interacting with multiple AI models. It supports a range of operations from synchronous and streaming chat to audio generation, document processing, and vision tasks.
 
@@ -112,6 +110,19 @@ SmartAi supports multiple AI providers. Configure each provider with its corresp
   }
   ```
 
+### Exo
+
+- **Models:** Configurable (supports LLaMA, Mistral, LlaVA, Qwen, and Deepseek)
+- **Features:** Chat, Streaming
+- **Configuration Example:**
+  
+  ```typescript
+  exo: {
+    baseUrl: 'http://localhost:8080/v1', // Optional
+    apiKey: 'your-api-key'               // Optional for local deployments
+  }
+  ```
+
 ## Quick Start
 
 Initialize SmartAi with the provider configurations you plan to use:
@@ -128,6 +139,10 @@ const smartAi = new SmartAi({
   ollama: {
     baseUrl: 'http://localhost:11434',
     model: 'llama2'
+  },
+  exo: {
+    baseUrl: 'http://localhost:8080/v1',
+    apiKey: 'your-api-key'
   }
 });
 
@@ -310,24 +325,21 @@ Contributions are welcome! Please follow these steps:
    ```
 5. Open a Pull Request with a detailed description of your changes.
 
-## License
+## License and Legal Information
 
-This project is licensed under the [MIT License](LICENSE).
+This repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository. 
 
-## Legal Information
+**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.
 
 ### Trademarks
 
-This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and its related products or services are trademarks of Task Venture Capital GmbH and are not covered by the MIT License. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines.
+This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.
 
 ### Company Information
 
 Task Venture Capital GmbH  
-Registered at District Court Bremen HRB 35230 HB, Germany  
-Contact: hello@task.vc
+Registered at District court Bremen HRB 35230 HB, Germany
 
-By using this repository, you agree to the terms outlined in this section.
+For any legal inquiries or if you require further information, please contact us via email at hello@task.vc.
 
----
-
-Happy coding with SmartAi!
+By using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.

ts/00_commitinfo_data.ts

@@ -3,6 +3,6 @@
  */
 export const commitinfo = {
   name: '@push.rocks/smartai',
-  version: '0.3.1',
+  version: '0.4.2',
   description: 'A TypeScript library for integrating and interacting with multiple AI models, offering capabilities for chat and potentially audio responses.'
 }

ts/classes.conversation.ts

@@ -48,6 +48,18 @@ export class Conversation {
     return conversation;
   }
 
+  public static async createWithExo(smartaiRefArg: SmartAi) {
+    if (!smartaiRefArg.exoProvider) {
+      throw new Error('Exo provider not available');
+    }
+    const conversation = new Conversation(smartaiRefArg, {
+      processFunction: async (input) => {
+        return '' // TODO implement proper streaming
+      }
+    });
+    return conversation;
+  }
+
   public static async createWithOllama(smartaiRefArg: SmartAi) {
     if (!smartaiRefArg.ollamaProvider) {
       throw new Error('Ollama provider not available');
@@ -60,6 +72,30 @@ export class Conversation {
     return conversation;
   }
 
+  public static async createWithGroq(smartaiRefArg: SmartAi) {
+    if (!smartaiRefArg.groqProvider) {
+      throw new Error('Groq provider not available');
+    }
+    const conversation = new Conversation(smartaiRefArg, {
+      processFunction: async (input) => {
+        return '' // TODO implement proper streaming
+      }
+    });
+    return conversation;
+  }
+
+  public static async createWithXai(smartaiRefArg: SmartAi) {
+    if (!smartaiRefArg.xaiProvider) {
+      throw new Error('XAI provider not available');
+    }
+    const conversation = new Conversation(smartaiRefArg, {
+      processFunction: async (input) => {
+        return '' // TODO implement proper streaming
+      }
+    });
+    return conversation;
+  }
+
   // INSTANCE
   smartaiRef: SmartAi
   private systemMessage: string;

ts/classes.smartai.ts

@@ -1,18 +1,32 @@
 import { Conversation } from './classes.conversation.js';
 import * as plugins from './plugins.js';
 import { AnthropicProvider } from './provider.anthropic.js';
-import type { OllamaProvider } from './provider.ollama.js';
+import { OllamaProvider } from './provider.ollama.js';
 import { OpenAiProvider } from './provider.openai.js';
-import type { PerplexityProvider } from './provider.perplexity.js';
+import { PerplexityProvider } from './provider.perplexity.js';
+import { ExoProvider } from './provider.exo.js';
+import { GroqProvider } from './provider.groq.js';
+import { XAIProvider } from './provider.xai.js';
 
 
 export interface ISmartAiOptions {
   openaiToken?: string;
   anthropicToken?: string;
   perplexityToken?: string;
+  groqToken?: string;
+  xaiToken?: string;
+  exo?: {
+    baseUrl?: string;
+    apiKey?: string;
+  };
+  ollama?: {
+    baseUrl?: string;
+    model?: string;
+    visionModel?: string;
+  };
 }
 
-export type TProvider = 'openai' | 'anthropic' | 'perplexity' | 'ollama';
+export type TProvider = 'openai' | 'anthropic' | 'perplexity' | 'ollama' | 'exo' | 'groq' | 'xai';
 
 export class SmartAi {
   public options: ISmartAiOptions;
@@ -21,6 +35,9 @@ export class SmartAi {
   public anthropicProvider: AnthropicProvider;
   public perplexityProvider: PerplexityProvider;
   public ollamaProvider: OllamaProvider;
+  public exoProvider: ExoProvider;
+  public groqProvider: GroqProvider;
+  public xaiProvider: XAIProvider;
 
   constructor(optionsArg: ISmartAiOptions) {
     this.options = optionsArg;
@@ -37,6 +54,40 @@ export class SmartAi {
       this.anthropicProvider = new AnthropicProvider({
         anthropicToken: this.options.anthropicToken,
       });
+      await this.anthropicProvider.start();
+    }
+    if (this.options.perplexityToken) {
+      this.perplexityProvider = new PerplexityProvider({
+        perplexityToken: this.options.perplexityToken,
+      });
+      await this.perplexityProvider.start();
+    }
+    if (this.options.groqToken) {
+      this.groqProvider = new GroqProvider({
+        groqToken: this.options.groqToken,
+      });
+      await this.groqProvider.start();
+    }
+    if (this.options.xaiToken) {
+      this.xaiProvider = new XAIProvider({
+        xaiToken: this.options.xaiToken,
+      });
+      await this.xaiProvider.start();
+    }
+    if (this.options.ollama) {
+      this.ollamaProvider = new OllamaProvider({
+        baseUrl: this.options.ollama.baseUrl,
+        model: this.options.ollama.model,
+        visionModel: this.options.ollama.visionModel,
+      });
+      await this.ollamaProvider.start();
+    }
+    if (this.options.exo) {
+      this.exoProvider = new ExoProvider({
+        exoBaseUrl: this.options.exo.baseUrl,
+        apiKey: this.options.exo.apiKey,
+      });
+      await this.exoProvider.start();
     }
   }
 
@@ -47,6 +98,8 @@ export class SmartAi {
    */
   createConversation(provider: TProvider) {
     switch (provider) {
+      case 'exo':
+        return Conversation.createWithExo(this);
       case 'openai':
         return Conversation.createWithOpenAi(this);
       case 'anthropic':
@@ -55,6 +108,10 @@ export class SmartAi {
         return Conversation.createWithPerplexity(this);
       case 'ollama':
         return Conversation.createWithOllama(this);
+      case 'groq':
+        return Conversation.createWithGroq(this);
+      case 'xai':
+        return Conversation.createWithXai(this);
       default:
         throw new Error('Provider not available');
     }

ts/provider.exo.ts

@@ -0,0 +1,128 @@
+import * as plugins from './plugins.js';
+import * as paths from './paths.js';
+import { MultiModalModel } from './abstract.classes.multimodal.js';
+import type { ChatOptions, ChatResponse, ChatMessage } from './abstract.classes.multimodal.js';
+import type { ChatCompletionMessageParam } from 'openai/resources/chat/completions';
+
+export interface IExoProviderOptions {
+  exoBaseUrl?: string;
+  apiKey?: string;
+}
+
+export class ExoProvider extends MultiModalModel {
+  private options: IExoProviderOptions;
+  public openAiApiClient: plugins.openai.default;
+
+  constructor(optionsArg: IExoProviderOptions = {}) {
+    super();
+    this.options = {
+      exoBaseUrl: 'http://localhost:8080/v1',  // Default Exo API endpoint
+      ...optionsArg
+    };
+  }
+
+  public async start() {
+    this.openAiApiClient = new plugins.openai.default({
+      apiKey: this.options.apiKey || 'not-needed',  // Exo might not require an API key for local deployment
+      baseURL: this.options.exoBaseUrl,
+    });
+  }
+
+  public async stop() {}
+
+  public async chatStream(input: ReadableStream<Uint8Array>): Promise<ReadableStream<string>> {
+    // Create a TextDecoder to handle incoming chunks
+    const decoder = new TextDecoder();
+    let buffer = '';
+    let currentMessage: { role: string; content: string; } | null = null;
+
+    // Create a TransformStream to process the input
+    const transform = new TransformStream<Uint8Array, string>({
+      transform: async (chunk, controller) => {
+        buffer += decoder.decode(chunk, { stream: true });
+
+        // Try to parse complete JSON messages from the buffer
+        while (true) {
+          const newlineIndex = buffer.indexOf('\n');
+          if (newlineIndex === -1) break;
+
+          const line = buffer.slice(0, newlineIndex);
+          buffer = buffer.slice(newlineIndex + 1);
+
+          if (line.trim()) {
+            try {
+              const message = JSON.parse(line);
+              currentMessage = message;
+              
+              // Process the message based on its type
+              if (message.type === 'message') {
+                const response = await this.chat({
+                  systemMessage: '',
+                  userMessage: message.content,
+                  messageHistory: [{ role: message.role as 'user' | 'assistant' | 'system', content: message.content }]
+                });
+                
+                controller.enqueue(JSON.stringify(response) + '\n');
+              }
+            } catch (error) {
+              console.error('Error processing message:', error);
+            }
+          }
+        }
+      },
+      flush(controller) {
+        if (buffer) {
+          try {
+            const message = JSON.parse(buffer);
+            currentMessage = message;
+          } catch (error) {
+            console.error('Error processing remaining buffer:', error);
+          }
+        }
+      }
+    });
+
+    return input.pipeThrough(transform);
+  }
+
+  public async chat(options: ChatOptions): Promise<ChatResponse> {
+    const messages: ChatCompletionMessageParam[] = [
+      { role: 'system', content: options.systemMessage },
+      ...options.messageHistory,
+      { role: 'user', content: options.userMessage }
+    ];
+
+    try {
+      const response = await this.openAiApiClient.chat.completions.create({
+        model: 'local-model', // Exo uses local models
+        messages: messages,
+        stream: false
+      });
+
+      return {
+        role: 'assistant',
+        message: response.choices[0]?.message?.content || ''
+      };
+    } catch (error) {
+      console.error('Error in chat completion:', error);
+      throw error;
+    }
+  }
+
+  public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
+    throw new Error('Audio generation is not supported by Exo provider');
+  }
+
+  public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
+    throw new Error('Vision processing is not supported by Exo provider');
+  }
+
+  public async document(optionsArg: {
+    systemMessage: string;
+    userMessage: string;
+    pdfDocuments: Uint8Array[];
+    messageHistory: ChatMessage[];
+  }): Promise<{ message: any }> {
+    throw new Error('Document processing is not supported by Exo provider');
+  }
+}

ts/provider.groq.ts

@@ -32,7 +32,7 @@ export class GroqProvider extends MultiModalModel {
 
     // Create a TransformStream to process the input
     const transform = new TransformStream<Uint8Array, string>({
-      async transform(chunk, controller) {
+      transform: async (chunk, controller) => {
         buffer += decoder.decode(chunk, { stream: true });
 
         // Try to parse complete JSON messages from the buffer

ts/provider.ollama.ts

@@ -45,7 +45,7 @@ export class OllamaProvider extends MultiModalModel {
 
     // Create a TransformStream to process the input
     const transform = new TransformStream<Uint8Array, string>({
-      async transform(chunk, controller) {
+      transform: async (chunk, controller) => {
         buffer += decoder.decode(chunk, { stream: true });
 
         // Try to parse complete JSON messages from the buffer

ts/provider.openai.ts

@@ -1,10 +1,20 @@
 import * as plugins from './plugins.js';
 import * as paths from './paths.js';
 
+// Custom type definition for chat completion messages
+export type TChatCompletionRequestMessage = { 
+  role: "system" | "user" | "assistant"; 
+  content: string; 
+};
+
 import { MultiModalModel } from './abstract.classes.multimodal.js';
 
 export interface IOpenaiProviderOptions {
   openaiToken: string;
+  chatModel?: string;
+  audioModel?: string;
+  visionModel?: string;
+  // Optionally add more model options (e.g., documentModel) if needed.
 }
 
 export class OpenAiProvider extends MultiModalModel {
@@ -31,11 +41,14 @@ export class OpenAiProvider extends MultiModalModel {
     // Create a TextDecoder to handle incoming chunks
     const decoder = new TextDecoder();
     let buffer = '';
-    let currentMessage: { role: string; content: string; } | null = null;
+    let currentMessage: { 
+      role: "function" | "user" | "system" | "assistant" | "tool" | "developer"; 
+      content: string; 
+    } | null = null;
 
     // Create a TransformStream to process the input
     const transform = new TransformStream<Uint8Array, string>({
-      async transform(chunk, controller) {
+      transform: async (chunk, controller) => {
         buffer += decoder.decode(chunk, { stream: true });
 
         // Try to parse complete JSON messages from the buffer
@@ -50,7 +63,7 @@ export class OpenAiProvider extends MultiModalModel {
             try {
               const message = JSON.parse(line);
               currentMessage = {
-                role: message.role || 'user',
+                role: (message.role || 'user') as "function" | "user" | "system" | "assistant" | "tool" | "developer",
                 content: message.content || '',
               };
             } catch (e) {
@@ -61,20 +74,24 @@ export class OpenAiProvider extends MultiModalModel {
 
         // If we have a complete message, send it to OpenAI
         if (currentMessage) {
-          const stream = await this.openAiApiClient.chat.completions.create({
-            model: 'gpt-4',
-            messages: [{ role: currentMessage.role, content: currentMessage.content }],
+          const messageToSend = { role: "user" as const, content: currentMessage.content };
+          const chatModel = this.options.chatModel ?? 'o3-mini';
+          const requestParams: any = {
+            model: chatModel,
+            messages: [messageToSend],
             stream: true,
-          });
-
+          };
+          // Temperature is omitted since the model does not support it.
+          const stream = await this.openAiApiClient.chat.completions.create(requestParams);
+          // Explicitly cast the stream as an async iterable to satisfy TypeScript.
+          const streamAsyncIterable = stream as unknown as AsyncIterableIterator<any>;
           // Process each chunk from OpenAI
-          for await (const chunk of stream) {
+          for await (const chunk of streamAsyncIterable) {
             const content = chunk.choices[0]?.delta?.content;
             if (content) {
               controller.enqueue(content);
             }
           }
-
           currentMessage = null;
         }
       },
@@ -104,15 +121,17 @@ export class OpenAiProvider extends MultiModalModel {
       content: string;
     }[];
   }) {
-    const result = await this.openAiApiClient.chat.completions.create({
-      model: 'gpt-4o',
-
+    const chatModel = this.options.chatModel ?? 'o3-mini';
+    const requestParams: any = {
+      model: chatModel,
       messages: [
         { role: 'system', content: optionsArg.systemMessage },
         ...optionsArg.messageHistory,
         { role: 'user', content: optionsArg.userMessage },
       ],
-    });
+    };
+    // Temperature parameter removed to avoid unsupported error.
+    const result = await this.openAiApiClient.chat.completions.create(requestParams);
     return {
       role: result.choices[0].message.role as 'assistant',
       message: result.choices[0].message.content,
@@ -122,7 +141,7 @@ export class OpenAiProvider extends MultiModalModel {
   public async audio(optionsArg: { message: string }): Promise<NodeJS.ReadableStream> {
     const done = plugins.smartpromise.defer<NodeJS.ReadableStream>();
     const result = await this.openAiApiClient.audio.speech.create({
-      model: 'tts-1-hd',
+      model: this.options.audioModel ?? 'o3-mini',
       input: optionsArg.message,
       voice: 'nova',
       response_format: 'mp3',
@@ -144,27 +163,30 @@ export class OpenAiProvider extends MultiModalModel {
   }) {
     let pdfDocumentImageBytesArray: Uint8Array[] = [];
 
+    // Convert each PDF into one or more image byte arrays.
+    const smartpdfInstance = new plugins.smartpdf.SmartPdf();
+    await smartpdfInstance.start();
     for (const pdfDocument of optionsArg.pdfDocuments) {
-      const documentImageArray = await this.smartpdfInstance.convertPDFToPngBytes(pdfDocument);
+      const documentImageArray = await smartpdfInstance.convertPDFToPngBytes(pdfDocument);
       pdfDocumentImageBytesArray = pdfDocumentImageBytesArray.concat(documentImageArray);
     }
+    await smartpdfInstance.stop();
 
     console.log(`image smartfile array`);
     console.log(pdfDocumentImageBytesArray.map((smartfile) => smartfile.length));
 
-    const smartfileArray = await plugins.smartarray.map(
-      pdfDocumentImageBytesArray,
-      async (pdfDocumentImageBytes) => {
-        return plugins.smartfile.SmartFile.fromBuffer(
-          'pdfDocumentImage.jpg',
-          Buffer.from(pdfDocumentImageBytes)
-        );
-      }
-    );
+    // Filter out any empty buffers to avoid sending invalid image URLs.
+    const validImageBytesArray = pdfDocumentImageBytesArray.filter(imageBytes => imageBytes && imageBytes.length > 0);
+    const imageAttachments = validImageBytesArray.map(imageBytes => ({
+      type: 'image_url',
+      image_url: {
+        url: 'data:image/png;base64,' + Buffer.from(imageBytes).toString('base64'),
+      },
+    }));
 
-    const result = await this.openAiApiClient.chat.completions.create({
-      model: 'gpt-4o',
-      // response_format: { type: "json_object" }, // not supported for now
+    const chatModel = this.options.chatModel ?? 'gpt-4o';
+    const requestParams: any = {
+      model: chatModel,
       messages: [
         { role: 'system', content: optionsArg.systemMessage },
         ...optionsArg.messageHistory,
@@ -172,30 +194,22 @@ export class OpenAiProvider extends MultiModalModel {
           role: 'user',
           content: [
             { type: 'text', text: optionsArg.userMessage },
-            ...(() => {
-              const returnArray = [];
-              for (const imageBytes of pdfDocumentImageBytesArray) {
-                returnArray.push({
-                  type: 'image_url',
-                  image_url: {
-                    url: 'data:image/png;base64,' + Buffer.from(imageBytes).toString('base64'),
-                  },
-                });
-              }
-              return returnArray;
-            })(),
+            ...imageAttachments,
           ],
         },
       ],
-    });
+    };
+    // Temperature parameter removed.
+    const result = await this.openAiApiClient.chat.completions.create(requestParams);
     return {
       message: result.choices[0].message,
     };
   }
 
   public async vision(optionsArg: { image: Buffer; prompt: string }): Promise<string> {
-    const result = await this.openAiApiClient.chat.completions.create({
-      model: 'gpt-4-vision-preview',
+    const visionModel = this.options.visionModel ?? 'gpt-4o';
+    const requestParams: any = {
+      model: visionModel,
       messages: [
         {
           role: 'user',
@@ -211,8 +225,8 @@ export class OpenAiProvider extends MultiModalModel {
         }
       ],
       max_tokens: 300
-    });
-
+    };
+    const result = await this.openAiApiClient.chat.completions.create(requestParams);
     return result.choices[0].message.content || '';
   }
-}
+}