0.5.0

changelog.md

@@ -1,5 +1,53 @@
 # Changelog
 
+## 2025-02-25 - 0.5.0 - feat(documentation and configuration)
+Enhanced package and README documentation
+
+- Expanded the package description to better reflect the library's capabilities.
+- Improved README with detailed usage examples for initialization, chat interactions, streaming chat, audio generation, document analysis, and vision processing.
+- Provided error handling strategies and advanced streaming customization examples.
+
+## 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
+
+- Introduced a Table of Contents
+- Included comprehensive sections for chat, streaming chat, audio generation, document processing, and vision processing
+- Added example code and detailed configuration steps for supported AI providers
+- Clarified the development setup with instructions for running tests and building the project
+
 ## 2025-02-05 - 0.3.0 - feat(integration-xai)
 Add support for X.AI provider with chat and document processing capabilities.
 

npmextra.json

@@ -5,20 +5,33 @@
       "githost": "code.foss.global",
       "gitscope": "push.rocks",
       "gitrepo": "smartai",
-      "description": "A TypeScript library for integrating and interacting with multiple AI models, offering capabilities for chat and potentially audio responses.",
+      "description": "SmartAi is a versatile TypeScript library designed to facilitate integration and interaction with various AI models, offering functionalities for chat, audio generation, document processing, and vision tasks.",
       "npmPackagename": "@push.rocks/smartai",
       "license": "MIT",
       "projectDomain": "push.rocks",
       "keywords": [
         "AI integration",
-        "chatbot",
         "TypeScript",
+        "chatbot",
         "OpenAI",
         "Anthropic",
-        "multi-model support",
-        "audio responses",
+        "multi-model",
+        "audio generation",
         "text-to-speech",
-        "streaming chat"
+        "document processing",
+        "vision processing",
+        "streaming chat",
+        "API",
+        "multiple providers",
+        "AI models",
+        "synchronous chat",
+        "asynchronous chat",
+        "real-time interaction",
+        "content analysis",
+        "image description",
+        "document classification",
+        "AI toolkit",
+        "provider switching"
       ]
     }
   },

package.json

@@ -1,8 +1,8 @@
 {
   "name": "@push.rocks/smartai",
-  "version": "0.3.0",
+  "version": "0.5.0",
   "private": false,
-  "description": "A TypeScript library for integrating and interacting with multiple AI models, offering capabilities for chat and potentially audio responses.",
+  "description": "SmartAi is a versatile TypeScript library designed to facilitate integration and interaction with various AI models, offering functionalities for chat, audio generation, document processing, and vision tasks.",
   "main": "dist_ts/index.js",
   "typings": "dist_ts/index.d.ts",
   "type": "module",
@@ -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",
@@ -58,13 +58,31 @@
   ],
   "keywords": [
     "AI integration",
-    "chatbot",
     "TypeScript",
+    "chatbot",
     "OpenAI",
     "Anthropic",
-    "multi-model support",
-    "audio responses",
+    "multi-model",
+    "audio generation",
     "text-to-speech",
-    "streaming chat"
+    "document processing",
+    "vision processing",
+    "streaming chat",
+    "API",
+    "multiple providers",
+    "AI models",
+    "synchronous chat",
+    "asynchronous chat",
+    "real-time interaction",
+    "content analysis",
+    "image description",
+    "document classification",
+    "AI toolkit",
+    "provider switching"
+  ],
+  "pnpm": {
+    "onlyBuiltDependencies": [
+      "puppeteer"
     ]
+  }
 }

readme.md

@@ -1,95 +1,42 @@
 # @push.rocks/smartai
 
-Provides a standardized interface for integrating and conversing with multiple AI models, supporting operations like chat, streaming interactions, and audio responses.
+SmartAi is a TypeScript library providing a unified interface for integrating and interacting with multiple AI models, supporting chat interactions, audio and document processing, and vision tasks.
 
 ## Install
 
-To add @push.rocks/smartai to your project, run the following command in your terminal:
+To install SmartAi into your project, you need to run the following command in your terminal:
 
 ```bash
 npm install @push.rocks/smartai
 ```
 
-This command installs the package and adds it to your project's dependencies.
-
-## Supported AI Providers
-
-@push.rocks/smartai supports multiple AI providers, each with its own unique capabilities:
-
-### OpenAI
-- Models: GPT-4, GPT-3.5-turbo, GPT-4-vision-preview
-- Features: Chat, Streaming, Audio Generation, Vision, Document Processing
-- Configuration:
-  ```typescript
-  openaiToken: 'your-openai-token'
-  ```
-
-### X.AI
-- Models: Grok-2-latest
-- Features: Chat, Streaming, Document Processing
-- Configuration:
-  ```typescript
-  xaiToken: 'your-xai-token'
-  ```
-
-### Anthropic
-- Models: Claude-3-opus-20240229
-- Features: Chat, Streaming, Vision, Document Processing
-- Configuration:
-  ```typescript
-  anthropicToken: 'your-anthropic-token'
-  ```
-
-### Perplexity
-- Models: Mixtral-8x7b-instruct
-- Features: Chat, Streaming
-- Configuration:
-  ```typescript
-  perplexityToken: 'your-perplexity-token'
-  ```
-
-### Groq
-- Models: Llama-3.3-70b-versatile
-- Features: Chat, Streaming
-- Configuration:
-  ```typescript
-  groqToken: 'your-groq-token'
-  ```
-
-### Ollama
-- Models: Configurable (default: llama2, llava for vision/documents)
-- Features: Chat, Streaming, Vision, Document Processing
-- Configuration:
-  ```typescript
-  baseUrl: 'http://localhost:11434' // Optional
-  model: 'llama2' // Optional
-  visionModel: 'llava' // Optional, for vision and document tasks
-  ```
+This command will add the SmartAi library to your project's dependencies, making it available for use in your TypeScript application.
 
 ## Usage
 
-The `@push.rocks/smartai` package is a comprehensive solution for integrating and interacting with various AI models, designed to support operations ranging from chat interactions to audio responses. This documentation will guide you through the process of utilizing `@push.rocks/smartai` in your applications.
+SmartAi is designed to provide a comprehensive and unified API for working seamlessly with multiple AI providers like OpenAI, Anthropic, Perplexity, and others. Below we will delve into how to make the most out of this library, illustrating the setup and functionality with in-depth examples. Our scenarios will explore synchronous and streaming interactions, audio generation, document handling, and vision tasks with different AI providers.
 
-### Getting Started
+### Initialization
 
-Before you begin, ensure you have installed the package as described in the **Install** section above. Once installed, you can start integrating AI functionalities into your application.
-
-### Initializing SmartAi
-
-The first step is to import and initialize the `SmartAi` class with appropriate options for the AI services you plan to use:
+Initialization is the first step before using any AI functionalities. You should provide API tokens for each provider you plan to utilize.
 
 ```typescript
 import { SmartAi } from '@push.rocks/smartai';
 
 const smartAi = new SmartAi({
   openaiToken: 'your-openai-token',
-  xaiToken: 'your-xai-token',
   anthropicToken: 'your-anthropic-token',
   perplexityToken: 'your-perplexity-token',
+  xaiToken: 'your-xai-token',
   groqToken: 'your-groq-token',
   ollama: {
     baseUrl: 'http://localhost:11434',
-    model: 'llama2'
+    model: 'llama2',
+    visionModel: 'llava'
+  },
+  exo: {
+    baseUrl: 'http://localhost:8080/v1',
+    apiKey: 'your-api-key'
   }
 });
 
@@ -98,33 +45,34 @@ await smartAi.start();
 
 ### Chat Interactions
 
-#### Synchronous Chat
+Interaction through chat is a key feature. SmartAi caters to both synchronous and asynchronous (streaming) chats across several AI models.
 
-For simple question-answer interactions:
+#### Regular Synchronous Chat
+
+Connect with AI models via straightforward request-response interactions.
 
 ```typescript
-const response = await smartAi.openaiProvider.chat({
+const syncResponse = await smartAi.openaiProvider.chat({
   systemMessage: 'You are a helpful assistant.',
   userMessage: 'What is the capital of France?',
-  messageHistory: [] // Previous messages in the conversation
+  messageHistory: [] // Could include context or preceding messages
 });
 
-console.log(response.message);
+console.log(syncResponse.message); // Outputs: "The capital of France is Paris."
 ```
 
-#### Streaming Chat
+#### Real-Time Streaming Chat
 
-For real-time, streaming interactions:
+For continuous interaction and lower latency, engage in streaming chat.
 
 ```typescript
 const textEncoder = new TextEncoder();
 const textDecoder = new TextDecoder();
 
-// Create input and output streams
+// Establish a transform stream
 const { writable, readable } = new TransformStream();
 const writer = writable.getWriter();
 
-// Send a message
 const message = {
   role: 'user',
   content: 'Tell me a story about a brave knight'
@@ -132,104 +80,151 @@ const message = {
 
 writer.write(textEncoder.encode(JSON.stringify(message) + '\n'));
 
-// Process the response stream
+// Initiate streaming
 const stream = await smartAi.openaiProvider.chatStream(readable);
 const reader = stream.getReader();
 
 while (true) {
   const { done, value } = await reader.read();
   if (done) break;
-  console.log('AI:', value); // Process each chunk of the response
+  console.log('AI:', value);
 }
 ```
 
 ### Audio Generation
 
-For providers that support audio generation (currently OpenAI):
+Audio generation from textual input is possible using providers like OpenAI.
 
 ```typescript
 const audioStream = await smartAi.openaiProvider.audio({
-  message: 'Hello, this is a test of text-to-speech'
+  message: 'This is a test message for generating speech.'
 });
 
-// Handle the audio stream (e.g., save to file or play)
+// Use the audioStream e.g., playing or saving it.
 ```
 
-### Document Processing
+### Document Analysis
 
-For providers that support document processing (OpenAI, Ollama, and Anthropic):
+SmartAi can ingest and process documents, extracting meaningful information or performing classifications.
 
 ```typescript
-// Using OpenAI
-const result = await smartAi.openaiProvider.document({
-  systemMessage: 'Classify the document type',
-  userMessage: 'What type of document is this?',
+const pdfBuffer = await fetchPdf('https://example.com/document.pdf');
+const documentRes = await smartAi.openaiProvider.document({
+  systemMessage: 'Determine the nature of the document.',
+  userMessage: 'Classify this document.',
   messageHistory: [],
-  pdfDocuments: [pdfBuffer] // Uint8Array of PDF content
+  pdfDocuments: [pdfBuffer]
 });
 
-// Using Ollama with llava
-const analysis = await smartAi.ollamaProvider.document({
-  systemMessage: 'You are a document analysis assistant',
-  userMessage: 'Extract the key information from this document',
-  messageHistory: [],
-  pdfDocuments: [pdfBuffer] // Uint8Array of PDF content
-});
-
-// Using Anthropic with Claude 3
-const anthropicAnalysis = await smartAi.anthropicProvider.document({
-  systemMessage: 'You are a document analysis assistant',
-  userMessage: 'Please analyze this document and extract key information',
-  messageHistory: [],
-  pdfDocuments: [pdfBuffer] // Uint8Array of PDF content
-});
+console.log(documentRes.message); // Outputs: classified document type
 ```
 
-Both providers will:
-1. Convert PDF documents to images
-2. Process each page using their vision models
-3. Return a comprehensive analysis based on the system message and user query
+SmartAi allows easy switching between providers, thus giving developers flexibility:
+
+```typescript
+const anthopicRes = await smartAi.anthropicProvider.document({
+  systemMessage: 'Analyze this document.',
+  userMessage: 'Extract core points.',
+  messageHistory: [],
+  pdfDocuments: [pdfBuffer]
+});
+
+console.log(anthopicRes.message); // Outputs: summarized core points
+```
 
 ### Vision Processing
 
-For providers that support vision tasks (OpenAI, Ollama, and Anthropic):
+Engage AI models in analyzing and describing images:
 
 ```typescript
-// Using OpenAI's GPT-4 Vision
-const description = await smartAi.openaiProvider.vision({
-  image: imageBuffer, // Buffer containing the image data
-  prompt: 'What do you see in this image?'
+const imageBuffer = await fetchImage('path/to/image.jpg');
+
+// Using OpenAI's vision capabilities
+const visionOutput = await smartAi.openaiProvider.vision({
+  image: imageBuffer,
+  prompt: 'Describe the image.'
 });
 
-// Using Ollama's Llava model
-const analysis = await smartAi.ollamaProvider.vision({
-  image: imageBuffer,
-  prompt: 'Analyze this image in detail'
-});
-
-// Using Anthropic's Claude 3
-const anthropicAnalysis = await smartAi.anthropicProvider.vision({
-  image: imageBuffer,
-  prompt: 'Please analyze this image and describe what you see'
-});
+console.log(visionOutput); // Outputs: image description
 ```
 
-## Error Handling
+Use other providers for more varied analysis:
 
-All providers implement proper error handling. It's recommended to wrap API calls in try-catch blocks:
+```typescript
+const ollamaOutput = await smartAi.ollamaProvider.vision({
+  image: imageBuffer,
+  prompt: 'Detailed analysis required.'
+});
+
+console.log(ollamaOutput); // Outputs: detailed analysis results
+```
+
+### Error Handling
+
+Due to the nature of external integrations, ensure to wrap AI calls within try-catch blocks.
 
 ```typescript
 try {
-  const response = await smartAi.openaiProvider.chat({
-    systemMessage: 'You are a helpful assistant.',
-    userMessage: 'Hello!',
+  const response = await smartAi.anthropicProvider.chat({
+    systemMessage: 'Hello!',
+    userMessage: 'Help me out.',
     messageHistory: []
   });
-} catch (error) {
-  console.error('AI provider error:', error.message);
+  console.log(response.message);
+} catch (error: any) {
+  console.error('Encountered an error:', error.message);
 }
 ```
 
+### Providers and Customization
+
+The library supports provider-specific customization, enabling tailored interactions:
+
+```typescript
+const smartAi = new SmartAi({
+  openaiToken: 'your-openai-token',
+  anthropicToken: 'your-anthropic-token',
+  ollama: {
+    baseUrl: 'http://localhost:11434',
+    model: 'llama2',
+    visionModel: 'llava'
+  }
+});
+
+await smartAi.start();
+```
+
+### Advanced Streaming Customization
+
+Developers can implement real-time processing pipelines with custom transformations:
+
+```typescript
+const customProcessingStream = new TransformStream({
+  transform(chunk, controller) {
+    const processed = chunk.toUpperCase(); // Example transformation
+    controller.enqueue(processed);
+  }
+});
+
+const processedStream = stream.pipeThrough(customProcessingStream);
+const processedReader = processedStream.getReader();
+
+while (true) {
+  const { done, value } = await processedReader.read();
+  if (done) break;
+  console.log('Processed Output:', value);
+}
+```
+
+This approach can facilitate adaptive content processing workflows.
+
+### Conclusion
+
+SmartAi is a powerful toolkit for multi-faceted AI integration, offering robust solutions for chat, media, and document processing. Developers can enjoy a consistent API experience while leveraging the strengths of each supported AI model.
+
+For futher exploration, developers might consider perusing individual provider's documentation to understand specific capabilities and limitations.
+
+
 ## License and Legal Information
 
 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. 

ts/00_commitinfo_data.ts

@@ -3,6 +3,6 @@
  */
 export const commitinfo = {
   name: '@push.rocks/smartai',
-  version: '0.3.0',
-  description: 'A TypeScript library for integrating and interacting with multiple AI models, offering capabilities for chat and potentially audio responses.'
+  version: '0.5.0',
+  description: 'SmartAi is a versatile TypeScript library designed to facilitate integration and interaction with various AI models, offering functionalities for chat, audio generation, document processing, and vision tasks.'
 }

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 || '';
   }
 }