@push.rocks/smartai 0.5.11 → 0.7.0

package/ts/abstract.classes.multimodal.ts

@@ -25,6 +25,85 @@ export interface ChatResponse {
   message: string;
 }
 
+/**
+ * Options for research interactions
+ */
+export interface ResearchOptions {
+  query: string;
+  searchDepth?: 'basic' | 'advanced' | 'deep';
+  maxSources?: number;
+  includeWebSearch?: boolean;
+  background?: boolean;
+}
+
+/**
+ * Response format for research interactions
+ */
+export interface ResearchResponse {
+  answer: string;
+  sources: Array<{
+    url: string;
+    title: string;
+    snippet: string;
+  }>;
+  searchQueries?: string[];
+  metadata?: any;
+}
+
+/**
+ * Options for image generation
+ */
+export interface ImageGenerateOptions {
+  prompt: string;
+  model?: 'gpt-image-1' | 'dall-e-3' | 'dall-e-2';
+  quality?: 'low' | 'medium' | 'high' | 'standard' | 'hd' | 'auto';
+  size?: '256x256' | '512x512' | '1024x1024' | '1536x1024' | '1024x1536' | '1792x1024' | '1024x1792' | 'auto';
+  style?: 'vivid' | 'natural';
+  background?: 'transparent' | 'opaque' | 'auto';
+  outputFormat?: 'png' | 'jpeg' | 'webp';
+  outputCompression?: number; // 0-100 for webp/jpeg
+  moderation?: 'low' | 'auto';
+  n?: number; // Number of images to generate
+  stream?: boolean;
+  partialImages?: number; // 0-3 for streaming
+}
+
+/**
+ * Options for image editing
+ */
+export interface ImageEditOptions {
+  image: Buffer;
+  prompt: string;
+  mask?: Buffer;
+  model?: 'gpt-image-1' | 'dall-e-2';
+  quality?: 'low' | 'medium' | 'high' | 'standard' | 'auto';
+  size?: '256x256' | '512x512' | '1024x1024' | '1536x1024' | '1024x1536' | 'auto';
+  background?: 'transparent' | 'opaque' | 'auto';
+  outputFormat?: 'png' | 'jpeg' | 'webp';
+  outputCompression?: number;
+  n?: number;
+  stream?: boolean;
+  partialImages?: number;
+}
+
+/**
+ * Response format for image operations
+ */
+export interface ImageResponse {
+  images: Array<{
+    b64_json?: string;
+    url?: string;
+    revisedPrompt?: string;
+  }>;
+  metadata?: {
+    model: string;
+    quality?: string;
+    size?: string;
+    outputFormat?: string;
+    tokensUsed?: number;
+  };
+}
+
 /**
  * Abstract base class for multi-modal AI models.
  * Provides a common interface for different AI providers (OpenAI, Anthropic, Perplexity, Ollama)
@@ -98,4 +177,28 @@ export abstract class MultiModalModel {
     pdfDocuments: Uint8Array[];
     messageHistory: ChatMessage[];
   }): Promise<{ message: any }>;
+
+  /**
+   * Research and web search capabilities
+   * @param optionsArg Options containing the research query and configuration
+   * @returns Promise resolving to the research results with sources
+   * @throws Error if the provider doesn't support research capabilities
+   */
+  public abstract research(optionsArg: ResearchOptions): Promise<ResearchResponse>;
+
+  /**
+   * Image generation from text prompts
+   * @param optionsArg Options containing the prompt and generation parameters
+   * @returns Promise resolving to the generated image(s)
+   * @throws Error if the provider doesn't support image generation
+   */
+  public abstract imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse>;
+
+  /**
+   * Image editing and inpainting
+   * @param optionsArg Options containing the image, prompt, and editing parameters
+   * @returns Promise resolving to the edited image(s)
+   * @throws Error if the provider doesn't support image editing
+   */
+  public abstract imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse>;
 }

package/ts/index.ts

@@ -1,3 +1,9 @@
 export * from './classes.smartai.js';
 export * from './abstract.classes.multimodal.js';
 export * from './provider.openai.js';
+export * from './provider.anthropic.js';
+export * from './provider.perplexity.js';
+export * from './provider.groq.js';
+export * from './provider.ollama.js';
+export * from './provider.xai.js';
+export * from './provider.exo.js';

package/ts/provider.anthropic.ts

@@ -1,13 +1,25 @@
 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 {
+  ChatOptions,
+  ChatResponse,
+  ChatMessage,
+  ResearchOptions,
+  ResearchResponse,
+  ImageGenerateOptions,
+  ImageEditOptions,
+  ImageResponse
+} from './abstract.classes.multimodal.js';
 import type { ImageBlockParam, TextBlockParam } from '@anthropic-ai/sdk/resources/messages';
 
 type ContentBlock = ImageBlockParam | TextBlockParam;
 
 export interface IAnthropicProviderOptions {
   anthropicToken: string;
+  enableWebSearch?: boolean;
+  searchDomainAllowList?: string[];
+  searchDomainBlockList?: string[];
 }
 
 export class AnthropicProvider extends MultiModalModel {
@@ -65,7 +77,7 @@ export class AnthropicProvider extends MultiModalModel {
         // If we have a complete message, send it to Anthropic
         if (currentMessage) {
           const stream = await this.anthropicApiClient.messages.create({
-            model: 'claude-3-opus-20240229',
+            model: 'claude-sonnet-4-5-20250929',
             messages: [{ role: currentMessage.role, content: currentMessage.content }],
             system: '',
             stream: true,
@@ -109,7 +121,7 @@ export class AnthropicProvider extends MultiModalModel {
     }));
 
     const result = await this.anthropicApiClient.messages.create({
-      model: 'claude-3-opus-20240229',
+      model: 'claude-sonnet-4-5-20250929',
       system: optionsArg.systemMessage,
       messages: [
         ...messages,
@@ -156,7 +168,7 @@ export class AnthropicProvider extends MultiModalModel {
     ];
 
     const result = await this.anthropicApiClient.messages.create({
-      model: 'claude-3-opus-20240229',
+      model: 'claude-sonnet-4-5-20250929',
       messages: [{
         role: 'user',
         content
@@ -215,7 +227,7 @@ export class AnthropicProvider extends MultiModalModel {
     }
 
     const result = await this.anthropicApiClient.messages.create({
-      model: 'claude-3-opus-20240229',
+      model: 'claude-sonnet-4-5-20250929',
       system: optionsArg.systemMessage,
       messages: [
         ...messages,
@@ -239,4 +251,155 @@ export class AnthropicProvider extends MultiModalModel {
       }
     };
   }
+
+  public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
+    // Prepare the messages for the research request
+    const systemMessage = `You are a research assistant with web search capabilities.
+    Provide comprehensive, well-researched answers with citations and sources.
+    When searching the web, be thorough and cite your sources accurately.`;
+
+    try {
+      // Build the tool configuration for web search
+      const tools: any[] = [];
+
+      if (this.options.enableWebSearch) {
+        const webSearchTool: any = {
+          type: 'web_search_20250305',
+          name: 'web_search'
+        };
+
+        // Add optional parameters
+        if (optionsArg.maxSources) {
+          webSearchTool.max_uses = optionsArg.maxSources;
+        }
+
+        if (this.options.searchDomainAllowList?.length) {
+          webSearchTool.allowed_domains = this.options.searchDomainAllowList;
+        } else if (this.options.searchDomainBlockList?.length) {
+          webSearchTool.blocked_domains = this.options.searchDomainBlockList;
+        }
+
+        tools.push(webSearchTool);
+      }
+
+      // Configure the request based on search depth
+      const maxTokens = optionsArg.searchDepth === 'deep' ? 8192 :
+                        optionsArg.searchDepth === 'advanced' ? 6144 : 4096;
+
+      // Create the research request
+      const requestParams: any = {
+        model: 'claude-sonnet-4-5-20250929',
+        system: systemMessage,
+        messages: [
+          {
+            role: 'user' as const,
+            content: optionsArg.query
+          }
+        ],
+        max_tokens: maxTokens,
+        temperature: 0.7
+      };
+
+      // Add tools if web search is enabled
+      if (tools.length > 0) {
+        requestParams.tools = tools;
+      }
+
+      // Execute the research request
+      const result = await this.anthropicApiClient.messages.create(requestParams);
+
+      // Extract the answer from content blocks
+      let answer = '';
+      const sources: Array<{ url: string; title: string; snippet: string }> = [];
+      const searchQueries: string[] = [];
+
+      // Process content blocks
+      for (const block of result.content) {
+        if ('text' in block) {
+          // Accumulate text content
+          answer += block.text;
+
+          // Extract citations if present
+          if ('citations' in block && Array.isArray(block.citations)) {
+            for (const citation of block.citations) {
+              if (citation.type === 'web_search_result_location') {
+                sources.push({
+                  title: citation.title || '',
+                  url: citation.url || '',
+                  snippet: citation.cited_text || ''
+                });
+              }
+            }
+          }
+        } else if ('type' in block && block.type === 'server_tool_use') {
+          // Extract search queries from server tool use
+          if (block.name === 'web_search' && block.input && typeof block.input === 'object' && 'query' in block.input) {
+            searchQueries.push((block.input as any).query);
+          }
+        } else if ('type' in block && block.type === 'web_search_tool_result') {
+          // Extract sources from web search results
+          if (Array.isArray(block.content)) {
+            for (const result of block.content) {
+              if (result.type === 'web_search_result') {
+                // Only add if not already in sources (avoid duplicates from citations)
+                if (!sources.some(s => s.url === result.url)) {
+                  sources.push({
+                    title: result.title || '',
+                    url: result.url || '',
+                    snippet: '' // Search results don't include snippets, only citations do
+                  });
+                }
+              }
+            }
+          }
+        }
+      }
+
+      // Fallback: Parse markdown-style links if no citations found
+      if (sources.length === 0) {
+        const urlRegex = /\[([^\]]+)\]\(([^)]+)\)/g;
+        let match: RegExpExecArray | null;
+
+        while ((match = urlRegex.exec(answer)) !== null) {
+          sources.push({
+            title: match[1],
+            url: match[2],
+            snippet: ''
+          });
+        }
+      }
+
+      // Check if web search was used based on usage info
+      const webSearchCount = result.usage?.server_tool_use?.web_search_requests || 0;
+
+      return {
+        answer,
+        sources,
+        searchQueries: searchQueries.length > 0 ? searchQueries : undefined,
+        metadata: {
+          model: 'claude-sonnet-4-5-20250929',
+          searchDepth: optionsArg.searchDepth || 'basic',
+          tokensUsed: result.usage?.output_tokens,
+          webSearchesPerformed: webSearchCount
+        }
+      };
+    } catch (error) {
+      console.error('Anthropic research error:', error);
+      throw new Error(`Failed to perform research: ${error.message}`);
+    }
+  }
+
+  /**
+   * Image generation is not supported by Anthropic
+   */
+  public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
+    throw new Error('Image generation is not supported by Anthropic. Claude can only analyze images, not generate them. Please use OpenAI provider for image generation.');
+  }
+
+  /**
+   * Image editing is not supported by Anthropic
+   */
+  public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
+    throw new Error('Image editing is not supported by Anthropic. Claude can only analyze images, not edit them. Please use OpenAI provider for image editing.');
+  }
 }

package/ts/provider.exo.ts

@@ -1,7 +1,16 @@
 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 {
+  ChatOptions,
+  ChatResponse,
+  ChatMessage,
+  ResearchOptions,
+  ResearchResponse,
+  ImageGenerateOptions,
+  ImageEditOptions,
+  ImageResponse
+} from './abstract.classes.multimodal.js';
 import type { ChatCompletionMessageParam } from 'openai/resources/chat/completions';
 
 export interface IExoProviderOptions {
@@ -125,4 +134,22 @@ export class ExoProvider extends MultiModalModel {
   }): Promise<{ message: any }> {
     throw new Error('Document processing is not supported by Exo provider');
   }
+
+  public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
+    throw new Error('Research capabilities are not yet supported by Exo provider.');
+  }
+
+  /**
+   * Image generation is not supported by Exo
+   */
+  public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
+    throw new Error('Image generation is not supported by Exo. Please use OpenAI provider for image generation.');
+  }
+
+  /**
+   * Image editing is not supported by Exo
+   */
+  public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
+    throw new Error('Image editing is not supported by Exo. Please use OpenAI provider for image editing.');
+  }
 }

package/ts/provider.groq.ts

@@ -1,7 +1,16 @@
 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 {
+  ChatOptions,
+  ChatResponse,
+  ChatMessage,
+  ResearchOptions,
+  ResearchResponse,
+  ImageGenerateOptions,
+  ImageEditOptions,
+  ImageResponse
+} from './abstract.classes.multimodal.js';
 
 export interface IGroqProviderOptions {
   groqToken: string;
@@ -189,4 +198,22 @@ export class GroqProvider extends MultiModalModel {
   }): Promise<{ message: any }> {
     throw new Error('Document processing is not yet supported by Groq.');
   }
+
+  public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
+    throw new Error('Research capabilities are not yet supported by Groq provider.');
+  }
+
+  /**
+   * Image generation is not supported by Groq
+   */
+  public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
+    throw new Error('Image generation is not supported by Groq. Please use OpenAI provider for image generation.');
+  }
+
+  /**
+   * Image editing is not supported by Groq
+   */
+  public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
+    throw new Error('Image editing is not supported by Groq. Please use OpenAI provider for image editing.');
+  }
 }

package/ts/provider.ollama.ts

@@ -1,7 +1,16 @@
 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 {
+  ChatOptions,
+  ChatResponse,
+  ChatMessage,
+  ResearchOptions,
+  ResearchResponse,
+  ImageGenerateOptions,
+  ImageEditOptions,
+  ImageResponse
+} from './abstract.classes.multimodal.js';
 
 export interface IOllamaProviderOptions {
   baseUrl?: string;
@@ -251,4 +260,22 @@ export class OllamaProvider extends MultiModalModel {
       }
     };
   }
+
+  public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
+    throw new Error('Research capabilities are not yet supported by Ollama provider.');
+  }
+
+  /**
+   * Image generation is not supported by Ollama
+   */
+  public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
+    throw new Error('Image generation is not supported by Ollama. Please use OpenAI provider for image generation.');
+  }
+
+  /**
+   * Image editing is not supported by Ollama
+   */
+  public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
+    throw new Error('Image editing is not supported by Ollama. Please use OpenAI provider for image editing.');
+  }
 }