push.rocks/smartai
3
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(providers): Add research API and image generation/editing support; extend providers and tests

Browse Source
This commit is contained in:
Jürgen Kunz
2025-10-03 13:43:29 +00:00
parent fe8540c8ba
commit f0556e89f3
13 changed files with 612 additions and 194 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ts/00_commitinfo_data.ts
View File

@@ -3,6 +3,6 @@
*/
export const commitinfo = {
name: '@push.rocks/smartai',
version: '0.6.1',
version: '0.7.0',
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.'
}

70
ts/abstract.classes.multimodal.ts
View File

@@ -50,6 +50,60 @@ export interface ResearchResponse {
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)
@@ -131,4 +185,20 @@ export abstract class MultiModalModel {
* @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>;
}

25
ts/provider.anthropic.ts
View File

@@ -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, ResearchOptions, ResearchResponse } 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;
@@ -379,4 +388,18 @@ export class AnthropicProvider extends MultiModalModel {
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.');
}
}

25
ts/provider.exo.ts
View File

@@ -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, ResearchOptions, ResearchResponse } 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 {
@@ -129,4 +138,18 @@ export class ExoProvider extends MultiModalModel {
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.');
}
}

25
ts/provider.groq.ts
View File

@@ -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, ResearchOptions, ResearchResponse } 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;
@@ -193,4 +202,18 @@ export class GroqProvider extends MultiModalModel {
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.');
}
}

25
ts/provider.ollama.ts
View File

@@ -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, ResearchOptions, ResearchResponse } 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;
@@ -255,4 +264,18 @@ 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.');
}
}

126
ts/provider.openai.ts
View File

@@ -9,7 +9,13 @@ export type TChatCompletionRequestMessage = {
};
import { MultiModalModel } from './abstract.classes.multimodal.js';
import type { ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
import type {
ResearchOptions,
ResearchResponse,
ImageGenerateOptions,
ImageEditOptions,
ImageResponse
} from './abstract.classes.multimodal.js';
export interface IOpenaiProviderOptions {
openaiToken: string;
@@ -17,6 +23,7 @@ export interface IOpenaiProviderOptions {
audioModel?: string;
visionModel?: string;
researchModel?: string;
imageModel?: string;
enableWebSearch?: boolean;
}
@@ -328,4 +335,121 @@ export class OpenAiProvider extends MultiModalModel {
throw new Error(`Failed to perform research: ${error.message}`);
}
}
/**
* Image generation using OpenAI's gpt-image-1 or DALL-E models
*/
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
const model = optionsArg.model || this.options.imageModel || 'gpt-image-1';
try {
const requestParams: any = {
model,
prompt: optionsArg.prompt,
n: optionsArg.n || 1,
};
// Add gpt-image-1 specific parameters
if (model === 'gpt-image-1') {
if (optionsArg.quality) requestParams.quality = optionsArg.quality;
if (optionsArg.size) requestParams.size = optionsArg.size;
if (optionsArg.background) requestParams.background = optionsArg.background;
if (optionsArg.outputFormat) requestParams.output_format = optionsArg.outputFormat;
if (optionsArg.outputCompression !== undefined) requestParams.output_compression = optionsArg.outputCompression;
if (optionsArg.moderation) requestParams.moderation = optionsArg.moderation;
if (optionsArg.stream !== undefined) requestParams.stream = optionsArg.stream;
if (optionsArg.partialImages !== undefined) requestParams.partial_images = optionsArg.partialImages;
} else if (model === 'dall-e-3') {
// DALL-E 3 specific parameters
if (optionsArg.quality) requestParams.quality = optionsArg.quality;
if (optionsArg.size) requestParams.size = optionsArg.size;
if (optionsArg.style) requestParams.style = optionsArg.style;
requestParams.response_format = 'b64_json'; // Always use base64 for consistency
} else if (model === 'dall-e-2') {
// DALL-E 2 specific parameters
if (optionsArg.size) requestParams.size = optionsArg.size;
requestParams.response_format = 'b64_json';
}
const result = await this.openAiApiClient.images.generate(requestParams);
const images = (result.data || []).map(img => ({
b64_json: img.b64_json,
url: img.url,
revisedPrompt: img.revised_prompt
}));
return {
images,
metadata: {
model,
quality: result.quality,
size: result.size,
outputFormat: result.output_format,
tokensUsed: result.usage?.total_tokens
}
};
} catch (error) {
console.error('Image generation error:', error);
throw new Error(`Failed to generate image: ${error.message}`);
}
}
/**
* Image editing using OpenAI's gpt-image-1 or DALL-E 2 models
*/
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
const model = optionsArg.model || this.options.imageModel || 'gpt-image-1';
try {
const requestParams: any = {
model,
image: optionsArg.image,
prompt: optionsArg.prompt,
n: optionsArg.n || 1,
};
// Add mask if provided
if (optionsArg.mask) {
requestParams.mask = optionsArg.mask;
}
// Add gpt-image-1 specific parameters
if (model === 'gpt-image-1') {
if (optionsArg.quality) requestParams.quality = optionsArg.quality;
if (optionsArg.size) requestParams.size = optionsArg.size;
if (optionsArg.background) requestParams.background = optionsArg.background;
if (optionsArg.outputFormat) requestParams.output_format = optionsArg.outputFormat;
if (optionsArg.outputCompression !== undefined) requestParams.output_compression = optionsArg.outputCompression;
if (optionsArg.stream !== undefined) requestParams.stream = optionsArg.stream;
if (optionsArg.partialImages !== undefined) requestParams.partial_images = optionsArg.partialImages;
} else if (model === 'dall-e-2') {
// DALL-E 2 specific parameters
if (optionsArg.size) requestParams.size = optionsArg.size;
requestParams.response_format = 'b64_json';
}
const result = await this.openAiApiClient.images.edit(requestParams);
const images = (result.data || []).map(img => ({
b64_json: img.b64_json,
url: img.url,
revisedPrompt: img.revised_prompt
}));
return {
images,
metadata: {
model,
quality: result.quality,
size: result.size,
outputFormat: result.output_format,
tokensUsed: result.usage?.total_tokens
}
};
} catch (error) {
console.error('Image edit error:', error);
throw new Error(`Failed to edit image: ${error.message}`);
}
}
}

25
ts/provider.perplexity.ts
View File

@@ -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, ResearchOptions, ResearchResponse } from './abstract.classes.multimodal.js';
import type {
ChatOptions,
ChatResponse,
ChatMessage,
ResearchOptions,
ResearchResponse,
ImageGenerateOptions,
ImageEditOptions,
ImageResponse
} from './abstract.classes.multimodal.js';
export interface IPerplexityProviderOptions {
perplexityToken: string;
@@ -233,4 +242,18 @@ export class PerplexityProvider extends MultiModalModel {
throw new Error(`Failed to perform research: ${error.message}`);
}
}
/**
* Image generation is not supported by Perplexity
*/
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
throw new Error('Image generation is not supported by Perplexity. Please use OpenAI provider for image generation.');
}
/**
* Image editing is not supported by Perplexity
*/
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
throw new Error('Image editing is not supported by Perplexity. Please use OpenAI provider for image editing.');
}
}

25
ts/provider.xai.ts
View File

@@ -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, ResearchOptions, ResearchResponse } 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 IXAIProviderOptions {
@@ -185,4 +194,18 @@ export class XAIProvider extends MultiModalModel {
public async research(optionsArg: ResearchOptions): Promise<ResearchResponse> {
throw new Error('Research capabilities are not yet supported by xAI provider.');
}
/**
* Image generation is not supported by xAI
*/
public async imageGenerate(optionsArg: ImageGenerateOptions): Promise<ImageResponse> {
throw new Error('Image generation is not supported by xAI. Please use OpenAI provider for image generation.');
}
/**
* Image editing is not supported by xAI
*/
public async imageEdit(optionsArg: ImageEditOptions): Promise<ImageResponse> {
throw new Error('Image editing is not supported by xAI. Please use OpenAI provider for image editing.');
}
}