ISSUES FIXED: - ❌ Invalid JSON response errors during streaming - ❌ Incorrect token limits causing API rejections - ❌ Outdated hardcoded model configurations - ❌ Poor error messages for API failures SOLUTIONS IMPLEMENTED: 🎯 ACCURATE TOKEN LIMITS & CONTEXT SIZES - OpenAI GPT-4o: 128k context (was 8k) - OpenAI GPT-3.5-turbo: 16k context (was 8k) - Anthropic Claude 3.5 Sonnet: 200k context (was 8k) - Anthropic Claude 3 Haiku: 200k context (was 8k) - Google Gemini 1.5 Pro: 2M context (was 8k) - Google Gemini 1.5 Flash: 1M context (was 8k) - Groq Llama models: 128k context (was 8k) - Together models: Updated with accurate limits �� DYNAMIC MODEL FETCHING ENHANCED - Smart context detection from provider APIs - Automatic fallback to known limits when API unavailable - Safety caps to prevent token overflow (100k max) - Intelligent model filtering and deduplication 🛡️ IMPROVED ERROR HANDLING - Specific error messages for Invalid JSON responses - Token limit exceeded warnings with solutions - API key validation with clear guidance - Rate limiting detection and user guidance - Network timeout handling ⚡ PERFORMANCE OPTIMIZATIONS - Reduced static models from 40+ to 12 essential - Enhanced streaming error detection - Better API response validation - Improved context window display (shows M/k units) 🔧 TECHNICAL IMPROVEMENTS - Dynamic model context detection from APIs - Enhanced streaming reliability - Better token limit enforcement - Comprehensive error categorization - Smart model validation before API calls IMPACT: ✅ Eliminates Invalid JSON response errors ✅ Prevents token limit API rejections ✅ Provides accurate model capabilities ✅ Improves user experience with clear errors ✅ Enables full utilization of modern LLM context windows
112 lines
3.5 KiB
TypeScript
112 lines
3.5 KiB
TypeScript
import { BaseProvider } from '~/lib/modules/llm/base-provider';
|
|
import type { ModelInfo } from '~/lib/modules/llm/types';
|
|
import type { IProviderSetting } from '~/types/model';
|
|
import type { LanguageModelV1 } from 'ai';
|
|
import { createOpenAI } from '@ai-sdk/openai';
|
|
|
|
export default class OpenAIProvider extends BaseProvider {
|
|
name = 'OpenAI';
|
|
getApiKeyLink = 'https://platform.openai.com/api-keys';
|
|
|
|
config = {
|
|
apiTokenKey: 'OPENAI_API_KEY',
|
|
};
|
|
|
|
staticModels: ModelInfo[] = [
|
|
/*
|
|
* Essential fallback models - only the most stable/reliable ones
|
|
* GPT-4o: 128k context, high performance, recommended for most tasks
|
|
*/
|
|
{ name: 'gpt-4o', label: 'GPT-4o', provider: 'OpenAI', maxTokenAllowed: 128000 },
|
|
|
|
// GPT-3.5-turbo: 16k context, fast and cost-effective
|
|
{ name: 'gpt-3.5-turbo', label: 'GPT-3.5 Turbo', provider: 'OpenAI', maxTokenAllowed: 16000 },
|
|
];
|
|
|
|
async getDynamicModels(
|
|
apiKeys?: Record<string, string>,
|
|
settings?: IProviderSetting,
|
|
serverEnv?: Record<string, string>,
|
|
): Promise<ModelInfo[]> {
|
|
const { apiKey } = this.getProviderBaseUrlAndKey({
|
|
apiKeys,
|
|
providerSettings: settings,
|
|
serverEnv: serverEnv as any,
|
|
defaultBaseUrlKey: '',
|
|
defaultApiTokenKey: 'OPENAI_API_KEY',
|
|
});
|
|
|
|
if (!apiKey) {
|
|
throw `Missing Api Key configuration for ${this.name} provider`;
|
|
}
|
|
|
|
const response = await fetch(`https://api.openai.com/v1/models`, {
|
|
headers: {
|
|
Authorization: `Bearer ${apiKey}`,
|
|
},
|
|
});
|
|
|
|
const res = (await response.json()) as any;
|
|
const staticModelIds = this.staticModels.map((m) => m.name);
|
|
|
|
const data = res.data.filter(
|
|
(model: any) =>
|
|
model.object === 'model' &&
|
|
(model.id.startsWith('gpt-') || model.id.startsWith('o') || model.id.startsWith('chatgpt-')) &&
|
|
!staticModelIds.includes(model.id),
|
|
);
|
|
|
|
return data.map((m: any) => {
|
|
// Get accurate context window from OpenAI API
|
|
let contextWindow = 32000; // default fallback
|
|
|
|
// OpenAI provides context_length in their API response
|
|
if (m.context_length) {
|
|
contextWindow = m.context_length;
|
|
} else if (m.id?.includes('gpt-4o')) {
|
|
contextWindow = 128000; // GPT-4o has 128k context
|
|
} else if (m.id?.includes('gpt-4-turbo') || m.id?.includes('gpt-4-1106')) {
|
|
contextWindow = 128000; // GPT-4 Turbo has 128k context
|
|
} else if (m.id?.includes('gpt-4')) {
|
|
contextWindow = 8192; // Standard GPT-4 has 8k context
|
|
} else if (m.id?.includes('gpt-3.5-turbo')) {
|
|
contextWindow = 16385; // GPT-3.5-turbo has 16k context
|
|
}
|
|
|
|
return {
|
|
name: m.id,
|
|
label: `${m.id} (${Math.floor(contextWindow / 1000)}k context)`,
|
|
provider: this.name,
|
|
maxTokenAllowed: Math.min(contextWindow, 128000), // Cap at 128k for safety
|
|
};
|
|
});
|
|
}
|
|
|
|
getModelInstance(options: {
|
|
model: string;
|
|
serverEnv: Env;
|
|
apiKeys?: Record<string, string>;
|
|
providerSettings?: Record<string, IProviderSetting>;
|
|
}): LanguageModelV1 {
|
|
const { model, serverEnv, apiKeys, providerSettings } = options;
|
|
|
|
const { apiKey } = this.getProviderBaseUrlAndKey({
|
|
apiKeys,
|
|
providerSettings: providerSettings?.[this.name],
|
|
serverEnv: serverEnv as any,
|
|
defaultBaseUrlKey: '',
|
|
defaultApiTokenKey: 'OPENAI_API_KEY',
|
|
});
|
|
|
|
if (!apiKey) {
|
|
throw new Error(`Missing API key for ${this.name} provider`);
|
|
}
|
|
|
|
const openai = createOpenAI({
|
|
apiKey,
|
|
});
|
|
|
|
return openai(model);
|
|
}
|
|
}
|