Files
bolt-diy/app/lib/modules/llm/providers/together.ts
Stijnus ff8b0d7af1 fix: maxCompletionTokens Implementation for All Providers (#1938)
* Update LLM providers and constants

- Updated constants in app/lib/.server/llm/constants.ts
- Modified stream-text functionality in app/lib/.server/llm/stream-text.ts
- Updated Anthropic provider in app/lib/modules/llm/providers/anthropic.ts
- Modified GitHub provider in app/lib/modules/llm/providers/github.ts
- Updated Google provider in app/lib/modules/llm/providers/google.ts
- Modified OpenAI provider in app/lib/modules/llm/providers/openai.ts
- Updated LLM types in app/lib/modules/llm/types.ts
- Modified API route in app/routes/api.llmcall.ts

* Fix maxCompletionTokens Implementation for All Providers

 - Cohere: Added maxCompletionTokens: 4000 to all 10 static models
  - DeepSeek: Added maxCompletionTokens: 8192 to all 3 static models
  - Groq: Added maxCompletionTokens: 8192 to both static models
  - Mistral: Added maxCompletionTokens: 8192 to all 9 static models
  - Together: Added maxCompletionTokens: 8192 to both static models

  - Groq: Fixed getDynamicModels to include maxCompletionTokens: 8192
  - Together: Fixed getDynamicModels to include maxCompletionTokens: 8192
  - OpenAI: Fixed getDynamicModels with proper logic for reasoning models (o1: 16384, o1-mini: 8192) and standard models
2025-08-29 23:13:58 +02:00

99 lines
2.9 KiB
TypeScript

import { BaseProvider, getOpenAILikeModel } 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';
export default class TogetherProvider extends BaseProvider {
name = 'Together';
getApiKeyLink = 'https://api.together.xyz/settings/api-keys';
config = {
baseUrlKey: 'TOGETHER_API_BASE_URL',
apiTokenKey: 'TOGETHER_API_KEY',
};
staticModels: ModelInfo[] = [
/*
* Essential fallback models - only the most stable/reliable ones
* Llama 3.2 90B Vision: 128k context, multimodal capabilities
*/
{
name: 'meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo',
label: 'Llama 3.2 90B Vision',
provider: 'Together',
maxTokenAllowed: 128000,
maxCompletionTokens: 8192,
},
// Mixtral 8x7B: 32k context, strong performance
{
name: 'mistralai/Mixtral-8x7B-Instruct-v0.1',
label: 'Mixtral 8x7B Instruct',
provider: 'Together',
maxTokenAllowed: 32000,
maxCompletionTokens: 8192,
},
];
async getDynamicModels(
apiKeys?: Record<string, string>,
settings?: IProviderSetting,
serverEnv: Record<string, string> = {},
): Promise<ModelInfo[]> {
const { baseUrl: fetchBaseUrl, apiKey } = this.getProviderBaseUrlAndKey({
apiKeys,
providerSettings: settings,
serverEnv,
defaultBaseUrlKey: 'TOGETHER_API_BASE_URL',
defaultApiTokenKey: 'TOGETHER_API_KEY',
});
const baseUrl = fetchBaseUrl || 'https://api.together.xyz/v1';
if (!baseUrl || !apiKey) {
return [];
}
// console.log({ baseUrl, apiKey });
const response = await fetch(`${baseUrl}/models`, {
headers: {
Authorization: `Bearer ${apiKey}`,
},
});
const res = (await response.json()) as any;
const data = (res || []).filter((model: any) => model.type === 'chat');
return data.map((m: any) => ({
name: m.id,
label: `${m.display_name} - in:$${m.pricing.input.toFixed(2)} out:$${m.pricing.output.toFixed(2)} - context ${Math.floor(m.context_length / 1000)}k`,
provider: this.name,
maxTokenAllowed: 8000,
maxCompletionTokens: 8192,
}));
}
getModelInstance(options: {
model: string;
serverEnv: Env;
apiKeys?: Record<string, string>;
providerSettings?: Record<string, IProviderSetting>;
}): LanguageModelV1 {
const { model, serverEnv, apiKeys, providerSettings } = options;
const { baseUrl, apiKey } = this.getProviderBaseUrlAndKey({
apiKeys,
providerSettings: providerSettings?.[this.name],
serverEnv: serverEnv as any,
defaultBaseUrlKey: 'TOGETHER_API_BASE_URL',
defaultApiTokenKey: 'TOGETHER_API_KEY',
});
if (!baseUrl || !apiKey) {
throw new Error(`Missing configuration for ${this.name} provider`);
}
return getOpenAILikeModel(baseUrl, apiKey, model);
}
}