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
This commit is contained in:
@@ -13,16 +13,64 @@ export default class CohereProvider extends BaseProvider {
|
||||
};
|
||||
|
||||
staticModels: ModelInfo[] = [
|
||||
{ name: 'command-r-plus-08-2024', label: 'Command R plus Latest', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'command-r-08-2024', label: 'Command R Latest', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'command-r-plus', label: 'Command R plus', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'command-r', label: 'Command R', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'command', label: 'Command', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'command-nightly', label: 'Command Nightly', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'command-light', label: 'Command Light', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'command-light-nightly', label: 'Command Light Nightly', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'c4ai-aya-expanse-8b', label: 'c4AI Aya Expanse 8b', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{ name: 'c4ai-aya-expanse-32b', label: 'c4AI Aya Expanse 32b', provider: 'Cohere', maxTokenAllowed: 4096 },
|
||||
{
|
||||
name: 'command-r-plus-08-2024',
|
||||
label: 'Command R plus Latest',
|
||||
provider: 'Cohere',
|
||||
maxTokenAllowed: 4096,
|
||||
maxCompletionTokens: 4000,
|
||||
},
|
||||
{
|
||||
name: 'command-r-08-2024',
|
||||
label: 'Command R Latest',
|
||||
provider: 'Cohere',
|
||||
maxTokenAllowed: 4096,
|
||||
maxCompletionTokens: 4000,
|
||||
},
|
||||
{
|
||||
name: 'command-r-plus',
|
||||
label: 'Command R plus',
|
||||
provider: 'Cohere',
|
||||
maxTokenAllowed: 4096,
|
||||
maxCompletionTokens: 4000,
|
||||
},
|
||||
{ name: 'command-r', label: 'Command R', provider: 'Cohere', maxTokenAllowed: 4096, maxCompletionTokens: 4000 },
|
||||
{ name: 'command', label: 'Command', provider: 'Cohere', maxTokenAllowed: 4096, maxCompletionTokens: 4000 },
|
||||
{
|
||||
name: 'command-nightly',
|
||||
label: 'Command Nightly',
|
||||
provider: 'Cohere',
|
||||
maxTokenAllowed: 4096,
|
||||
maxCompletionTokens: 4000,
|
||||
},
|
||||
{
|
||||
name: 'command-light',
|
||||
label: 'Command Light',
|
||||
provider: 'Cohere',
|
||||
maxTokenAllowed: 4096,
|
||||
maxCompletionTokens: 4000,
|
||||
},
|
||||
{
|
||||
name: 'command-light-nightly',
|
||||
label: 'Command Light Nightly',
|
||||
provider: 'Cohere',
|
||||
maxTokenAllowed: 4096,
|
||||
maxCompletionTokens: 4000,
|
||||
},
|
||||
{
|
||||
name: 'c4ai-aya-expanse-8b',
|
||||
label: 'c4AI Aya Expanse 8b',
|
||||
provider: 'Cohere',
|
||||
maxTokenAllowed: 4096,
|
||||
maxCompletionTokens: 4000,
|
||||
},
|
||||
{
|
||||
name: 'c4ai-aya-expanse-32b',
|
||||
label: 'c4AI Aya Expanse 32b',
|
||||
provider: 'Cohere',
|
||||
maxTokenAllowed: 4096,
|
||||
maxCompletionTokens: 4000,
|
||||
},
|
||||
];
|
||||
|
||||
getModelInstance(options: {
|
||||
|
||||
Reference in New Issue
Block a user