Service category | Service description |
Text embedding | OpenSearch Text Vectorization Service-001: Provides multilingual (40+) text vectorization service, with maximum input text length of 300 tokens and output vector dimension of 1536. ID: ops-text-embedding-001 OpenSearch General Text Vectorization Service-002: Provides multilingual (100+) text vectorization service, with maximum input text length of 8192 tokens and output vector dimension of 1024. ID: ops-text-embedding-002 OpenSearch Text Vectorization Service-Chinese-001: Provides Chinese text vectorization service, with maximum input text length of 1024 tokens and output vector dimension of 768. ID: ops-text-embedding-zh-001 OpenSearch Text Vectorization Service-English-001: Provides English text vectorization service, with maximum input text length of 512 tokens and output vector dimension of 768. ID: ops-text-embedding-en-001
|
Content generation service | OpenSearch-Qwen-Turbo: Uses qwen-turbo large language model as the foundation model, with supervised model fine-tuning, enhanced retrieval augmentation, and reduced harmfulness. ID: ops-qwen-turbo Qwen-Turbo: The fastest and most cost-effective model in the Qwen series, suitable for simple tasks. For more information, see Qwen-Turbo. ID: qwen-turbo Qwen-Plus: Balanced capabilities with inference effect, cost, and speed between Qwen-Max and Qwen-Turbo, suitable for moderately complex tasks. For more information, see Qwen-Plus. ID: qwen-plus Qwen-Max: The best performing model in the Qwen series, suitable for complex, multi-step tasks. For more information, see Qwen-Max. ID: qwen-max DeepSeek-R1: A large language model focused on complex reasoning tasks, with outstanding performance in complex instruction understanding and result accuracy. ID: deepseek-r1 DeepSeek-V3: An MoE model with excellent performance in long text, code, mathematics, encyclopedia, and Chinese language capabilities. ID: deepseek-v3 DeepSeek-R1-distill-qwen-7b: A model based on knowledge distillation technology, fine-tuned on Qwen-7B using training samples generated by DeepSeek-R1. ID: deepseek-r1-distill-qwen-7b DeepSeek-R1-distill-qwen-14b: A model based on knowledge distillation technology, fine-tuned on Qwen-14B using training samples generated by DeepSeek-R1. ID: deepseek-r1-distill-qwen-14b
|