DingTalk has announced that its AI Assistant is now fully integrated with the DeepSeek series models, providing users with more intelligent options. When creating an AI Assistant, users can choose the DeepSeek R1&V3671B model as well as the distilled series models.
Additionally, DingTalk has launched a brand new template that simplifies the creation process of the AI Assistant, allowing users to publish assistants based on DeepSeek models with just one click.
The AI Assistant based on DeepSeek not only possesses deep thinking capabilities but also supports online query functions. Users can easily create an AI Assistant that suits their needs without complex configurations. In workflow configurations, users can also select the appropriate DeepSeek series model according to their requirements, greatly enhancing flexibility and convenience.
It is worth noting that DingTalk's low-code platform, Yida, has also integrated with DeepSeek. Users can generate prompts through Yida to leverage the capabilities of DeepSeek, showcasing extensive application potential in scenarios such as data analysis and text generation. Recently, an intelligent comment generation application created based on the combination of Yida and DeepSeek has also been well received by users.
DingTalk officially launched the AI Assistant in January 2024. This assistant is based on a universal large model and possesses multiple capabilities including perception, memory, planning, and action. As of the end of May 2023, there are already 500,000 AI Assistants in use on DingTalk.
Key Points:
🌟 DingTalk AI Assistant integrates with the DeepSeek series models, allowing users to choose from various models.
🚀 New template released, enabling users to create deep-thinking AI Assistants with one click.
🔍 Low-code platform Yida combines with DeepSeek, expanding application scenarios.
