DeepSeek

DeepSeek

Properties used to connect to DeepSeek AI.

deepSeek

• Type: {
       model?: string,
       temperature?: number,
       max_tokens?: number,
       top_p?: number,
       frequency_penalty?: number,
       presence_penalty?: number,
       stop?: string | string[],
       system_prompt?: string
  }
• Default: {model: "deepseek-chat", temperature: 1, max_tokens: 4096}

Connect to DeepSeek's chat completion API.
model is the DeepSeek model to use ("deepseek-chat" or "deepseek-reasoner").
temperature controls randomness (0.0-2.0). Higher values produce more creative outputs.
max_tokens limits the maximum number of tokens in the response (1-8192).
top_p controls diversity through nucleus sampling (0.0-1.0).
frequency_penalty penalizes tokens based on their frequency in the text (-2.0 to 2.0).
presence_penalty penalizes tokens based on their presence in the text (-2.0 to 2.0).
stop defines sequences where the API will stop generating (up to 16 sequences).
system_prompt provides behavioral context and instructions to the model.

Example

Sample code

<deep-chat
  directConnection='{
    "deepSeek": {
      "key": "placeholder key",
      "system_prompt": "You are a helpful assistant.",
      "temperature": 0.7
    }
  }'
></deep-chat>

Full code

<!-- This example is for Vanilla JS and should be tailored to your framework (see Examples) -->

<deep-chat
  directConnection='{
    "deepSeek": {
      "key": "placeholder key",
      "system_prompt": "You are a helpful assistant.",
      "temperature": 0.7
    }
  }'
  style="border-radius: 8px"
></deep-chat>

info

Use stream to stream the AI responses.