DeepSeek

Generate text and code completions using DeepSeek models.

AI and MLAPI key1 actionAll integrations

On this page

Connect
Call it from a workflow
Actions (1)
ask_deepseek
Details

Connect

Auth type: API key (secret_text). Paste the API key (or token) from the provider's settings into the connect dialog. It is encrypted at rest and only decrypted on the server when an action runs.

In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
For every project in a workspace: Workspace settings, Integrations.
Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.

Call it from a workflow

Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.

Native workflow

// .workflow.js (native ctx)
export async function run(ctx) {
  const res = await ctx.integrations.invoke("deepseek", "ask_deepseek", {
    "model": "<model>",
    "prompt": "<question>",
    "maxTokens": 1,
    "responseFormat": "text"
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("DeepSeek answered", { output: res.output });
}

defineWorkflow module

// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";

export default defineWorkflow({
  id: "deepseek-ask-deepseek",
  name: "DeepSeek: Ask Deepseek",
  description: "Calls DeepSeek when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("deepseek", {
      "action": "ask_deepseek",
      "model": "<model>",
      "prompt": "<question>",
      "maxTokens": 1,
      "responseFormat": "text"
    }) as { success: boolean; error?: string };
    if (!res.success) throw new Error(res.error);
  },
});

From an app (connector proxy)

curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/deepseek/ask_deepseek" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"model":"<model>","prompt":"<question>","maxTokens":1,"responseFormat":"text"}}'

Actions

ask_deepseekin catalog

Ask Deepseek. Ask Deepseek anything you want!

Input	Type	Description
`model`required	id (picked from your account)	The model which will generate the completion.
`prompt`required	long text	Question
`frequencyPenalty`optional	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
`maxTokens`required	number	The maximum number of tokens to generate. Possible values are between 1 and 8192.
`presencePenalty`optional	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the mode's likelihood to talk about new topics.
`responseFormat`required	one of "text" \| "json_object"	The format of the response. IMPORTANT: When using JSON Output, you must also instruct the model to produce JSON yourself
`temperature`optional	number	Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Between 0 and 2. We generally recommend alter…
`topP`optional	number	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top …
`memoryKey`optional	text	A memory key that will keep the chat history shared across runs and flows. Keep it empty to leave Deepseek without memory of previous messages.
`roles`optional	JSON	Array of roles to specify more accurate response

Details

Id: deepseek
Category: AI and ML
Tags: ai, deepseek, llm, code-generation
Package: @activepieces/piece-deepseek@0.1.3
Tier: Built in