DeepSeek Component

DeepSeek is an AI developer of large language models (LLM) focused on providing high performance models.

Component key: deepseek

Changelog ↓

Description

DeepSeek is an AI developer of large language models (LLM) focused on providing high performance models.

Use the component to create chat completions with available models.

API Documentation:

The component was built using the DeepSeek API Documentation.

Connections

API Key

1. Login to DeepSeek and navigate to the API Keys section.
2. Select Create New API Key and enter into the connection configuration of the integration.

Input	Notes	Example
API Key	DeepSeek API Key.	ASDB1234567890
Base URL	The base URL of the DeepSeek API.	https://api.deepseek.com

Data Sources

Select Model

A picklist of available models from the DeepSeek API. | key: selectModel | type: picklist

Input	Notes	Example
Connection

---

Actions

Create Chat Completion

Creates a model response for the given chat conversation. | key: createChatCompletion

Input	Notes	Example
Connection
Frequency Penalty	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.	2
Include Usage	Only set this when you set stream: When true, an additional chunk will be streamed before the data: [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array. All other chunks will also include a usage field, but with a null value.	false
Should return Log Probabilities	Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.	false
Max Tokens	Integer between 1 and 8192. The maximum number of tokens that can be generated in the chat completion.The total length of input tokens and generated tokens is limited by the model's context length. If max_tokens is not specified, the default value 4096 is used.	100
Messages	A list of messages comprising the conversation so far.
Model	The model to use in order to generate the chat completion.
Presence Penalty	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.	2
Response Format	The format of the response. The response format can be either 'json_object' or 'text'.	json_object
Stop Sequence(s)	The stop sequence(s) to use in order to generate the chat completion.	stop1,stop2
Stream	If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available, with the stream terminated by a data: [DONE] message.	false
Temperature	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. [We generally recommend altering this or top_p but not both].	0.5
Tool Choice	Controls which (if any) tool is called by the model. using 'none' means the model will not call any tool and instead generates a message. using 'auto' means the model can pick between generating a message or calling one or more tools. using 'required' means the model must call one or more tools. Specifying a particular tool via {type: "function", function: {name: "my_function"}} forces the model to call that tool.none is the default when no tools are present. auto is the default if tools are present.	auto
Tools	The tools to use in order to generate the chat completion.
Top Log Probabilities	An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.	10
Top P	Number between 0 and 1. Higher values like 0.95 will make the output more random, while lower values like 0.05 will make it more focused and deterministic. [We generally recommend altering this or temperature but not both].	0.5

{
  "data": {
    "id": "930c60df-bf64-41c9-a88e-3ec75f81e00e",
    "choices": [
      {
        "finish_reason": "stop",
        "index": 0,
        "message": {
          "content": "Hello! How can I help you today?",
          "role": "assistant"
        }
      }
    ],
    "created": 1705651092,
    "model": "deepseek-chat",
    "object": "chat.completion",
    "usage": {
      "completion_tokens": 10,
      "prompt_tokens": 16,
      "total_tokens": 26
    }
  }
}

---

List Models

Retrieves the currently available models, and provides basic information about each one such as the owner and availability. | key: listModels

Input	Notes	Example
Connection

{
  "data": {
    "object": "list",
    "data": [
      {
        "id": "deepseek-chat",
        "object": "model",
        "owned_by": "deepseek"
      },
      {
        "id": "deepseek-reasoner",
        "object": "model",
        "owned_by": "deepseek"
      }
    ]
  }
}

---

Raw Request

Send a Raw Request to the DeepSeek API. | key: rawRequest

Input	Notes	Example
Connection
Data	The HTTP body payload to send to the URL.	{"exampleKey": "Example Data"}
Debug Request	Enabling this flag will log out the current request.	false
File Data	File Data to be sent as a multipart form upload.	[{key: "example.txt", value: "My File Contents"}]
File Data File Names	File names to apply to the file data inputs. Keys must match the file data keys above.
Form Data	The Form Data to be sent as a multipart form upload.	[{"key": "Example Key", "value": new Buffer("Hello World")}]
Header	A list of headers to send with the request.	User-Agent: curl/7.64.1
Max Retry Count	The maximum number of retries to attempt. Specify 0 for no retries.	0
Method	The HTTP method to use.
Query Parameter	A list of query parameters to send with the request. This is the portion at the end of the URL similar to ?key1=value1&key2=value2.
Response Type	The type of data you expect in the response. You can request json, text, or binary data.	json
Retry On All Errors	If true, retries on all erroneous responses regardless of type. This is helpful when retrying after HTTP 429 or other 3xx or 4xx errors. Otherwise, only retries on HTTP 5xx and network errors.	false
Retry Delay (ms)	The delay in milliseconds between retries. This is used when 'Use Exponential Backoff' is disabled.	0
Timeout	The maximum time that a client will await a response to its request	2000
URL	This is the URL to call.	/sobjects/Account
Use Exponential Backoff	Specifies whether to use a pre-defined exponential backoff strategy for retries. When enabled, 'Retry Delay (ms)' is ignored.	false

---

Changelog

2025-05-30

Initial release of Deepseek component with AI chat completion and model management capabilities.