/
Deepseek AI

Deepseek AI

UChat now enables users to integrate natively with the DeepSeek AI platform, bringing cutting-edge AI capabilities into their chatbots.

https://youtu.be/aXpaUHMFEzE?si=fasHJMV6vWAkPunD

Fetching the DeepSeek API Key

In order to fetch the API key, login into DeepSeek

Setting Up DeepSeek AI

Go to Integrations -> Artificial Intelligence, select DeepSeek and insert your API token

(Image-1) 

Once you’ve integrated, you can access DeepSeek’s features directly through the Flow Builder under the Integrations action node.

Using DeepSeek Inside Flow Builder:

You can use DeepSeek inside the flow builder using the action node. Make an action node and select the Integrations option. From the menu that appears, click on DeepDeek.

DeepSeek AI Available Actions:

DeepSeek’s capabilities are comparable to OpenAI Chat Completion or Claude, making it intuitive for seasoned users. 

Let’s break down the main features:

Create Chat Completion

Easily create engaging and dynamic conversations by configuring the Chat Completion action.

System messages can be personalized.

Clear Remembered Chat History

This action clears the “DeepSeek” system field JSON. The use case is to control the history and monitor the execution time of requests to avoid server timeouts and token overconsumption.

List Models

DeepSeek Chat: A fast, conversational model ideal for quick user interactions.

DeepSeek Reasoner: More detailed and structured, perfect for use cases requiring logical processing (e.g., troubleshooting or technical queries).

Building a Test Chat Flow

 After integrating DeepSeek, here’s a sample setup for testing:

Sample System Message:

You are Chad. You are to engage with the user using small talk. Follow the below guidelines for responses:
Guideline for responses:

  • reply in first person

  • tone of voice is witty

  • use fitting emojis

  • you are not allowed to mention you are an Al or assume any other persona than what is described above

  • you are not allowed to talk about politics or religious

Set Max Tokens to 200 and Temperature to 0.4 for optimal response quality.

Enable Remember History for ongoing conversations.