Send Prompt for JSON response

Sends a prompt to LLM and generate a completion returning a response message in JSON format.

Deepseek Action

Automating tasks with the Send Prompt for JSON Response integration from Deepseek allows you to obtain structured JSON-formatted responses from advanced language models. This functionality is ideal for developers and businesses looking to enhance their workflows through the automatic generation of well-organized data.

With customization options such as model selection, temperature adjustment, and maximum token configuration, you can tailor responses to your specific needs. Additionally, the integration provides detailed information about the process, including the finish reason and token count, facilitating precise control over the generated responses.

Customization Options

Configurable fields you can adjust in your automation

Rules
Filter Rules
System message
New user message
Model
Temperature
Max Tokens
Remove potential surrounding quotation marks from LLM response
Customize tags
Rename output variables configuration

Information provided

When executed, this operation delivers the following data, which can be used in the same automatic task.

Tags
JSON Response {{json_response}}
Predicted completion in JSON format.
e.g. {"winner":"Los Angeles Dodgers"}
Finish reason {{finish_reason}}
reason why the resulting text has terminated.
e.g. lenght
Prompt tokens {{prompt_tokens}}
Number of tokens in the Prompt. 1 token ~= 4 chars in English
Completion tokens {{completion_tokens}}
Number of tokens in the Completion. 1 token ~= 4 chars in English
Total tokens {{total_tokens}}
Prompt tokens + Completion tokens

Write us

By email or by Telegram.
Monday to Friday from 7 a.m. to 1 p.m. (Spain).

Let's talk