Use “Groq chat completion brief” in Recued. Low-latency Groq chat workflow. It reads the selected model metadata, creates one non-streaming chat completion from an explicit question, and summarizes answer quality, finish reason, model, and token usage.

How it works 7 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (7 steps)

◆ model_details recued-core.groq.model.read

Read model on groq

◆ completion recued-core.groq.chat_completion.create

Create chat completion on groq

■ choices default

Apply default

■ choice_count count

Count items in choices

✦ summarize core.ai.summarize

AI generates a concise summary

■ choice_table to_table

Format results as a data table

■ card to_summary

Format results as a summary card

▼

Output

summary card

table choice_table

Settings 7 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

focus setting = Summarize the Groq answer, model metadata, finish reason, uncertainty, and token usage. Use only the Groq response and model metadata.

model setting = llama-3.3-70b-versatile

question setting = [object Object]

max length setting = 800

temperature setting = 0.2

system prompt setting = Answer concisely, call out uncertainty, and avoid inventing facts not present in the prompt.

max completion tokens setting = 900