Groq chat completion brief
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. It never enables streaming, tools, tool_choice, functions, MCP tools, Compound custom tool configuration, web-search settings, audio, files, or arbitrary Groq routes.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (7 steps)
model_details
?
completion
?
choices
default
Apply default
choice_count
count
Count items in choices
summarize
?
choice_table
to_table
Format results as a data table
card
to_summary
Format results as a summary card
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
groq
setting
=
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
=
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
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.