Chat Completions

Create a guarded chat completion

Generate a chat completion with guardrails applied.

The request shape is compatible with the OpenAI Chat Completions API and accepts Guardrails-specific options in the guardrails object.

post/v1/chat/completions

Request body

modelstring required

LLM model to use for the completion.

streamboolean

Return partial message deltas as server-sent events.

max_tokensinteger

Maximum number of tokens to generate.

temperaturenumber float

Sampling temperature.

top_pnumber float

Top-p sampling parameter.

presence_penaltynumber float

Presence penalty parameter.

frequency_penaltynumber float

Frequency penalty parameter.

function_callobject

Function call parameter.

logit_biasobject

Logit bias parameter.

logprobsboolean

Log probabilities parameter.

{
  "model": "meta/llama-3.1-8b-instruct",
  "messages": [
    {
      "role": "user"
    }
  ]
}

Chat completion response or server-sent event stream.

idstring

objectstring

createdinteger

modelstring

{
  "object": "chat.completion",
  "choices": [
    {
      "message": {
        "role": "user"
      }
    }
  ]
}

Changed in 1 of the 3 revisions of this API.11