Skip to main content

​
POST /v1/chat/completions

Create a chat completion with guardrails applied. This endpoint is compatible with the OpenAI Chat Completions API with additional guardrails-specific extensions.

​
Request

​
model
string
required
The LLM model to use for chat completion (e.g., “gpt-4o”, “llama-3.1-8b”).
​
messages
array
The list of messages in the current conversation.
[
  {"role": "user", "content": "Hello!"},
  {"role": "assistant", "content": "Hi there!"}
]
​
stream
boolean
default:"false"
If set, partial message deltas will be sent as server-sent events.
​
max_tokens
integer
The maximum number of tokens to generate.
​
temperature
number
Sampling temperature to use (0.0 to 2.0).
​
top_p
number
Top-p sampling parameter (0.0 to 1.0).
​
stop
string | array
Stop sequences where the API will stop generating further tokens.
​
presence_penalty
number
Presence penalty parameter (-2.0 to 2.0).
​
frequency_penalty
number
Frequency penalty parameter (-2.0 to 2.0).

​
Guardrails Extensions

​
guardrails
object
Guardrails-specific options:
​
guardrails.config_id
string
The guardrails configuration ID to use.
​
guardrails.config_ids
array
List of configuration IDs to combine. Cannot be used with config_id.
​
guardrails.thread_id
string
The ID of an existing thread to continue (minimum 16 characters).
​
guardrails.context
object
Additional context data for the conversation.
{
  "user_name": "Alice",
  "user_id": "12345"
}
​
guardrails.options
GenerationOptions
Additional generation options:
  • rails: Which rails to enable ({"input": true, "output": true})
  • log: Logging options ({"activated_rails": true, "llm_calls": true})
  • output_vars: Variables to extract from context
​
guardrails.state
object
State object to continue the interaction. Must contain events or state key.

​
Response

​
id
string
Unique identifier for the chat completion.
​
object
string
Always “chat.completion”.
​
created
integer
Unix timestamp of when the completion was created.
​
model
string
The model used for the completion.
​
choices
array
Array of completion choices.
​
choices[].index
integer
The index of this choice.
​
choices[].message
object
The generated message.
​
choices[].message.role
string
Always “assistant”.
​
choices[].message.content
string
The content of the message.
​
choices[].message.tool_calls
array
Tool calls generated by the model (if any).
​
choices[].finish_reason
string
The reason the generation stopped: “stop”, “length”, or “content_filter”.
​
guardrails
object
Guardrails-specific output data:
​
guardrails.config_id
string
The configuration ID that was used.
​
guardrails.state
object
Updated state object for continuing the conversation.
​
guardrails.log
object
Generation log data (if requested):
  • activated_rails: List of rails that were activated
  • llm_calls: Details of LLM calls made
  • stats: Performance statistics
curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "guardrails": {
      "config_id": "my-config"
    }
  }'

​
Response Examples

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop",
      "logprobs": null
    }
  ],
  "guardrails": {
    "config_id": "my-config",
    "state": {
      "events": [...]
    },
    "log": {
      "stats": {
        "total_llm_calls": 2,
        "total_time": 1.5
      }
    }
  }
}

​
Error Responses

​
error
object
​
error.message
string
Human-readable error message.
​
error.type
string
Error type: “invalid_request_error”, “authentication_error”, “server_error”, etc.
​
error.code
string
Error code.
{
  "error": {
    "message": "No guardrails config_id provided and server has no default configuration",
    "type": "invalid_request_error",
    "code": "missing_config"
  }
}