<POST> Chat API

3min

The Chat API processes user prompts according to the specified execution mode and returns a detailed response, including application metadata, guardrail configurations, token usage, and policy compliance checks.
POST
Request
Response
Path Params
app_name
required
String
Specifies the application endpoint for inference. Possible values: app1, app2, app3.
Body Parameters
prompt
required
String
The user's input or query to be processed by the API.
Curl
Python
curl --location --globoff '{guardian_url}/chat/{app_name}' \
--header 'Accept: application/json' \
--header 'Content-Type: application/json' \
--data '{"prompt":"String"}'
curl --location --globoff '{guardian_url}/chat/{app_name}' \
--header 'Accept: application/json' \
--header 'Content-Type: application/json' \
--data '{"prompt":"String"}'
Responses
200
401
429
500
{
      "api_status_code": 200,
      "api_status_message": "Successful",
      "app_prompt": "user prompt",
      "app_prompt_context": "",
      "input": {
        "guardrails_metadata": {
          "configuration": {input configuration dict},
          "number_of_active_guardrails": number of input active guardrails,
          "number_of_inactive_guardrails": number of input inactive guardrails
        },
        "num_tokens": number of input tokens,
        "violated_policies": "comma separated violated policies",
        "latency/sec": 0
      },
      "llm_response": "Generated LLM response based on the user prompt.",
      "metadata": {
        "api_version": "v1.5",
        "app_name": "application name",
        "event_id": "unique id for the user prompt",
        "execution_mode": "Block",
        "timestamp": "timestamp user has been created"
      },
      "output": {
        "guardrails_metadata": {
          "configuration": {output configuration dict},
          "number_of_active_guardrails": number of output active guardrails,
          "number_of_inactive_guardrails": number of output inactive guardrails
        },
        "num_tokens": number of output tokens,
        "violated_policies": "comma separated violated policies",
        "latency/sec": 0
      },
      "redacted_prompt": "",
      "siem": {
        "active_siem": [list of active siems],
        "inactive_siem": [list of inactive siems],
        "status_code": 200,
        "status_message": "Successful"
      },
      "violation_exist": false,
      "violation_on": "input or output or empty string"
}
{
      "api_status_code": 200,
      "api_status_message": "Successful",
      "app_prompt": "user prompt",
      "app_prompt_context": "",
      "input": {
        "guardrails_metadata": {
          "configuration": {input configuration dict},
          "number_of_active_guardrails": number of input active guardrails,
          "number_of_inactive_guardrails": number of input inactive guardrails
        },
        "num_tokens": number of input tokens,
        "violated_policies": "comma separated violated policies",
        "latency/sec": 0
      },
      "llm_response": "Generated LLM response based on the user prompt.",
      "metadata": {
        "api_version": "v1.5",
        "app_name": "application name",
        "event_id": "unique id for the user prompt",
        "execution_mode": "Block",
        "timestamp": "timestamp user has been created"
      },
      "output": {
        "guardrails_metadata": {
          "configuration": {output configuration dict},
          "number_of_active_guardrails": number of output active guardrails,
          "number_of_inactive_guardrails": number of output inactive guardrails
        },
        "num_tokens": number of output tokens,
        "violated_policies": "comma separated violated policies",
        "latency/sec": 0
      },
      "redacted_prompt": "",
      "siem": {
        "active_siem": [list of active siems],
        "inactive_siem": [list of inactive siems],
        "status_code": 200,
        "status_message": "Successful"
      },
      "violation_exist": false,
      "violation_on": "input or output or empty string"
}
﻿
Response Field Definitions:
The table below provides a comprehensive breakdown of all the fields included in the API response. It describes each field's purpose, type, and possible values to help you understand how to interpret the API's output effectively.
Field  
Type 
Description 
api_status_code
integer 
HTTP status code of the API response. Possible values: 200 (Success), 401 (Access Denied), 412 (Precondition Failed), 500 (Internal Server Error).
api_status_message 
string 
Message indicating the status of the API call (e.g., "Successful", "LLM Connectivity Issue", "Internal Server Error", "Access Denied").
﻿
app_prompt 
string 
The user's application-specific prompt.
app_prompt_context
string 
Context provided alongside the user's prompt. This field is currently an empty string.
input 
dictionary
Details about the input, including:
﻿
﻿
guardrails_metadata: Input configuration, number of active and inactive guardrails.
﻿
﻿
num_tokens: Number of tokens processed in the input.
﻿
﻿
violated_policies: Policies violated, if any, or an empty string.
﻿
﻿
latency/sec: given user's prompt processing time in sec
output 
dictionary
Details about the output, including:
﻿
﻿
guardrails_metadata: output configuration, number of active and inactive guardrails.
﻿
﻿
num_tokens: Number of tokens processed in the input.
﻿
﻿
violated_policies: Policies violated, if any, or an empty string.
﻿
﻿
latency/sec: llm response processing time in sec
metadata 
dictionary
Metadata about the API call, including:
﻿
﻿
api_version: API version (e.g., v1.5).
﻿
﻿
app_name: Application name 
﻿
﻿
event_id: Unique identifier for the API call.
﻿
﻿
execution_mode: Mode of operation (e.g., Block).
﻿
﻿
timestamp: Time of the API call in GMT.
redacted_prompt 
string 
Sanitized or redacted version of the user prompt if PII Redaction is enabled, or an empty string otherwise.
siem 
dictionary
Security Information and Event Management (SIEM) details, including:
﻿
﻿
active_siem: List of active SIEM systems.
﻿
﻿
inactive_siem: List of inactive SIEM systems.
﻿
﻿
status_code: Status code for SIEM processing. Possible values: 200 (Success) , 500 (Internal Server Error),  null or empty is not needed to send message to siem
﻿
﻿
status_message: Status message for SIEM processing.(e.g., "Successful", "Internal Server Error", empty string ).
violation_exist
boolean 
Indicates if any policy violations occurred (true or false).
violation_on
string 
Indicates whether the policy violation occurred due to the user's prompt (input) or the LLM response(output).
Connecting to the Chat API:
This below Gist provides a detailed example of how to connect to the Chat API, including how to structure the request, handle the response, and customize the API call based on your specific needs.
To get started with integrating the Chat API, you can refer to the following GitHub Gist for a step-by-step guide and example code:
﻿
﻿

Field	Type	Description
api_status_code	integer	HTTP status code of the API response. Possible values: 200 (Success), 401 (Access Denied), 412 (Precondition Failed), 500 (Internal Server Error).
api_status_message	string	Message indicating the status of the API call (e.g., "Successful", "LLM Connectivity Issue", "Internal Server Error", "Access Denied").
app_prompt	string	The user's application-specific prompt.
app_prompt_context	string	Context provided alongside the user's prompt. This field is currently an empty string.
input	dictionary	Details about the input, including:
		guardrails_metadata: Input configuration, number of active and inactive guardrails.
		num_tokens: Number of tokens processed in the input.
		violated_policies: Policies violated, if any, or an empty string.
		latency/sec: given user's prompt processing time in sec
output	dictionary	Details about the output, including:
		guardrails_metadata: output configuration, number of active and inactive guardrails.
		num_tokens: Number of tokens processed in the input.
		violated_policies: Policies violated, if any, or an empty string.
		latency/sec: llm response processing time in sec
metadata	dictionary	Metadata about the API call, including:
		api_version: API version (e.g., v1.5).
		app_name: Application name
		event_id: Unique identifier for the API call.
		execution_mode: Mode of operation (e.g., Block).
		timestamp: Time of the API call in GMT.
redacted_prompt	string	Sanitized or redacted version of the user prompt if PII Redaction is enabled, or an empty string otherwise.
siem	dictionary	Security Information and Event Management (SIEM) details, including:
		active_siem: List of active SIEM systems.
		inactive_siem: List of inactive SIEM systems.
		status_code: Status code for SIEM processing. Possible values: 200 (Success) , 500 (Internal Server Error), null or empty is not needed to send message to siem
		status_message: Status message for SIEM processing.(e.g., "Successful", "Internal Server Error", empty string ).
violation_exist	boolean	Indicates if any policy violations occurred (true or false).
violation_on	string	Indicates whether the policy violation occurred due to the user's prompt (input) or the LLM response(output).

Updated 29 Jan 2025

Did this page help you?

<POST> configureApp API

MLOps