<POST> Chat API

1min

POST
Request
Path Params
app_name
required
String
Choose the endpoint for inference. option app1, app2, app3. 
Body Parameters
prompt
required
String
Enter your prompt
Curl
Node.js
JS
Python
Ruby
import requests
import json

url = "##############/{app_name}"

payload = json.dumps({
   "prompt": "String"
})
headers = {
   'Accept': 'application/json',
   'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

import requests
import json

url = "##############/{app_name}"

payload = json.dumps({
   "prompt": "String"
})
headers = {
   'Accept': 'application/json',
   'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)
Responses
200
400
500
message = {
 
        "response": "",
        "policy_violated": "",
        "policy_type": "",
        "status": 500,
        "status_message": "Completed",
        "ip_op_blocked": "",
        "event_id": "",
        "mode": "",
        "input_scanning_latency/sec": 0,
        "output_scanning_latency/sec": 0,
        "target_llm_response_latency/sec": 0,
        "input_token": 0,
        "output_token": 0
    }
message = {
 
        "response": "",
        "policy_violated": "",
        "policy_type": "",
        "status": 500,
        "status_message": "Completed",
        "ip_op_blocked": "",
        "event_id": "",
        "mode": "",
        "input_scanning_latency/sec": 0,
        "output_scanning_latency/sec": 0,
        "target_llm_response_latency/sec": 0,
        "input_token": 0,
        "output_token": 0
    }
﻿
Note: Replace '##########' with your id address of guardian sandbox
﻿

Updated 19 Dec 2024

Did this page help you?

<POST> Supply Chain Attacks

MLOps