Chat API

Our Chat API allows a user to have a conversation with your AI agent via a simple API call.

The messages array should contain the conversation between the user and the AI agent. You can send the entire conversation within the API request.

Each message object has a role (user or assistant) and content.

In the example below you can see a short conversation between a user and an AI agent.

The message from the user has the role: user and all replies from the My AskAI have the role: assistant.

Chat with AskAI

post

Body

application/json

idstringRequired

AskAI ID

api_keystringRequired

AskAI API Key

Responses

200

Successful response

application/json

post

/ask-ai-chat

HTTPcURLJavaScriptPython

POST /api/1.1/wf/ask-ai-chat HTTP/1.1
Host: myaskai.com
Content-Type: application/json
Accept: */*
Content-Length: 76

{
  "id": "text",
  "api_key": "text",
  "messages": [
    {
      "role": "text",
      "content": "text"
    }
  ]
}

200

Successful response

{
  "answer": "text",
  "references": [
    {
      "content": "text",
      "link": "https://example.com",
      "score": 1,
      "title": "text"
    }
  ]
}

If your AI agent doesn't know the answer, the API will also return an additional field to confirm an answer wasn't found as well as 3 suggested questions the user can retry (these have a very high likelihood of being answered correctly):

"unknown_answer": "yes",

"suggestedQuestions": ["Example question", ...]

The query field has a 750 character limit. If this is exceeded, you will see an error: {"error":"This question is too long. Please ensure questions are less than 750 characters."}

If human handover guidance is triggered the API response will include: "human_handover": true