Process Questions & Answers for Knowledge Base

Used to ingest structured Question and Answer (Q&A) pairs into the knowledge base. This is ideal for creating a knowledge base optimized for direct question answering.

API Endpoint

Property	Value
Request Method	POST
Request URL	https://api.seliseblocks.com/kb/qa

Request

Request Example

curl -X POST 'https://api.seliseblocks.com/kb/qa' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "project_key": "YOUR_PROJECT_KEY",
    "agent_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
    "question": "How do I reset my password?",
    "answer": "To reset your password, click on the Forgot Password link on the login page. Enter your email address, and you will receive a password reset link. Click the link in the email and follow the instructions to create a new password."
  }'

Request Headers

Field	Type	Required	Description
accept	string	Yes	Accepted response format. Use application/json
Content-Type	application/json	Yes	Data type, must be application/json.

Request Body

Request Body Schema

{
  "project_key": "string",
  "agent_id": "string",
  "question": "string",
  "answer": "string"
}

Request Body Parameters

Field	Type	Required	Description
project_key	string	Yes	The project key for your project.
agent_id	string	Yes	UUID of the AI agent to associate the Q&A pair with.
question	string	Yes	The question text to be indexed in the knowledge base.
answer	string	Yes	The answer text corresponding to the question.

tip

Q&A pairs are particularly effective for:

• FAQs and common user queries
• Standardized responses to specific questions
• Product documentation in Q&A format
• Training the agent to respond accurately to known questions

Response

Success Response (200 OK)

Returns an object containing the processing status.

{
  "is_success": true,
  "detail": "Q&A pair processed and added to knowledge base successfully",
  "error": {}
}

Response Fields

Field	Type	Description
is_success	boolean	Indicates whether the Q&A processing was successful.
detail	string	Success or failure message with additional context.
error	object	Error details if the operation failed (empty if successful).

note

The Q&A pair is indexed in a way that optimizes retrieval when users ask similar questions. The agent can use this structured information to provide accurate and consistent answers.

Error Response (422 Unprocessable Entity)

Returns validation error details when the request body is invalid.

{
  "detail": [
    {
      "loc": [
        "body",
        "question"
      ],
      "msg": "field required",
      "type": "value_error.missing"
    }
  ]
}

Error Response Fields

Field	Type	Description
detail	array	Array of validation error objects.
loc	array	Location of the error in the request (e.g., body field).
msg	string	Human-readable error message.
type	string	Error type identifier.

Error Codes

Status Code	Description	Response Type
200	Successful Response	Success
400	Bad Request - Invalid Q&A data or processing error	Bad Request
422	Validation Error - Invalid request parameters	Unprocessable Entity