FAQ Generator

Overview

The FAQ Generator endpoint is a knowledge agent that automatically generates frequently asked questions (FAQs) from documents using AI-powered question extraction and answer generation. You can specify focus areas and the number of questions to generate, and the system will create relevant Q&A pairs with source and relevance rankings.

Use this endpoint to:

Automatically generate FAQs from documents, manuals, and knowledge bases
Create Q&A pairs with specific focus areas (e.g., pricing, legal, technical)
Build comprehensive FAQ sections for websites and documentation
Extract key information as question-answer pairs
Generate training data for chatbots and support systems

Endpoint Details

Method: POST
Endpoint: /api/agent/faq_generator
Base URL: https://api.k-v.ai
Authentication: Access Key (Required)

Request Specification

Headers

Header	Type	Required	Description
`access-key`	string	Yes	Your unique access-key generated from the platform UI
`Content-Type`	string	Yes	Must be `application/json`

Request Body

{
    "doc_process_ids": [
        "264dfa262b748d15ccbeaada89430c68"
    ],
    "focus_areas": ["fee"],
    "question_count": 2,
    "model_data": {
        "model_name": "gpt-5.1",
        "api_key": ""
    }
}

Body Fields

Field	Type	Required	Description
`doc_process_ids`	array	Yes	Array of document IDs to generate FAQs from (obtained from Upload or List Documents APIs)
`focus_areas`	array	No	List of focus areas to generate questions about (e.g., "pricing", "legal", "technical"). Leave empty for general FAQs
`question_count`	integer	Yes	Number of questions to generate (minimum: 1, maximum: 10)
`model_data`	object	Yes	AI model configuration
`model_data.model_name`	string	Yes	AI model to use for FAQ generation (see supported models below)
`model_data.api_key`	string	No	Your own LLM API key (leave empty to use platform's default keys)

Supported AI Models

Model Name	Provider
`gpt-5.1`	OpenAI
`gpt-5-mini`	OpenAI
`claude-sonnet-4-5-20250929`	Anthropic
`gemini/gemini-2.5-flash-lite`	Google
`gemini/gemini-2.5-pro`	Google
`gemini/gemini-3-pro-preview`	Google
`mistral/mistral-small-latest`	Mistral AI
`mistral/mistral-medium-latest`	Mistral AI
`llama3.1-70b`	Meta

Question Count Limits

Minimum: 1 question
Maximum: 10 questions per request

Using Your Own LLM API Keys

Platform Keys (Default):

{
    "model_data": {
        "model_name": "gpt-5.1",
        "api_key": ""
    }
}

Your Own Keys:

{
    "model_data": {
        "model_name": "gpt-5.1",
        "api_key": "sk-your-openai-api-key-here"
    }
}

Response Specification

Success Response (200 OK)

{
    "data": {
        "questions_answers": [
            {
                "question": "What is the prevailing party entitled to regarding attorneys' fees in any action relating to the Agreement?",
                "answer": "In any action relating to the Agreement, the prevailing party is entitled to collect reasonable attorneys' fees and costs from the non-prevailing party in addition to any other recovery.",
                "focus_area": "fee",
                "page_numbers": [
                    "1"
                ],
                "rank": 1,
                "source": "Settlement Agreement (1).pdf",
                "doc_hash": [
                    "264dfa262b748d15ccbeaada89430c68"
                ]
            },
            {
                "question": "Who is responsible for paying attorneys' fees and costs incurred before the execution of the Settlement Agreement?",
                "answer": "Each party is responsible for bearing its own attorneys' fees and costs arising from the actions of its own counsel incurred prior to the date of execution of the Agreement.",
                "focus_area": "fee",
                "page_numbers": [
                    "1"
                ],
                "rank": 2,
                "source": "Settlement Agreement (1).pdf",
                "doc_hash": [
                    "264dfa262b748d15ccbeaada89430c68"
                ]
            }
        ],
        "is_sufficient": true,
        "tokens": {
            "input": 1501,
            "output": 261,
            "total": 1762
        }
    },
    "message": "FAQs extracted successfully"
}

Response Fields

Field	Type	Description
`data`	object	Response data object
`data.questions_answers`	array	Array of generated Q&A pairs
`data.questions_answers[].question`	string	Generated question
`data.questions_answers[].answer`	string	AI-generated answer based on document content
`data.questions_answers[].focus_area`	string	Focus area this Q&A relates to (if specified in request)
`data.questions_answers[].page_numbers`	array	Page numbers where the answer information was found
`data.questions_answers[].rank`	integer	Relevance ranking (1 = most relevant) based on cosine similarity and keyword matching
`data.questions_answers[].source`	string	Original filename of the source document
`data.questions_answers[].doc_hash`	array	Document process ID(s)
`data.is_sufficient`	boolean	`true` if the number of generated questions matches `question_count`, `false` if fewer questions were generated
`data.tokens`	object	Token usage for this request
`data.tokens.input`	integer	Input tokens consumed
`data.tokens.output`	integer	Output tokens generated
`data.tokens.total`	integer	Total tokens used
`message`	string	Human-readable response message

Error Responses

401 Unauthorized

{
    "data": {},
    "message": "Invalid or missing access key"
}

Cause: Missing or invalid access-key header

422 Unprocessable Entity - Invalid Model Name

{
    "detail": [
        {
            "type": "literal_error",
            "loc": [
                "body",
                "model_data",
                "model_name"
            ],
            "msg": "Input should be 'gpt-5-chat-latest', 'gpt-5.1', 'gpt-5-mini', 'claude-sonnet-4-5-20250929', 'gemini/gemini-2.5-flash-lite', 'mistral/mistral-small-latest', 'mistral/mistral-medium-latest', 'gemini/gemini-2.5-pro', 'gemini/gemini-3-pro-preview' or 'llama3.1-70b'",
            "input": "",
            "ctx": {
                "expected": "'gpt-5-chat-latest', 'gpt-5.1', 'gpt-5-mini', 'claude-sonnet-4-5-20250929', 'gemini/gemini-2.5-flash-lite', 'mistral/mistral-small-latest', 'mistral/mistral-medium-latest', 'gemini/gemini-2.5-pro', 'gemini/gemini-3-pro-preview' or 'llama3.1-70b'"
            }
        }
    ]
}

Cause: Invalid or unsupported model_name in model_data. See supported models list above.

400 Bad Request - Invalid Document IDs

{
    "data": {},
    "message": "Invalid docs selected"
}

Causes: Missing or invalid doc_process_ids.

500 Internal Server Error - Invalid LLM API Key

{
    "data": {},
    "message": "litellm.AuthenticationError: AuthenticationError: OpenAIException - Incorrect API key provided: tyrdfuih**uhf7. You can find your API key at https://platform.openai.com/account/api-keys."
}

Cause: The api_key provided in model_data is invalid or expired. Verify your LLM provider API key.

500 Internal Server Error - General Error

{
    "data": {},
    "message": "Something went wrong"
}

Causes:

LLM service temporarily unavailable
Server-side processing error

422 Unprocessable Entity - Invalid Question Count

{
    "detail": [
        {
            "type": "json_invalid",
            "loc": [
                "body",
                121
            ],
            "msg": "JSON decode error",
            "input": {},
            "ctx": {
                "error": "Expecting value"
            }
        }
    ]
}

Causes:

Missing question_count field
Invalid question_count value (must be 1-10)
Malformed JSON request body

Code Snippets

cURL

curl --location 'https://api.k-v.ai/api/agent/faq_generator' \
--header 'access-key: YOUR_ACCESS_KEY' \
--header 'Content-Type: application/json' \
--data '{
    "doc_process_ids": [
        "264dfa262b748d15ccbeaada89430c68"
    ],
    "focus_areas": ["fee"],
    "question_count": 2,
    "model_data": {
        "model_name": "gpt-5.1",
        "api_key": ""
    }
}'

Python

import requests
import json

url = "https://api.k-v.ai/api/agent/faq_generator"

payload = json.dumps({
    "doc_process_ids": [
        "264dfa262b748d15ccbeaada89430c68"
    ],
    "focus_areas": [
        "fee"
    ],
    "question_count": 2,
    "model_data": {
        "model_name": "gpt-5.1",
        "api_key": ""
    }
})

headers = {
    'access-key': 'YOUR_ACCESS_KEY',
    'Content-Type': 'application/json'
}

response = requests.post(url, headers=headers, data=payload)

print(response.text)

JavaScript (Node.js)

const axios = require('axios');

let data = JSON.stringify({
    "doc_process_ids": [
        "264dfa262b748d15ccbeaada89430c68"
    ],
    "focus_areas": [
        "fee"
    ],
    "question_count": 2,
    "model_data": {
        "model_name": "gpt-5.1",
        "api_key": ""
    }
});

let config = {
    method: 'post',
    maxBodyLength: Infinity,
    url: 'https://api.k-v.ai/api/agent/faq_generator',
    headers: { 
        'access-key': 'YOUR_ACCESS_KEY',
        'Content-Type': 'application/json'
    },
    data: data
};

axios.request(config)
.then((response) => {
    console.log(JSON.stringify(response.data, null, 2));
})
.catch((error) => {
    console.log(error);
});

Important Notes

Document Processing: Only generate FAQs from documents with status: "processed"
Question Limits: Maximum 10 questions per request
Focus Areas: More specific focus areas yield better, more targeted questions
Rankings: Lower rank numbers indicate higher relevance
Sufficiency: Check is_sufficient to know if all requested questions were generated

Next Steps

After generating FAQs:

Review Quality: Verify generated Q&A accuracy against source documents
Build Knowledge Base: Integrate FAQs into documentation or support systems
Iterate: Refine focus areas and question counts based on results

Need Help? Contact support at support@k-v.ai

FAQ Generator

On this page