Home
APIs
FAQ & Knowledge Base
FAQ Collections Management API

FAQ Collections Management API

Programmatically organize and syndicate Q&A collections for automated chatbots and self-serve help portals.

POST https://rsflowhub.com/api/v1/ai/faq-collections

1 credit per call
X-API-Key header
JSON in, JSON out

Try it in the playground API reference

POST /api/v1/ai/faq-collections

{
    "name": "Support FAQs",
    "faqs": [
        {
            "id": "faq_1",
            "question": "How can I change my password?",
            "answer": "Go to settings, click on security, then select change password."
        },
        {
            "id": "faq_2",
            "question": "What is your refund policy?",
            "answer": "We offer a 14-day refund window on all of our premium plans."
        }
    ]
}

200 OK response.json

{
    "result": {
        "message": "See the API reference for the full result schema."
    }
}

Definition

What is the FAQ Collections Management API?

FAQ Collections Management API is a REST API on RSFlowHub for web, mobile and AI agent applications. Send a JSON request to POST /api/v1/ai/faq-collections with your API key; RSFlowHub runs it on a tuned AI model, falls back to a backup provider if needed, and returns a structured JSON result, usually within 1 to 3 seconds.

Category: FAQ & Knowledge Base
Endpoint: POST /api/v1/ai/faq-collections
Authentication: X-API-Key header
Price: 1 credit per call
Rate limit: 10 to 120 requests / minute by plan
Typical response: 1 to 3 seconds
Format: JSON, UTF-8

Request parameters

Send these fields as a JSON body. An invalid or missing field returns a 422 error that names the field.

Field	Type	Required	Description
`name`	string	Required	The name of the FAQ collection (e.g., "Billing support FAQs").
`faqs`	array of objects	Required	List of FAQ items to save. Maximum 500 items per collection.
`faqs.*.question`	string	Required	The FAQ question text.
`faqs.*.answer`	string	Required	The FAQ answer text.
`faqs.*.id`	string	Optional	Optional custom identifier (e.g. "faq_1").

Code examples

Copy, replace rfh_your_api_key with your key and run. Prefer a client library? See the official SDKs.

request.sh

curl -X POST "https://rsflowhub.com/api/v1/ai/faq-collections" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: rfh_your_api_key" \
  -d '{"name":"Support FAQs","faqs":[{"id":"faq_1","question":"How can I change my password?","answer":"Go to settings, click on security, then select change password."},{"id":"faq_2","question":"What is your refund policy?","answer":"We offer a 14-day refund window on all of our premium plans."}]}'

client.php

<?php

$client = new \GuzzleHttp\Client();
$response = $client->post('https://rsflowhub.com/api/v1/ai/faq-collections', [
    'headers' => [
        'Content-Type' => 'application/json',
        'X-API-Key'    => 'rfh_your_api_key',
    ],
    'json' => array (
      'name' => 'Support FAQs',
      'faqs' => 
      array (
        0 => 
        array (
          'id' => 'faq_1',
          'question' => 'How can I change my password?',
          'answer' => 'Go to settings, click on security, then select change password.',
        ),
        1 => 
        array (
          'id' => 'faq_2',
          'question' => 'What is your refund policy?',
          'answer' => 'We offer a 14-day refund window on all of our premium plans.',
        ),
      ),
    ),
]);

echo $response->getBody();

client.js

const response = await fetch('https://rsflowhub.com/api/v1/ai/faq-collections', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-API-Key': 'rfh_your_api_key'
  },
  body: JSON.stringify({"name":"Support FAQs","faqs":[{"id":"faq_1","question":"How can I change my password?","answer":"Go to settings, click on security, then select change password."},{"id":"faq_2","question":"What is your refund policy?","answer":"We offer a 14-day refund window on all of our premium plans."}]})
});

const data = await response.json();
console.log(data);

main.py

import requests

url = "https://rsflowhub.com/api/v1/ai/faq-collections"
headers = {
    "Content-Type": "application/json",
    "X-API-Key": "rfh_your_api_key"
}
payload = {"name":"Support FAQs","faqs":[{"id":"faq_1","question":"How can I change my password?","answer":"Go to settings, click on security, then select change password."},{"id":"faq_2","question":"What is your refund policy?","answer":"We offer a 14-day refund window on all of our premium plans."}]}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

Response

Every RSFlowHub endpoint uses the same envelope, so one parser handles all of them. Failed calls are not charged.

response.json

{
    "success": true,
    "request_id": "req_3f9a2c7e-5b1d-4e8a-9c2f-7d6e1a0b4c8d",
    "data": {
        "result": {
            "message": "See the API reference for the full result schema."
        }
    },
    "meta": {
        "version": "v1",
        "timestamp": "2026-10-05T09:30:00Z"
    }
}

error.json

{
    "success": false,
    "request_id": "req_8c1d4e2a-7f3b-4a9c",
    "error": {
        "code": "VALIDATION_ERROR",
        "message": "The given data was invalid.",
        "details": {
            "name": [
                "This field is required."
            ]
        }
    },
    "meta": {
        "version": "v1",
        "timestamp": "2026-10-05T09:30:00Z"
    }
}

Envelope fields
Field	Type	Meaning
`success`	boolean	true when the call worked, false on any error.
`request_id`	string	Unique id for this call. Quote it when you contact support.
`data.result`	object	The result of this endpoint (see the example).
`error`	object	Only on failure: code, message and details per field.
`meta`	object	API version and server timestamp.

All error codes: Errors reference

Features

Categorized Knowledge Clustering

Group hundreds of FAQs into logical collections (Billing, Technical, Shipping, Account) with automatic slug generation.

Instant Vector Synchronization

Updated FAQs are automatically re-indexed into pgvector for fast semantic similarity search in chatbots.

Multi-Tenant Isolation

Isolate FAQ collections per organization or team with scoped access tokens and atomic update validation.

Search-Engine Friendly Schema Exports

Export collections directly as Google-compliant FAQPage JSON-LD schemas for automated SEO publication.

Use cases

How teams use the FAQ Collections Management API in production.

SaaS Product

Dynamic In-App Help Centers

Sync help center articles from internal CMS into in-app contextual help widgets automatically.

Input: Collection: "Billing & Invoicing", 14 Q&A items including refund and VAT rules.
Output: {"collection_id": "col_billing_01", "indexed_items": 14, "vector_status": "ready"}

Answers repetitive tier-1 questions directly inside your app.

Chatbot Automation

AI Customer Support Bot Grounding

Ground automated support chatbots in curated, verified company answers to eliminate hallucinations.

Input: Add Q: "What is your return policy?" A: "30 days with receipt and original packaging."
Output: {"status": "success", "item_id": "faq_ret_30d", "vector_dims": 768}

Returns your approved answer wording for matched questions.

SEO & Growth

Programmatic SEO FAQ Injection

Programmatically generate and embed valid FAQPage schemas on marketing landing pages.

Input: Export collection "enterprise_pricing" as JSON-LD schema.
Output: {"@context": "https://schema.org", "@type": "FAQPage", "mainEntity": [...]}

Supplies FAQ content you can publish with FAQPage structured data.

FAQ Collections Management API vs building it yourself

The same job done three ways.

Topic	RSFlowHub API	Raw LLM prompts	Rules / regex
Output	Validated JSON fields	Free text you have to parse	Fixed patterns only
Setup	One POST request, no prompts	Write and maintain prompts and parsing	Write and maintain rule lists
Provider outage	Automatic fallback to a backup model	You build retries and a second vendor	Not applicable
Pricing	1 credit per call, failed calls free	Per token, per vendor	Your own servers and upkeep
Understands context	Yes, AI model	Yes, AI model	No, keywords only

Frequently asked questions

How are FAQs converted into vector embeddings?

When you sync a collection, RSFlowHub generates 768-dimensional text embeddings stored in Supabase pgvector for fast cosine similarity search.

Can I export collections as Google FAQPage schema?

Yes. The API returns pre-formatted Schema.org FAQPage JSON-LD objects ready for insertion into HTML headers.

How many items can a single FAQ collection contain?

Each collection supports up to 1,000 distinct Q&A pairs with automatic pagination and search filtering.

Can I update a single FAQ without re-uploading the entire collection?

Yes. Granular PUT/PATCH endpoints allow atomic updates to individual questions with immediate vector re-indexing.

How many credits does the FAQ Collections API consume?

Standard management calls consume 1 base credit per operation.

Start using the FAQ Collections Management API

Free plan with 100 credits/month + 1,000 bonus credits when you sign in before 23 Nov. Test it in the playground first, no code needed.

Get a free API key Try it now