Knowledge Bases & Search API Specification & Integration Reference

POST Knowledge Bases & Vector Search API

/api/v1/knowledge-bases

Manage AI knowledge bases, index FAQs, plain text, and PDF documents, and perform grounded vector search & Q&A.

Base Billing 1 Credit
Target Latency < 150ms (p50)
Client Timeout 5.0s (recommended)
SLA Guarantee 99.9% Uptime
JSON Contract Deterministic v1

Architecture Role & AI Definition

Knowledge Bases & Vector Search API provides low-latency, deterministic REST execution for production engineering workflows. It processes structured payloads with strict schema validation, returns uniform JSON envelopes, and is secured via SHA-256 API key authentication with atomic credit pre-authorization locks.

Production Reliability Guidelines

1. Strict Timeout Windows

Configure a hard client timeout of 5 to 8 seconds. If network latency spikes, cancel connection to avoid holding open sockets in worker pools.

2. Exponential Backoff with Jitter

Upon receiving 429 Rate Limit or transient 5xx, pause with exponential backoff:
wait = min(max_backoff, base * 2^attempt + jitter).

3. Atomic Pre-Auth Locks

RSFlowHub acquires an atomic lock verifying base credits before model invocation. If validation fails, zero credits are deducted.

Request Body Parameters

Field Type Required Description
name string Required Name of the Knowledge Base (e.g. "Support KB")
description string Optional Optional description of the knowledge base content.
status string Optional Status: active or inactive. Default is active.
Management Operations are Free

Creating, listing, updating, and deleting Knowledge Bases, Items, and Documents are 0 AI credits. Credits are only charged when performing embedding generation, document processing, vector search, or AI question answering.


Integration Journey

  1. Create Knowledge Base: POST /api/v1/knowledge-bases
  2. Add Knowledge Items / FAQs: POST /api/v1/knowledge-bases/{id}/items
  3. Upload Documents (PDF / TXT): POST /api/v1/knowledge-bases/{id}/documents
  4. Perform Vector Search: POST /api/v1/knowledge-bases/{id}/search
  5. Perform Grounded Q&A: POST /api/v1/knowledge-bases/{id}/ask

Example Knowledge Ask Request

JSON Request
{
  "question": "What is the refund policy for annual subscriptions?",
  "top_k": 3,
  "min_confidence": 0.3
}
curl-trigger.sh cURL
curl -X POST https://rsflowhub.com/api/v1/knowledge-bases/1/ask \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "question": "What is the refund policy for annual subscriptions?"
  }'

Example Response

response.json JSON Response
200 OK 118ms
{
  "success": true,
  "data": {
    "answer": "Annual subscriptions are eligible for a full refund within 14 days of purchase.",
    "sources": [
      {
        "id": "12",
        "source_type": "faq",
        "title": "Refund Policy",
        "confidence": 0.94
      }
    ],
    "usage": {
      "credits_used": 3,
      "credits_remaining": 997
    }
  }
}

Common Failure Modes & Troubleshooting Matrix

HTTP Code Error Code Root Cause Recommended Remediation
400 bad_request Malformed JSON syntax or missing required top-level parameters. Validate JSON payload with Content-Type: application/json and ensure all required fields are present.
401 unauthorized Missing, revoked, or incorrectly formatted x-api-key header. Verify API key exists in Dashboard → API Keys and pass in x-api-key or Authorization: Bearer.
402 insufficient_credits Account credit balance is lower than the base required credits (1 credits). Top up credits in billing settings or enable auto-recharge to prevent pipeline interruption.
422 validation_error Input failed parameter constraints (e.g., character length exceeded or invalid array types). Review parameters table above and adjust payload length, types, or structure accordingly.
429 rate_limit_exceeded Concurrency limit (60 requests/minute default) reached for this endpoint key. Back off and retry using the timestamp in Retry-After response header, or batch requests.

Technical Q&A (FAQ)

We recommend setting a client timeout of 5 to 8 seconds. While average latency is under 150ms, large input payloads or complex reasoning models may require additional processing time.

RSFlowHub uses an atomic pre-flight check. Before processing, the gateway validates that your wallet has at least 1 base credits. If the request fails validation (422) or is malformed (400), no credits are charged.

When a 429 is received, your application should respect the 'Retry-After' header and use an exponential backoff retry policy with randomized jitter to prevent thundering herd problems.

Every successful response returns { "success": true, "data": { ... }, "meta": { "credits_used": int, "credits_remaining": int } }.

Ready to build?

Create your free account and make your first API call in minutes.