Search Intelligence — LLM Provider
Budgeted LLM proposals for Magento SEO
- Dry Run First Preview without API spend
- Packet Budgeting Shrink, estimate, hash
- Strict JSON Validated SEO proposals
- Advisory Only Approve before any writes
Budgeted AI SEO proposals
Uncontrolled LLM calls can spend budget and write risky copy. Search Intelligence LLM Provider connects OpenAI-compatible models with packet budgeting, dry-run previews, and advisory-only JSON proposals until you approve.
- OpenAI-compatible provider for Core AI interface
- Dry-run packet preview without outbound API calls
- Daily call budget tracking on the connector screen
- Strict JSON validation before proposals enter Core
Built for your store
Built for Magento 2.4.4+ Open Source and Adobe Commerce. Requires Search Intelligence Core and AI Core; proposals stay advisory until change-set apply.
- Requires Search Intelligence Core and AI Core
- Configure provider, model, and budget in AI Core
- Suite connector screen under LLM Provider
- Admin-first with no storefront theme dependency
AI-Powered SEO Metadata Drafting for Magento
The LLM Provider is the bridge between Search Intelligence Core and any OpenAI-compatible language model. It builds deterministic context packets from your catalog and advisory queue, sends them to the LLM (GPT-4o mini by default), and returns structured JSON proposals for meta titles, meta descriptions, and other SEO fields.
Everything runs with dry run enabled by default — no live API calls, no catalog writes, no surprises. You see the packet structure, token estimate, and proposal format before committing a single API credit.
- OpenAI-compatible endpoint with configurable model slug
- Deterministic packet builder: site, bucket, entity, and action types
- Daily call budget with budget-remaining counter
- Strict JSON proposal validator (field, proposed_value, reason, confidence, evidence_ids)
- Dry-run preview page — see packet structure without making API calls
- Advisory only by default: proposals require admin approval before any writes
Safe Token Budget Management
Every outbound request is constrained by a configurable daily call budget. The connector tracks calls-today and budget-remaining in real time, preventing runaway API spend during aggressive advisory cycles or automated optimization runs.
The packet shrinker trims context deterministically when token estimates exceed the configured budget — ensuring the LLM always receives a well-formed, in-budget packet regardless of catalog size.
- Daily call budget enforced per store configuration
- Deterministic packet shrinker for oversized contexts
- Token estimate shown before any live call
- Packet hash for deduplication across advisory runs
- Last call timestamp with UTC display
Requirements
- Magento 2.4.4+ · PHP 8.1+
toweringmedia/module-search-intelligence-coretoweringmedia/module-ai-core2.1+- OpenAI API key (or compatible endpoint)
- Composer:
toweringmedia/module-search-intelligence-llm
Key Features
OpenAI-compatible provider for Search Intelligence Core with packet budgeting, dry-run previews, and advisory-only proposal validation.
- OpenAI-compatible provider Implements Core’s AiProviderInterface with a configurable model slug.
- Four packet types Builds site, bucket, entity, and action packets for SEO context.
- Daily call budget Tracks calls today and budget remaining on the connector screen.
- Deterministic shrinker Trims oversized context so packets stay within token limits.
- Dry-run packet preview Admin preview of packet structure and token estimate without HTTP calls.
- Proposal JSON validator Requires field, proposed value, reason, confidence, and evidence ids.
- SEO copy and AEO APIs Generators for meta copy and AEO content used by the suite.
- Suite connector screen Status and dry run under Intelligence SEO Suite → LLM Provider.
Frequently Asked Questions
Where do I configure the LLM Provider?
Go to Stores → Configuration → Towering Media → AI Core Settings. Provider, model, dry run, live API calls, and daily budget live in the AI Core groups. This module adds the Search Intelligence LLM Connector group (SEO LLM Connector Enabled) in that same section. The operational screen is Intelligence SEO Suite → Connectors → LLM Provider.
Does the LLM Provider write meta titles to the catalog?
No. Proposals are advisory only. They enter Search Intelligence Core’s approval workflow; nothing reaches the storefront until you approve and apply a change set in Core.
What happens when dry run is enabled?
Dry run is the default in AI Core. The connector builds and budgets packets locally, shows token estimates and packet structure on the dry-run preview page, and does not make outbound LLM HTTP calls until dry run is off, live API calls are enabled, and a provider key is saved.
Do you offer support?
Yes. Email support@toweringmedia.com or call (773) 466-2454. Updates and support continue while your subscription is active.
Can I try a demo?
Yes. Use the View Demo button on this page. For a guided walkthrough, email support@toweringmedia.com.
What happens when I don’t renew?
Uncheck auto-renew at purchase, or cancel later. You keep access until the end of the paid period. After that, updates and support stop.
Compatible with your Magento 2 store
Built for Magento 2.4.4+ (Open Source and Adobe Commerce) with PHP 8.1–8.4. Requires toweringmedia/module-search-intelligence-core and toweringmedia/module-ai-core 2.1+. Install via Composer as toweringmedia/module-search-intelligence-llm. Admin connector with no storefront theme dependency.
-
Magento 2.4
Open Source & Adobe Commerce
Hyvä compatibleBuilt for modern storefronts
Updates & supportKeep your store running smoothly