Social Media → Knowledge Graph

Open-source pipeline that crawls Instagram, YouTube, TikTok, X and transforms unstructured social data into queryable Knowledge Graphs with LLM-powered entity extraction.

Crawl Transform Filter Extract (LLM) Knowledge Graph RAG Chatbot
Quickstart

Up and Running in 5 Minutes

Docker or local install. Only one API key needed to start.

1

Clone & Configure

Get the code and add your OpenAI API key.

git clone https://github.com/Intellirim/ontix-universal.git
cd ontix-universal
cp .env.example .env
# Edit .env — minimum: OPENAI_API_KEY
2

Start with Docker (recommended)

One command spins up Neo4j + Redis + the app. No local installs needed.

docker-compose up -d
✓ Neo4j running on :7474
✓ Redis running on :6379
✓ ONTIX API running on :8000
✓ Web UI running on :3000

Open http://localhost:3000 for the full dashboard — or use the API directly.

3

Crawl or Upload Data

Crawl a social media account, or upload a CSV file you already have.

# Option A: Crawl Instagram (needs APIFY_TOKEN in .env)
curl -X POST http://localhost:8000/api/v1/pipeline/run \
  -H "Content-Type: application/json" \
  -d '{"brand_id":"demo","platform":"instagram",
       "target_type":"accounts","targets":["nike"],"max_items":20}'

# Option B: Upload a CSV (no Apify needed)
curl -X POST http://localhost:8000/api/v1/pipeline/upload \
  -F "file=@reviews.csv" -F "brand_id=demo"
{"job_id":"a1b2c3","status":"pending","rows_detected":150}
4

Ask Questions

Your Knowledge Graph is built. Now ask anything about your data.

curl -X POST http://localhost:8000/api/v1/chat \
  -H "Content-Type: application/json" \
  -d '{"brand_id":"demo",
       "message":"What are the most discussed topics?"}'
{"message":"Based on your data, the top 3 topics are..."}
Prerequisites: Docker + OpenAI API key. That's it.
For SNS crawling, also add an Apify token (free tier available).
How It Works

From Raw Data to Intelligence

The generic pipeline works out of the box. Industry Packs unlock domain-specific intelligence.

1. Crawl Any Platform

Instagram, YouTube, TikTok, X — or upload CSV/JSON from any source. 60+ column names auto-detected.

2. Extract Entities with LLM

GPT-5-mini reads every post and extracts structured entities and relationships. Generic prompt included free.

3. Build Knowledge Graph

Entities and relationships are stored in Neo4j. Query with Cypher, visualize connections, find patterns.

4. Ask Questions (RAG)

Built-in RAG chatbot answers questions about your data with retrieval-augmented generation and 4-layer quality filters.

5. Domain Intelligence

With Industry Packs: Extract domain-specific entities (ingredients, programs, IPs) instead of generic keywords.

6. Production Queries

With Industry Packs: 10-12 ready-to-use Cypher queries for competitive analysis, ROI tracking, and trend detection.

Industry Packs

Domain-Optimized Intelligence

Each pack includes extraction prompts, brand configs, and production-ready Cypher queries tailored for your industry.

💎

Beauty & Skincare

Ingredient analysis, routine tracking, and creator influence measurement for cosmetics and skincare brands.

Product Ingredient Skin_Concern Routine_Step Creator
$79
one-time, lifetime updates
Buy Pack
🍽️

Food & Beverage

Menu intelligence, location performance, and creator-driven foot traffic analysis for restaurants and F&B brands.

Menu_Item Location Occasion Ingredient Creator
$79
one-time, lifetime updates
Buy Pack
👟

Fashion & Apparel

Style trend tracking, body-inclusive fit intelligence, and resale value analysis for fashion brands.

Product Style_Aesthetic Body_Type Collection Color_Palette
$79
one-time, lifetime updates
Buy Pack
💻

Tech / SaaS

Competitive intelligence, feature sentiment tracking, and developer migration analysis for software products.

Product Feature Use_Case Buyer_Persona Pain_Point
$79
one-time, lifetime updates
Buy Pack
🏋️

Fitness & Wellness

Program effectiveness tracking, supplement intelligence, and transformation evidence analysis for fitness brands.

Program Exercise Goal Supplement Diet_Pattern
$79
one-time, lifetime updates
Buy Pack
🎮

Entertainment

IP performance tracking, fandom intelligence, and revenue attribution for games, music, and media brands.

IP_Title Artist_Creator Fandom Event Content
$79
one-time, lifetime updates
Buy Pack
Best Value

All 6 Industry Packs

Get every pack and all future updates. Perfect for agencies serving multiple industries.

$474 $249
Buy All Packs — Save 47%
What's Included

Each Pack Contains

Extraction Prompt

Domain-specific entity types and relationship definitions. Drop-in replacement for the generic prompt — immediately improves KG quality for your industry.

Brand Config

Optimized retrieval, filter, and generation settings. Temperature, trust thresholds, and top-k values tuned for your domain's data characteristics.

Sample Queries

10-12 production-ready Cypher queries with explanations. Covers competitive analysis, ROI tracking, trend detection, and creator performance.

100% Open Source Core

The full pipeline — crawling, transformation, KG generation, RAG chatbot — is MIT licensed. Industry Packs are optional add-ons for production-grade results.

Star on GitHub
After Purchase

Install Your Industry Pack

Download the ZIP, drop it into your project, and restart. Takes 30 seconds.

1. Download & Extract

After purchase, you'll receive a ZIP file via email. Extract it:

unzip ontix-beauty-pack.zip -d packs/beauty/

2. Verify Pack Contents

Each pack contains 3 files:

packs/beauty/
  ├── extraction_prompt.txt   # Domain-specific entity definitions
  ├── brand_config.yaml       # Optimized retrieval & filter settings
  └── sample_queries.md       # 10-12 production Cypher queries

3. Activate the Pack

Set the pack name in your .env or API call, then restart the server:

# In .env
INDUSTRY_PACK=beauty

# Or via API
curl -X POST http://localhost:8000/api/v1/pipeline/run \
  -d '{"brand_id":"demo", "industry_pack":"beauty", ...}'

# Restart to apply
docker-compose restart app

4. Run Your First Query

Open sample_queries.md and try the included Cypher queries in Neo4j Browser:

# Example: Top ingredients mentioned across all brands
MATCH (p:Product)-[:CONTAINS]->(i:Ingredient)
RETURN i.name, count(p) AS mentions
ORDER BY mentions DESC LIMIT 10
FAQ

Frequently Asked Questions

What's included in each Industry Pack?

Each pack contains 3 files: an extraction prompt with domain-specific entity and relationship definitions, a brand_config.yaml with optimized retrieval/filter/generation settings, and 10-12 production-ready Cypher queries with explanations. No code changes needed — just drop the files in and go.

Do I need to modify any code?

No. Industry Packs are pure configuration. Extract the ZIP into your packs/ directory, set the pack name in .env, and restart. The pipeline automatically uses the pack's prompts and settings.

What's the license?

The ONTIX Universal core is MIT licensed — fully open source, use it however you want. Industry Packs are sold under a per-team commercial license: one purchase covers your entire team, unlimited projects, forever.

Do I get updates?

Yes. All purchases include lifetime updates. When we improve a pack's prompts or add new queries, you'll receive the updated ZIP via email at no extra cost.

Can I get a refund?

Yes. We offer a 14-day money-back guarantee. If the pack doesn't work for your use case, email us and we'll refund you — no questions asked.

What if I need a custom pack for my industry?

Contact us at hanso@intellirim.com. We can build custom entity schemas, relationship definitions, and queries tailored to your specific domain.

Is the Bundle really a better deal?

The All 6 Packs Bundle saves you 47% ($249 vs $474 individually). It's ideal for agencies or teams serving clients across multiple industries. You also get all future packs added to the bundle for free.