4. Fundamental Examples

Semantic Search Query Core

Perform context-aware searches that understand intent, synonyms, and cross-disciplinary relationships rather than exact keyword matching.

Python • aevum_sdk

import aevum

client = aevum.Client(api_key="ae_live_...")

# Natural language query with semantic routing
results = client.search.query(
    text="How did 17th century navigation influence modern GPS?",
    domain="history_technology",
    depth="comprehensive",
    sources=5
)

print(results.primary_match.title)
print(results.semantic_related)

Expected Output


Title: Celestial Navigation to Satellite Positioning\nRelated: ["Trigonometry in Maritime Trade", "Cold War Space Race", "Geodesy Fundamentals"]\nConfidence: 0.94\nCross-References: 12

▶ Run in Sandbox Read Full Docs

Knowledge Graph Traversal Advanced

Navigate interconnected concepts visually or programmatically. Extract relationships, dependencies, and evolutionary paths across disciplines.

JavaScript • REST API

const response = await fetch(`https://api.aevum.dev/v1/graph/explore`, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "seed_concept": "Machine Learning",
    "hop_distance": 2,
    "min_relevance": 0.7,
    "format": "cypher_json"
  })
});

const graph = await response.json();
console.log(graph.nodes.length, "concepts discovered");

Expected Output


Nodes: 47 | Edges: 112\nPath: ["Machine Learning"] → ["Neural Networks"] → ["Backpropagation"] → ["Calculus"]\nMetadata: { disciplinary_span: ["CS", "Math", "Biology"], confidence: 0.89 }

▶ Visualize Graph Graph Schema Reference

Dynamic Article Embedding UI

Embed responsive, theme-aware encyclopedia articles into external platforms, CMS systems, or learning management platforms with zero maintenance.

HTML / React Component

<!-- Minimal Embed -->
<div class="aevum-embed" data-article="quantum_entanglement" data-theme="dark"></div>
<script src="https://cdn.aevum.dev/embed/v2.js"></script>

/* React Wrapper */
import { AevumArticle } from "@aevum/react-sdk";

function ResearchPanel() {
  return (
    <AevumArticle
      slug="behavioral_economics"
      sections={["overview", "key_models", "applications"]}
      language={"auto"}
      onCite={handleCitation} /
    >
  );
}

Expected Output


✅ Rendered in < 200ms\n✅ Respects host CSS variables\n✅ Auto-translates based on user locale\n✅ Citation modal triggered on click

▶ Live Playground Embed Configuration

Citation & Data Export Compliance

Generate academically compliant citations (APA, MLA, Chicago, BibTeX) and export structured datasets for offline research or LLM fine-tuning.

cURL • CLI Tool

# Generate formatted citations + download raw JSON
curl -X POST https://api.aevum.dev/v1/export/cite \n  -H "Authorization: Bearer $AEVUM_KEY" \n  -d '{
    "articles": ["dark_matter", "cosmic_inflation"],
    "format": "apa7",
    "include_metadata": true,
    "license": "cc-by-4.0"
  }'

# CLI alternative
aevum export --articles "dark_matter" --out ./dataset.jsonl --schema v2

Expected Output


[1] Smith, J., & Chen, L. (2024). Dark Matter Detection Methods. Aevum Encyclopedia. https://aevum.dev/a/dark_matter\n\nExported: 2 articles → ./dataset.jsonl (48.2 KB)\n✓ Validated against schema v2\n✓ CC-BY 4.0 license attached

▶ Batch Export Demo Citation Standards

AI Insight Integration Beta

Tap into Aevum's real-time reasoning layer to get synthesized summaries, contradiction detection, and forward-looking research suggestions.

Python • AI Layer

from aevum.ai import InsightEngine

engine = InsightEngine(model="aevum-reason-v3")

# Cross-verify and synthesizeanalysis = engine.analyze(
    query="Is nuclear fusion commercially viable by 2040?",
    constraints={"peer_reviewed": True, "temporal_window": "2020-2024"},
    output="structured_summary"
)

print(analysis.consensus_score)  # 0.87
print(analysis.conflicting_claims) # ["Net-energy gain timelines"]
print(analysis.suggested_next_queries)

Expected Output


Consensus: 0.87 | Confidence: High\nConflicts: ["ITER timeline vs. private fusion startups", "Material degradation rates"]\nSuggested: ["Superconducting magnets breakthrough", "Plasma stability control"]\n⚠️ Beta: Model outputs may evolve with training updates

▶ Try AI Playground Model Transparency Report