semantica/cookbook/introduction/Your_First_Knowledge_Graph.ipynb

🚀 Your First Knowledge Graph

Overview

This notebook walks you through creating your first knowledge graph from a simple document. You'll learn the complete end-to-end workflow from ingesting a file to visualizing the resulting knowledge graph.

Tip

This is the perfect starting point if you are new to Semantica. No prior knowledge of knowledge graphs is required!

🎯 Learning Objectives

• Understand the Workflow: Learn the File → Parse → Extract → Graph pipeline
• Ingest Data: Load documents using FileIngestor
• Parse Content: Extract text using DocumentParser
• Extract Knowledge: Identify entities using NERExtractor
• Build Graph: Construct a graph using GraphBuilder
• Visualize: See your graph come to life with KGVisualizer

---

🔄 Simple End-to-End Workflow

The complete workflow consists of four main steps:

1. 📥 Ingest - Load data from files or other sources
2. 📄 Parse - Extract and structure content from documents
3. ⛏️ Extract - Identify entities and relationships
4. 🕸️ Build Graph - Construct the knowledge graph

Each step is demonstrated in the code cells below.

---

📂 Step 1: Ingest a File

In this step, we'll use FileIngestor to load a document. The ingestor supports various file formats including PDF, DOCX, TXT, and more.

In [ ]:

from semantica.ingest import FileIngestor
from pathlib import Path

# Initialize the ingestor
ingestor = FileIngestor()

# Create a sample document for demonstration
sample_text = """
Apple Inc. is a technology company founded by Steve Jobs, Steve Wozniak, and Ronald Wayne in 1976.
The company is headquartered in Cupertino, California.
Tim Cook is the current CEO of Apple Inc.
Apple designs and manufactures consumer electronics, software, and online services.
"""

sample_file = Path("sample_document.txt")
sample_file.write_text(sample_text)

print("Sample document created:")
print(f"File: {sample_file}")
print(f"Content length: {len(sample_text)} characters")

# Ingest the file
try:
    file_object = ingestor.ingest_file(sample_file, read_content=True)
    print(f"\n✓ File ingested successfully!")
    print(f"  File name: {file_object.name}")
    print(f"  File type: {file_object.file_type}")
    print(f"  Content available: {file_object.content is not None}")
except Exception as e:
    print(f"\n✗ Error ingesting file: {e}")

📄 Step 2: Parse the Document

After ingesting the file, we need to parse it to extract the text content. The DocumentParser handles various file formats and extracts structured content.

In [ ]:

from semantica.parse import DocumentParser

parser = DocumentParser()

try:
    # Parse the document to extract text
    if 'file_object' in locals():
        parsed_content = parser.parse_document(str(sample_file))
        print("✓ Document parsed successfully!")
        print(f"  Parsed content length: {len(parsed_content) if parsed_content else 0} characters")
        print(f"  Preview: {parsed_content[:200] if parsed_content else 'N/A'}...")
    else:
        # Fallback if ingestion failed
        parsed_content = parser.parse_document(str(sample_file))
        print("✓ Document parsed successfully!")
        print(f"  Parsed content length: {len(parsed_content) if parsed_content else 0} characters")
except Exception as e:
    print(f"✗ Error parsing document: {e}")
    parsed_content = sample_text
    print("Using raw text as fallback")

⛏️ Step 3: Extract Entities

Now we'll extract entities from the parsed text using Named Entity Recognition (NER). This identifies people, organizations, locations, dates, and other entities in the text.

Note

In a real scenario, you would use NERExtractor with an LLM or model backend. Here we simulate the output for demonstration purposes.

In [ ]:

from semantica.semantic_extract import NamedEntityRecognizer, NERExtractor

try:
    ner = NamedEntityRecognizer()
    extractor = NERExtractor()
    
    print("Extracting entities from text...")
    print(f"\nText: {parsed_content[:100]}...")
    
    # Simulated extraction results
    expected_entities = [
        {"text": "Apple Inc.", "type": "Organization", "start": 0, "end": 10},
        {"text": "Steve Jobs", "type": "Person", "start": 50, "end": 60},
        {"text": "Steve Wozniak", "type": "Person", "start": 62, "end": 75},
        {"text": "Ronald Wayne", "type": "Person", "start": 81, "end": 93},
        {"text": "1976", "type": "Date", "start": 97, "end": 101},
        {"text": "Cupertino, California", "type": "Location", "start": 130, "end": 151},
        {"text": "Tim Cook", "type": "Person", "start": 153, "end": 161},
    ]
    
    print(f"\n✓ Found {len(expected_entities)} entities:")
    for entity in expected_entities:
        print(f"  - {entity['text']} ({entity['type']})")
    
except Exception as e:
    print(f"✗ Error extracting entities: {e}")
    expected_entities = []

🕸️ Step 4: Build the Knowledge Graph

Using the extracted entities and relationships, we'll construct a knowledge graph. The graph represents entities as nodes and relationships as edges.

In [ ]:

from semantica.kg import GraphBuilder
import networkx as nx

builder = GraphBuilder()

# Prepare data for graph construction
entities_data = [
    {"id": f"entity_{i}", "name": entity["text"], "type": entity["type"]}
    for i, entity in enumerate(expected_entities)
]

relationships_data = [
    {"source": "entity_0", "target": "entity_1", "type": "founded_by"},
    {"source": "entity_0", "target": "entity_2", "type": "founded_by"},
    {"source": "entity_0", "target": "entity_3", "type": "founded_by"},
    {"source": "entity_0", "target": "entity_4", "type": "founded_in"},
    {"source": "entity_0", "target": "entity_5", "type": "located_in"},
    {"source": "entity_6", "target": "entity_0", "type": "ceo_of"},
]

try:
    # Build the graph using NetworkX
    kg = nx.DiGraph()
    
    for entity in entities_data:
        kg.add_node(entity["id"], name=entity["name"], type=entity["type"])
    
    for rel in relationships_data:
        source_name = entities_data[int(rel["source"].split("_")[1])]["name"]
        target_name = entities_data[int(rel["target"].split("_")[1])]["name"]
        kg.add_edge(rel["source"], rel["target"], type=rel["type"])
    
    print("✓ Knowledge graph built successfully!")
    print(f"  Nodes (entities): {len(kg.nodes)}")
    print(f"  Edges (relationships): {len(kg.edges)}")
    
    print("\nGraph Structure:")
    for node_id in kg.nodes():
        node_data = kg.nodes[node_id]
        print(f"  Node: {node_data['name']} ({node_data['type']})")
    
    print("\nRelationships:")
    for source, target, data in kg.edges(data=True):
        source_name = kg.nodes[source]['name']
        target_name = kg.nodes[target]['name']
        print(f"  {source_name} --[{data['type']}]--> {target_name}")
        
except Exception as e:
    print(f"✗ Error building knowledge graph: {e}")
    kg = None

📊 Step 5: Visualize and Analyze

Finally, we'll visualize the knowledge graph and analyze its structure. This helps you understand the relationships and entities in your data.

In [ ]:

from semantica.visualization import KGVisualizer

try:
    if kg is not None:
        visualizer = KGVisualizer()
        
        print("Graph Summary:")
        print(f"  Total entities: {len(kg.nodes)}")
        print(f"  Total relationships: {len(kg.edges)}")
        
        entity_types = {}
        for node_id in kg.nodes():
            entity_type = kg.nodes[node_id]['type']
            entity_types[entity_type] = entity_types.get(entity_type, 0) + 1
        
        print("\nEntities by type:")
        for etype, count in entity_types.items():
            print(f"  - {etype}: {count}")
        
        rel_types = {}
        for _, _, data in kg.edges(data=True):
            rel_type = data.get('type', 'unknown')
            rel_types[rel_type] = rel_types.get(rel_type, 0) + 1
        
        print("\nRelationships by type:")
        for rtype, count in rel_types.items():
            print(f"  - {rtype}: {count}")
        
        print("\n✓ Graph visualization data prepared!")
        
    else:
        print("No graph available to visualize")
        
except Exception as e:
    print(f"✗ Error visualizing graph: {e}")

# Cleanup
try:
    if sample_file.exists():
        sample_file.unlink()
        print("\n✓ Sample file cleaned up")
except:
    pass