Getting Started - Semantica

Already installed? Jump straight to Quickstart. Need setup help first? See Installation.

What You Can Build

GraphRAG Systems — Ground LLM responses in traceable, structured knowledge. Every claim links back to a source node.
Accountable AI Agents — Agents with structured decision history, causal chains, and precedent search. Every choice is recorded and auditable.
Production Knowledge Graphs — Build, validate, and maintain enterprise-grade semantic knowledge bases from multi-source data.
Compliance-Ready AI — W3C PROV-O provenance on every fact. HIPAA, SOX, GDPR, FDA 21 CFR Part 11 infrastructure built in.

Setup in 3 Steps

Install Semantica

pip install semantica

pip install semantica[all]

git clone https://github.com/semantica-agi/semantica.git
cd semantica
pip install -e ".[dev]"

Verify installation:

import semantica
print(semantica.__version__)  # 0.6.0

Choose your path

Pick the track that matches what you’re building: each starts with a focused 5-minute example.

Track	You want to…	Start with
Knowledge Graph	Turn documents into structured, queryable graphs	Quickstart → Step 1
Agent Context	Give your AI agent persistent memory and decision tracking	Context reference
GraphRAG	Ground LLM answers in structured knowledge	Concepts → GraphRAG
MCP Integration	Use Semantica from Claude Desktop or VS Code	MCP Server

Run the pipeline

The full 6-step pipeline: ingest, parse, extract, build, visualize, export: is in the Quickstart. Takes under 5 minutes with pattern-based extraction (no API key required).

An LLM API key is optional for the quickstart. Pattern-based extraction works out of the box: upgrade to LLM extraction for higher accuracy when you’re ready.

Choose Your Path

Knowledge Graph
Agent Context
GraphRAG
MCP Integration

Build a structured knowledge graph from any document or data source.

from semantica.ingest import FileIngestor
from semantica.parse import DocumentParser
from semantica.semantic_extract import NERExtractor, RelationExtractor
from semantica.kg import GraphBuilder

# 1. Ingest
sources = FileIngestor().ingest("data/report.pdf")

# 2. Parse
parsed = DocumentParser().parse(sources[0])

# 3. Extract
ner           = NERExtractor(method="pattern")  # no API key needed
entities      = ner.extract(parsed)
relationships = RelationExtractor().extract(parsed, entities=entities)

# 4. Build
graph = GraphBuilder(merge_entities=True).build(
    {"entities": entities, "relationships": relationships}
)
print(f"{len(graph['entities'])} nodes, {len(graph['relationships'])} edges")

Next: Full pipeline walkthrough →

Give your agent persistent memory, decision tracking, and precedent search.

from semantica.context import AgentContext, ContextGraph
from semantica.vector_store import VectorStore

context = AgentContext(
    vector_store=VectorStore(backend="faiss", dimension=768),
    knowledge_graph=ContextGraph(advanced_analytics=True),
    decision_tracking=True,
)

# Store a fact with provenance
context.store("GPT-4 outperforms GPT-3.5 on reasoning by 40%")

# Record a decision with full causal chain
decision_id = context.record_decision(
    category="model_selection",
    scenario="Choose LLM for production pipeline",
    reasoning="GPT-4 benchmark advantage justifies cost",
    outcome="selected_gpt4",
    confidence=0.91,
)

# Search past decisions before making a new one
precedents = context.find_precedents("model selection", limit=5)

Next: Context module reference →

Ground every LLM response in your knowledge graph: no floating assertions.

from semantica.context import AgentContext, ContextGraph
from semantica.vector_store import VectorStore

context = AgentContext(
    vector_store=VectorStore(backend="faiss", dimension=768),
    knowledge_graph=ContextGraph(advanced_analytics=True),
)

# Load your knowledge graph
context.load_graph("company_kg.json")

# Multi-hop GraphRAG query
result = context.query(
    "What companies were founded by people who worked at Apple?",
    mode="graphrag",
    reasoning=True,
)

# Every claim links back to a source node
for claim in result.claims:
    print(f"{claim.text}  →  source: {claim.source_node}")

Next: GraphRAG concepts →

Use Semantica from Claude Desktop, VS Code, Cursor, or any MCP client: no Python code required after setup.

pip install semantica

Add to your MCP client config:

{
  "mcpServers": {
    "semantica": {
      "command": "semantica-mcp"
    }
  }
}

12 tools available instantly: extract entities, query graph, record decisions, run reasoning, export results.Next: MCP Server reference →

Core Architecture

Semantica uses a modular, layered architecture: import only what you need.

Input Layer — Load and prepare data from any source. Modules: ingest, parse, split, normalize
Semantic Layer — Extract meaning from raw text. Modules: semantic_extract, kg, ontology, reasoning
Storage Layer — Persist knowledge for retrieval. Modules: embeddings, vector_store, graph_store, triplet_store
Quality Layer — Validate and deduplicate. Modules: deduplication, conflicts
Context Layer — Track decisions and lineage. Modules: context, provenance, change_management
Output Layer — Deliver results downstream. Modules: export, visualization, pipeline, explorer

Which Module Do I Need?

See the Choose the Right Module guide — it maps 35+ developer goals to the right starting point across all 27 modules, with working code for the most common paths.

Next Steps

Core Concepts — Knowledge graphs, ontologies, and reasoning explained in depth.
Quickstart Tutorial — Full 6-step pipeline walkthrough with working code.
Module Reference — Every module, class, and common chain explained.
API Reference — Complete module documentation for every class and method.

Help

Discord — Ask questions, share projects, get community support.
GitHub Issues — Report bugs or request features.
FAQ — Common questions answered.

​What You Can Build

​Setup in 3 Steps

​Choose Your Path

​Core Architecture

​Which Module Do I Need?

​Next Steps

​Help

What You Can Build

Setup in 3 Steps

Choose Your Path

Core Architecture

Which Module Do I Need?

Next Steps

Help