Mapping Architecture & Semantic Indexing¶

How the unified supply chain schema maps to the existing systems of record, how the semantic indexing pipeline processes it, and how the ReAct agent uses the indexed ontology to serve queries and take actions.

Schema-First Architecture¶

The supply chain ontology uses a schema-first approach — the unified schema is the primary knowledge source, not the FDW foreign tables. FDW becomes a mapping resolution layer that annotates which schema entities have live database connections.

flowchart TD
    subgraph SchemaOverlay [Unified Schema - supply-chain-schema.yaml]
        SF["Salesforce Entities<br/>Account, Opportunity, Campaign..."]
        SAP["SAP Entities - virtual<br/>Material_Master, Inventory_Position..."]
        ORA["Oracle Entities - virtual<br/>AR_Invoice, Purchase_Order..."]
        UNS["Unstructured - virtual<br/>Contract_Document, Market_Signal..."]
    end

    subgraph FDWLayer [FDW Mapping Resolution]
        DISC["FDW Discovery Service<br/>pg_foreign_server + information_schema"]
        MATCH["Match schema fdw_table<br/>to live foreign tables"]
    end

    subgraph Status [Mapping Status]
        MAPPED["MAPPED<br/>Live FDW table exists<br/>Queryable via SQL"]
        VIRTUAL["VIRTUAL<br/>Data via integration<br/>Not directly queryable"]
        UNMAPPED["UNMAPPED<br/>Expected FDW table<br/>not yet connected"]
    end

    SF --> MATCH
    DISC --> MATCH
    MATCH --> MAPPED
    SAP --> VIRTUAL
    ORA --> VIRTUAL
    UNS --> VIRTUAL

Entity Mapping Status¶

Status	Meaning	Count	Example
Mapped	Live FDW foreign table exists; entity is queryable via `query_table` tool	~6	Account, Opportunity, Contact
Virtual	Entity data flows via integration sync; not directly queryable via FDW	~37	Material_Master, Oracle_AR_Invoice, Market_Signal
Unmapped	Schema defines the entity but no FDW table or integration connected yet	~2	Forecast_Override, Campaign (pending FDW config)

Semantic RAG Pipeline (12 Steps)¶

The pipeline has been extended from the original 10 steps to 12 steps with the addition of Steps 1A (Unified Schema Extraction) and 1B (FDW Mapping Resolution):

flowchart LR
    subgraph Extraction [Extraction Phase]
        S1A["Step 1A<br/>Unified Schema Extract<br/>~45 entities from *-schema.yaml"]
        S1B["Step 1B<br/>FDW Mapping Resolution<br/>Match to live FDW tables"]
        S1C["Step 1C<br/>Legacy FDW Extract<br/>Non-schema FDW tables"]
        S2["Step 2<br/>Policy Extract<br/>11 policies from *.md"]
        S3["Step 3<br/>Workflow Extract<br/>15 workflows from *.yaml"]
        S4["Step 4<br/>Integration Extract<br/>7 integrations from *.yaml"]
    end

    subgraph Processing [Processing Phase]
        S5["Step 5<br/>Normalize + Dedupe<br/>Merge into OntoBundle"]
        S6["Step 6<br/>Enrich<br/>SCOR/GS1/FDW-aware"]
        S7["Step 7<br/>Chunk + Embed"]
    end

    subgraph Loading [Loading Phase]
        S8["Step 8<br/>Load pgvector"]
        S9["Step 9<br/>Load Apache AGE Graph"]
        S10["Step 10<br/>Validate - 16 scenarios"]
    end

    S1A --> S1B --> S1C --> S5
    S2 --> S5
    S3 --> S5
    S4 --> S5
    S5 --> S6 --> S7 --> S8 --> S9 --> S10

Step Details¶

Step	File	What It Does
1A	`unified_schema_extractor.py`	Reads all `*-schema.yaml` files; creates OntoDocuments for every entity with SCOR process, GS1 standard, and FDW mapping status annotations
1B	`fdw_mapping_resolver.py`	Queries `FDWDiscoveryService` to match schema entities to live FDW foreign tables; annotates as mapped/virtual/unmapped; enriches mapped entities with live column metadata
1C	`fdw_extractor.py`	Original FDW extractor for non-schema tables (backward compatibility for CRM-only FDW tables)
2	`policy_extractor.py`	Auto-discovers all `*.md` from `enterprise-knowledge/policies/` — includes 8 supply chain + 3 CRM policies
3	`workflow_extractor.py`	Auto-discovers all `*.yaml` from `enterprise-knowledge/workflows/` — includes 12 supply chain + 3 CRM workflows
4	`integration_extractor.py`	Auto-discovers all `*.yaml` from `enterprise-knowledge/integrations/` — includes 6 supply chain + 1 CRM integration
5	`normalizer.py`	Merges all extracted documents; deduplicates by ID; merges relationships and `structured_metadata` on collision
6	`enricher.py`	Schema entities: auto-enriched with SCOR process, GS1 standard, and FDW status. Policies/workflows/integrations: LLM-enriched via gpt-4o-mini
7	`chunker.py`	1 document = 1 chunk; batch embedded (20/batch) via OpenAI text-embedding-3-small
8	`vector_loader.py`	Upserted to pgvector `control_plane_embeddings` with content_type: `onto_schema`, `onto_policy`, `onto_workflow`, `onto_integration`
9	`graph_loader.py`	Nodes (Entity) and edges (triggers/syncs_to/constrained_by/depends_on/validates) merged into Apache AGE `enterprise_onto` graph
10	`validator.py`	16 black-box test scenarios (10 CRM + 6 supply chain) validating retrieval quality across 6 dimensions

What Gets Indexed¶

Source	Content Type	Approx Count
Unified schema (Salesforce + SAP + Oracle + unstructured)	`onto_schema`	~45
Policies (8 SC + 3 CRM)	`onto_policy`	~60+ (split by section)
Workflows (12 SC + 3 CRM)	`onto_workflow`	~15
Integrations (6 SC + 1 CRM)	`onto_integration`	~7
Total	—	~125+

ReAct Agent and Tools¶

The ReAct agent uses the indexed ontology to answer questions and take actions. The flow is: Search ontology -> Reason with policies -> Execute actions -> Validate compliance.

Tool Inventory¶

Read Tools¶

Tool	Domain	What It Does
`search_enterprise_knowledge`	Core	Hybrid vector + graph search across all ontology types
`search_schema_knowledge`	Core	Vector search over FDW table definitions
`discover_tables` / `discover_columns` / `query_table`	Core	FDW table discovery and parameterized SQL queries
`check_policy_compliance`	Governance	Validates proposed actions against indexed policies
`get_inventory_position`	Supply Chain	Query inventory for a material across plants
`get_order_lifecycle`	Supply Chain	Trace order from Salesforce -> SAP -> Oracle
`score_supplier_risk`	Supply Chain	Retrieve supplier risk scoring framework

Write Tools¶

Tool	Risk Level	What It Does
`create_forecast_override`	LOW_RISK_WRITE	Create demand forecast override in Salesforce
`create_transfer_order`	LOW_RISK_WRITE	Create stock rebalancing transfer in SAP
`hold_batch`	HIGH_RISK_WRITE	Quality hold on a batch in SAP
`update_customer_credit`	HIGH_RISK_WRITE	Update credit limit in Salesforce (triggers approval)

End-to-End ReAct Flow¶

sequenceDiagram
    participant User
    participant Agent as ReAct Agent
    participant RAG as Ontology Search
    participant Policy as Policy Check
    participant SoR as System of Record

    User->>Agent: "Should we rebalance Pepsi 500ml inventory?"
    Agent->>RAG: search_enterprise_knowledge("inventory Pepsi 500ml rebalancing")
    RAG-->>Agent: Inventory_Position schema + inventory-policy + rebalancing workflow
    Agent->>Agent: REASON: Policy says rebalance when >45 days AND <5 days
    Agent->>Policy: check_policy_compliance("rebalance", "Inventory_Position", "$45K transfer")
    Policy-->>Agent: COMPLIANT — auto-approved <$50K per POL-INV-001 Section 6
    Agent->>SoR: create_transfer_order(from="PlantA", to="PlantB", qty=5000)
    SoR-->>Agent: Transfer_ID: WT-2026-0042
    Agent->>User: Transfer created. Auto-approved per inventory policy.

UI Integration¶

Data Plane Page¶

Vertical selector filters data sources by domain (All / Supply Chain / CRM)
Each source node shows ontology entity count and SCOR process coverage
Source cards display FDW mapping status (mapped / virtual) and entity count badges

Control Plane Page¶

Semantic Layer tab shows vertical-level stats (Supply Chain: 45 entities, 12 workflows, 8 policies, 6 integrations)
SCOR process distribution badges (Plan, Source, Make, Deliver, Return, Enable)
Knowledge Formation and Semantic Explorer tabs support system and SCOR filtering

Reasoning Page¶

ReAct Tools tab organizes tools into Read Tools and Write Tools with domain badges (Core / Supply Chain / CRM / Governance)
AI Copilot system prompt includes supply chain context and tool selection strategy

Configuration¶

The pipeline is configured via SemanticRagConfig:

Parameter	Default	Purpose
`schema_dir`	`enterprise-knowledge/`	Directory containing `*-schema.yaml` files
`policy_path`	`enterprise-knowledge/policies/`	Directory with policy Markdown files
`workflow_path`	`enterprise-knowledge/workflows/`	Directory with workflow YAML files
`integration_path`	`enterprise-knowledge/integrations/`	Directory with integration YAML files
`skip_unified_schema`	`false`	Skip Step 1A (unified schema extraction)
`skip_fdw_mapping`	`false`	Skip Step 1B (FDW mapping resolution)
`enrich_with_llm`	`true`	Enable LLM enrichment for non-schema docs
`skip_graph`	`false`	Skip Apache AGE graph loading

Trigger reindex via: POST /api/v1/control-plane/reindex

← Back to Ontology Overview