Mapping Architecture & Semantic Indexing¶

How the unified finance & banking 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 finance & banking 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 - finance-banking-schema.yaml]
        CBS["CBS Entities<br/>Customer_Master, Deposit_Account, Transaction_Ledger..."]
        LOS["LOS Entities - virtual<br/>Loan_Application, Loan_Account, Collateral..."]
        AML["AML Entities - virtual<br/>AML_Alert, SAR_Filing, Watchlist_Match..."]
        MKT["Market Data - virtual<br/>Yield_Curve, Macro_Indicator, Sector_Index..."]
        UNS["Unstructured - virtual<br/>KYC_Document, Loan_Document, Contract_Document..."]
    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

    CBS --> MATCH
    DISC --> MATCH
    MATCH --> MAPPED
    LOS --> VIRTUAL
    AML --> VIRTUAL
    MKT --> VIRTUAL
    UNS --> VIRTUAL

Entity Mapping Status¶

Status	Meaning	Count	Example
Mapped	Live FDW foreign table exists; entity is queryable via `query_table` tool	~8	Customer_Master, Deposit_Account, Transaction_Ledger, SF_Account
Virtual	Entity data flows via integration sync; not directly queryable via FDW	~38	Loan_Account, AML_Alert, Yield_Curve, Investment_Holding
Unmapped	Schema defines the entity but no FDW table or integration connected yet	~4	Process_Event_Log, Household (derived entities)

Semantic RAG Pipeline (12 Steps)¶

The pipeline follows the same 12-step process as other vertical ontologies, extended with Steps 1A (Unified Schema Extraction) and 1B (FDW Mapping Resolution):

flowchart LR
    subgraph Extraction [Extraction Phase]
        S1A["Step 1A<br/>Unified Schema Extract<br/>~50 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/>8 policies from *.md"]
        S3["Step 3<br/>Workflow Extract<br/>10 workflows from *.yaml"]
        S4["Step 4<br/>Integration Extract<br/>6 integrations from *.yaml"]
    end

    subgraph Processing [Processing Phase]
        S5["Step 5<br/>Normalize + Dedupe<br/>Merge into OntoBundle"]
        S6["Step 6<br/>Enrich<br/>Basel/IFRS/FATF-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 - 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 `finance-banking-schema.yaml`; creates OntoDocuments for every entity with Basel pillar, IFRS 9 stage, FATF recommendation, 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)
2	`policy_extractor.py`	Auto-discovers all `*.md` from `enterprise-knowledge/policies/` — includes 8 finance-banking policies
3	`workflow_extractor.py`	Auto-discovers all `*.yaml` from `enterprise-knowledge/workflows/` — includes 10 finance-banking workflows
4	`integration_extractor.py`	Auto-discovers all `*.yaml` from `enterprise-knowledge/integrations/` — includes 6 finance-banking integrations
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 Basel pillar, IFRS 9 classification, FATF recommendation, 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`	Black-box test scenarios validating retrieval quality across 6 dimensions

What Gets Indexed¶

Source	Content Type	Approx Count
Unified schema (CBS + LOS + AML + Market Data + DMS + Salesforce FSC)	`onto_schema`	~50
Policies (8 finance-banking)	`onto_policy`	~55+ (split by section)
Workflows (10 finance-banking)	`onto_workflow`	~10
Integrations (6 finance-banking)	`onto_integration`	~6
Total	—	~120+

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_customer_360`	Banking	Assemble unified customer profile across CBS, Salesforce FSC, LOS, AML
`get_credit_exposure`	Banking	Query loan portfolio exposure by borrower, sector, or product
`get_ecl_position`	Banking	Retrieve ECL staging and provision numbers for a borrower or portfolio segment
`get_liquidity_position`	Banking	Query current LCR, NSFR, and cash flow projections
`get_aml_status`	Banking	Retrieve AML alert history, KYC status, and sanctions matches for a customer

Write Tools¶

Tool	Risk Level	What It Does
`update_risk_rating`	HIGH_RISK_WRITE	Update internal credit risk rating (triggers ECL recalculation)
`create_ews_signal`	LOW_RISK_WRITE	Create early warning signal on a borrower
`escalate_aml_alert`	HIGH_RISK_WRITE	Escalate AML alert to senior investigator
`create_loan_restructuring`	HIGH_RISK_WRITE	Initiate loan restructuring (triggers Stage 2)
`create_advisory_interaction`	LOW_RISK_WRITE	Log advisor interaction in Salesforce FSC

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: "What is the ECL impact if Sector X declines 20%?"
    Agent->>RAG: search_enterprise_knowledge("ECL sector stress test Sector X")
    RAG-->>Agent: ECL_Staging schema + credit-risk-policy + Sector_Index + ecl-calculation workflow
    Agent->>Agent: REASON: Need sector exposure, current ECL, and stressed PD/LGD
    Agent->>SoR: get_credit_exposure(sector="Sector X")
    SoR-->>Agent: 142 loans, $180M outstanding, avg PD 2.3%, current ECL $4.2M
    Agent->>Agent: REASON: Apply 20% sector decline → PD uplift ~1.8x → Stage 2 migration for 35% of exposures
    Agent->>Policy: check_policy_compliance("stress_test", "ECL_Staging", "sector decline 20%")
    Policy-->>Agent: COMPLIANT — within stress test authority per POL-CR-001
    Agent->>User: Sector X stress impact: ECL would increase from $4.2M to $7.8M (+$3.6M). 50 loans would migrate to Stage 2. Recommend ALCO review per credit risk policy.

UI Integration¶

Data Plane Page¶

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

Control Plane Page¶

Semantic Layer tab shows vertical-level stats (Finance-Banking: 50 entities, 10 workflows, 8 policies, 6 integrations)
Basel pillar distribution badges (Pillar 1-Credit, Pillar 1-Market, Pillar 1-OpRisk, Pillar 2, Pillar 3, Liquidity)
Knowledge Formation and Semantic Explorer tabs support system and Basel filtering

Reasoning Page¶

ReAct Tools tab organizes tools into Read Tools and Write Tools with domain badges (Core / Banking / CRM / Governance)
AI Copilot system prompt includes banking 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