Mapping Architecture & Semantic Indexing¶

How the unified telecommunications 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 telecommunications 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 - telco-schema.yaml]
        BSS["BSS Entities<br/>Subscriber_Master, Plan_Product, Billing_Record..."]
        OSS["OSS/CDR Entities - virtual<br/>Alarm, Performance_Counter, CDR_Record, Cell_Site..."]
        CRM["CRM Entities - virtual<br/>Contact, Interaction_Record, Campaign, NPS_Survey..."]
        FIELD["Field Entities - virtual<br/>Work_Order, Technician, Equipment_Telemetry, Site_Survey..."]
        EXT["External - virtual<br/>Competitor_Plan, Regulatory_Publication, Spectrum_License..."]
    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

    BSS --> MATCH
    DISC --> MATCH
    MATCH --> MAPPED
    OSS --> VIRTUAL
    CRM --> VIRTUAL
    FIELD --> VIRTUAL
    EXT --> VIRTUAL

Entity Mapping Status¶

Status	Meaning	Count	Example
Mapped	Live FDW foreign table exists; entity is queryable via `query_table` tool	~8	Subscriber_Master, Plan_Product, Billing_Record, CDR_Record, Alarm, Cell_Site, Performance_Counter, Network_Element
Virtual	Entity data flows via integration sync; not directly queryable via FDW	~35	Work_Order, Equipment_Telemetry, Interaction_Record, NPS_Survey, Campaign, Competitor_Plan, Regulatory_Publication
Unmapped	Schema defines the entity but no FDW table or integration connected yet	~5	Aggregated_Usage, KQI (derived/calculated 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/>TMF/eTOM-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 `telco-schema.yaml`; creates OntoDocuments for every entity with TMF API alignment, eTOM process area, 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 telco policies
3	`workflow_extractor.py`	Auto-discovers all `*.yaml` from `enterprise-knowledge/workflows/` — includes 10 telco workflows
4	`integration_extractor.py`	Auto-discovers all `*.yaml` from `enterprise-knowledge/integrations/` — includes 6 telco 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 TMF API alignment, eTOM process area, 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 (BSS + OSS + CDR + CRM + Field + External)	`onto_schema`	~50
Policies (8 telco)	`onto_policy`	~55+ (split by section)
Workflows (10 telco)	`onto_workflow`	~10
Integrations (6 telco)	`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_subscriber_360`	Telco	Assemble unified subscriber profile across BSS, CRM, CDR, Interactions
`get_network_health`	Telco	Query network-wide health: active alarms, degraded cells, SLA metrics
`get_cell_site_performance`	Telco	Retrieve cell site KPIs: PRB utilization, throughput, availability, alarms
`get_revenue_leakage`	Telco	Query revenue leakage metrics: CDR integrity, billing reconciliation, fraud
`get_churn_risk`	Telco	Retrieve churn risk scores, contributing factors, and recommended actions

Write Tools¶

Tool	Risk Level	What It Does
`create_retention_offer`	LOW_RISK_WRITE	Create retention offer for at-risk subscriber (policy-constrained)
`create_fault_ticket`	LOW_RISK_WRITE	Create fault ticket from correlated alarm group
`escalate_alarm`	HIGH_RISK_WRITE	Escalate alarm to NOC or CTO (triggers SLA clock)
`update_spectrum_config`	HIGH_RISK_WRITE	Update spectrum configuration (requires regulatory compliance check)
`create_work_order`	LOW_RISK_WRITE	Create field work order with dispatch priority and SLA

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's driving churn in the South region and are there network issues contributing?"
    Agent->>RAG: search_enterprise_knowledge("churn South region network issues correlation")
    RAG-->>Agent: Churn_Event schema + customer-retention-policy + network-sla-policy + churn-prediction workflow
    Agent->>Agent: REASON: Need churn data by region, network performance, and complaint correlation
    Agent->>SoR: get_churn_risk(region="South")
    SoR-->>Agent: 847 churned subscribers (30d), top factors: network quality (42%), pricing (31%), competitor offer (27%)
    Agent->>SoR: get_network_health(region="South")
    SoR-->>Agent: 12 degraded cells, avg availability 99.87% (below 99.95% SLA), 3 repeat fault sites
    Agent->>Policy: check_policy_compliance("retention_intervention", "Churn_Event", "South region network-driven churn")
    Policy-->>Agent: COMPLIANT — retention intervention authorized per POL-RET-001; network remediation required per POL-SLA-001
    Agent->>User: South region churn is 1.8% (above 1.2% target). Root cause: 42% network-driven — 12 degraded cells with availability below SLA. 3 sites have repeat faults. Recommend: (1) Priority fault resolution for 3 repeat-fault sites, (2) Proactive retention offers to 312 high-CLV subscribers on affected cells, (3) Capacity review for top-traffic cells in South region.

UI Integration¶

Data Plane Page¶

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

Control Plane Page¶

Semantic Layer tab shows vertical-level stats (Telco: 50 entities, 10 workflows, 8 policies, 6 integrations)
TMF API distribution badges (TMF629 Customer, TMF622 Product, TMF638 Service, TMF639 Resource, TMF642 Alarm, TMF654 Prepay, TMF678 Billing)
Knowledge Formation and Semantic Explorer tabs support system and TMF filtering

Reasoning Page¶

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