# hardikdhawan2904/mva-azure architecture

> Architecture diagram of the GitHub repository hardikdhawan2904/mva-azure, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/hardikdhawan2904/mva-azure
- Repository: https://github.com/hardikdhawan2904/mva-azure

## Overview

MVA is a multi-agent data pipeline: a user uploads CSV/Excel data to the orchestrator, which deduplicates or versions it, invokes schema quality/classification, then structural profiling and readiness analysis, and optionally analytics. The README documents the major capabilities and service handoffs; sampled pipeline excerpts support several internal stages. Some service-to-service details and unsampled integrations are documented only at the README level, so edges below avoid inferring finer-grained calls.

Main entry points: [`Data-Profiling-Agent/app/agents/data_profiling_agent/nodes/pipeline.py`](https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/agents/data_profiling_agent/nodes/pipeline.py) (Profiling Pipeline), [`Agent-Orchestrator/app/agents/orchestration_agent/nodes/pipeline.py`](https://github.com/hardikdhawan2904/mva-azure/blob/main/Agent-Orchestrator/app/agents/orchestration_agent/nodes/pipeline.py) (Pipeline Orchestrator), [`Analytics-Agent/app/agents/analytics_agent/nodes/pipeline.py`](https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/agents/analytics_agent/nodes/pipeline.py) (Analytics Pipeline), [`Schema-Intelligence-Layer/app/agents/schema_intelligence_agent/nodes/pipeline.py`](https://github.com/hardikdhawan2904/mva-azure/blob/main/Schema-Intelligence-Layer/app/agents/schema_intelligence_agent/nodes/pipeline.py) (Schema Service)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_orchestration["Orchestration"]
  node_orchestrator["Pipeline Orchestrator<br/>[pipeline.py]"]
  node_registry[("Dataset Registry")]
end

subgraph group_schema["Schema Intelligence"]
  node_schema_service["Schema Service<br/>[pipeline.py]"]
  node_quality_gate["Quality Gate"]
  node_classification["Domain Classification<br/>[pipeline.py]"]
end

subgraph group_profiling["Data Profiling"]
  node_profiling_service["Profiling Pipeline<br/>[pipeline.py]"]
  node_structural_profile["Structural Profiling<br/>[column_profiler.py]"]
  node_hierarchy["Hierarchy Inference"]
  node_quality_rules["Quality Rules<br/>[rule_engine.py]"]
  node_readiness["AI Readiness"]
  node_charts["Chart Generation"]
  node_rule_suggestions["Rule Suggestions"]
end

subgraph group_analytics["Analytics"]
  node_analytics_service["Analytics Pipeline<br/>[pipeline.py]"]
  node_analytics_capabilities["Analytics Capabilities"]
  node_analytics_planning["Analytics Planning"]
  node_analytics_tools["Analytics Tools<br/>[analytics_tool.py]"]
  node_conversation_memory[("Conversation Memory<br/>[database.py]")]
end

subgraph group_persistence["Shared Persistence"]
  node_postgres[("Shared Postgres")]
end

node_user(("Dataset User"))

node_user -->|"uploads data"| node_orchestrator
node_orchestrator -->|"checks identity"| node_registry
node_orchestrator -->|"invokes classification"| node_schema_service
node_schema_service -->|"validates quality"| node_quality_gate
node_schema_service -->|"classifies dataset"| node_classification
node_orchestrator -->|"invokes profiling"| node_profiling_service
node_classification -->|"provides domain and descriptions"| node_profiling_service
node_profiling_service -->|"profiles columns"| node_structural_profile
node_profiling_service -->|"builds hierarchy"| node_hierarchy
node_profiling_service -->|"evaluates rules"| node_quality_rules
node_profiling_service -->|"scores readiness"| node_readiness
node_profiling_service -->|"generates charts"| node_charts
node_profiling_service -->|"proposes rules"| node_rule_suggestions
node_orchestrator -.->|"optionally invokes"| node_analytics_service
node_analytics_service -->|"resolves capabilities"| node_analytics_capabilities
node_analytics_service -->|"plans analysis"| node_analytics_planning
node_analytics_service -->|"uses analysis tools"| node_analytics_tools
node_schema_service -->|"persists metadata"| node_postgres
node_profiling_service -->|"persists profiles"| node_postgres
node_analytics_service -->|"loads and saves turns"| node_conversation_memory
node_conversation_memory -->|"stores turns"| node_postgres

click node_orchestrator "https://github.com/hardikdhawan2904/mva-azure/blob/main/Agent-Orchestrator/app/agents/orchestration_agent/nodes/pipeline.py"
click node_registry "https://github.com/hardikdhawan2904/mva-azure/blob/main/Agent-Orchestrator/app/services/dataset_registry/dataset_registry.py"
click node_schema_service "https://github.com/hardikdhawan2904/mva-azure/blob/main/Schema-Intelligence-Layer/app/agents/schema_intelligence_agent/nodes/pipeline.py"
click node_quality_gate "https://github.com/hardikdhawan2904/mva-azure/blob/main/Schema-Intelligence-Layer/app/services/quality_validator.py"
click node_classification "https://github.com/hardikdhawan2904/mva-azure/blob/main/Schema-Intelligence-Layer/app/agents/classification_agent/nodes/pipeline.py"
click node_profiling_service "https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/agents/data_profiling_agent/nodes/pipeline.py"
click node_structural_profile "https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/profiling/column_profiler.py"
click node_hierarchy "https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/hierarchy/candidate_builder.py"
click node_quality_rules "https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/rules/rule_engine.py"
click node_readiness "https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/readiness/readiness_engine.py"
click node_charts "https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/charts/candidate_generator.py"
click node_rule_suggestions "https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/rules/suggestion_generator.py"
click node_analytics_service "https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/agents/analytics_agent/nodes/pipeline.py"
click node_analytics_capabilities "https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/services/capability_resolution/analytics_capability_resolver.py"
click node_analytics_planning "https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/services/planning/analytics_planner.py"
click node_analytics_tools "https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/services/tools/analytics_tool.py"
click node_conversation_memory "https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/services/database.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_orchestrator,node_registry,node_user toneBlue
class node_schema_service,node_quality_gate,node_classification toneAmber
class node_profiling_service,node_structural_profile,node_hierarchy,node_quality_rules,node_readiness,node_charts,node_rule_suggestions toneMint
class node_analytics_service,node_analytics_capabilities,node_analytics_planning,node_analytics_tools,node_conversation_memory toneRose
class node_postgres toneIndigo
```

## Components

### Orchestration

- [Pipeline Orchestrator](https://github.com/hardikdhawan2904/mva-azure/blob/main/Agent-Orchestrator/app/agents/orchestration_agent/nodes/pipeline.py): `Agent-Orchestrator/app/agents/orchestration_agent/nodes/pipeline.py`
- [Dataset Registry](https://github.com/hardikdhawan2904/mva-azure/blob/main/Agent-Orchestrator/app/services/dataset_registry/dataset_registry.py): `Agent-Orchestrator/app/services/dataset_registry/dataset_registry.py`

### Schema Intelligence

- [Schema Service](https://github.com/hardikdhawan2904/mva-azure/blob/main/Schema-Intelligence-Layer/app/agents/schema_intelligence_agent/nodes/pipeline.py): `Schema-Intelligence-Layer/app/agents/schema_intelligence_agent/nodes/pipeline.py`
- [Quality Gate](https://github.com/hardikdhawan2904/mva-azure/blob/main/Schema-Intelligence-Layer/app/services/quality_validator.py): `Schema-Intelligence-Layer/app/services/quality_validator.py`
- [Domain Classification](https://github.com/hardikdhawan2904/mva-azure/blob/main/Schema-Intelligence-Layer/app/agents/classification_agent/nodes/pipeline.py): `Schema-Intelligence-Layer/app/agents/classification_agent/nodes/pipeline.py`

### Data Profiling

- [Profiling Pipeline](https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/agents/data_profiling_agent/nodes/pipeline.py): `Data-Profiling-Agent/app/agents/data_profiling_agent/nodes/pipeline.py`
- [Structural Profiling](https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/profiling/column_profiler.py): `Data-Profiling-Agent/app/services/profiling/column_profiler.py`
- [Hierarchy Inference](https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/hierarchy/candidate_builder.py): `Data-Profiling-Agent/app/services/hierarchy/candidate_builder.py`
- [Quality Rules](https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/rules/rule_engine.py): `Data-Profiling-Agent/app/services/rules/rule_engine.py`
- [AI Readiness](https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/readiness/readiness_engine.py): `Data-Profiling-Agent/app/services/readiness/readiness_engine.py`
- [Chart Generation](https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/charts/candidate_generator.py): `Data-Profiling-Agent/app/services/charts/candidate_generator.py`
- [Rule Suggestions](https://github.com/hardikdhawan2904/mva-azure/blob/main/Data-Profiling-Agent/app/services/rules/suggestion_generator.py): `Data-Profiling-Agent/app/services/rules/suggestion_generator.py`

### Analytics

- [Analytics Pipeline](https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/agents/analytics_agent/nodes/pipeline.py): `Analytics-Agent/app/agents/analytics_agent/nodes/pipeline.py`
- [Analytics Capabilities](https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/services/capability_resolution/analytics_capability_resolver.py): `Analytics-Agent/app/services/capability_resolution/analytics_capability_resolver.py`
- [Analytics Planning](https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/services/planning/analytics_planner.py): `Analytics-Agent/app/services/planning/analytics_planner.py`
- [Analytics Tools](https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/services/tools/analytics_tool.py): `Analytics-Agent/app/services/tools/analytics_tool.py`
- [Conversation Memory](https://github.com/hardikdhawan2904/mva-azure/blob/main/Analytics-Agent/app/services/database.py): `Analytics-Agent/app/services/database.py`

### Shared Persistence

- **Shared Postgres**

### Other components

- **Dataset User**

## Connections

- Dataset User → Pipeline Orchestrator: uploads data (evidence: `README.md`)
- Pipeline Orchestrator → Dataset Registry: checks identity (evidence: `Agent-Orchestrator/app/agents/orchestration_agent/nodes/pipeline.py`)
- Pipeline Orchestrator → Schema Service: invokes classification (evidence: `README.md`)
- Schema Service → Quality Gate: validates quality (evidence: `Schema-Intelligence-Layer/app/agents/schema_intelligence_agent/nodes/pipeline.py`)
- Schema Service → Domain Classification: classifies dataset (evidence: `Schema-Intelligence-Layer/app/agents/schema_intelligence_agent/nodes/pipeline.py`)
- Pipeline Orchestrator → Profiling Pipeline: invokes profiling (evidence: `README.md`)
- Domain Classification → Profiling Pipeline: provides domain and descriptions (evidence: `README.md`)
- Profiling Pipeline → Structural Profiling: profiles columns (evidence: `Data-Profiling-Agent/app/agents/data_profiling_agent/nodes/pipeline.py`)
- Profiling Pipeline → Hierarchy Inference: builds hierarchy (evidence: `README.md`)
- Profiling Pipeline → Quality Rules: evaluates rules (evidence: `README.md`)
- Profiling Pipeline → AI Readiness: scores readiness (evidence: `Data-Profiling-Agent/app/services/readiness/readiness_engine.py`)
- Profiling Pipeline → Chart Generation: generates charts (evidence: `Data-Profiling-Agent/app/agents/data_profiling_agent/nodes/pipeline.py`)
- Profiling Pipeline → Rule Suggestions: proposes rules (evidence: `README.md`)
- Pipeline Orchestrator → Analytics Pipeline: optionally invokes (evidence: `README.md`)
- Analytics Pipeline → Analytics Capabilities: resolves capabilities (evidence: `Analytics-Agent/app/agents/analytics_agent/nodes/pipeline.py`)
- Analytics Pipeline → Analytics Planning: plans analysis (evidence: `Analytics-Agent/app/agents/analytics_agent/nodes/pipeline.py`)
- Analytics Pipeline → Analytics Tools: uses analysis tools (evidence: `Analytics-Agent/app/agents/analytics_agent/nodes/pipeline.py`)
- Schema Service → Shared Postgres: persists metadata (evidence: `README.md`)
- Profiling Pipeline → Shared Postgres: persists profiles (evidence: `README.md`)
- Analytics Pipeline → Conversation Memory: loads and saves turns (evidence: `Analytics-Agent/app/services/database.py`)
- Conversation Memory → Shared Postgres: stores turns (evidence: `Analytics-Agent/app/services/database.py`)
