# erikhenning927/engineering_ai architecture

> Architecture diagram of the GitHub repository erikhenning927/engineering_ai, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/erikhenning927/engineering_ai
- Repository: https://github.com/erikhenning927/engineering_ai

## Overview

This repository combines an AI commerce API, an asynchronous recommendation worker, and a separate RAG product-intelligence service. The main workflow accepts a query, checks safety and intent, and queues recommendation work; the worker processes the task and persists its result. Separately, the RAG API indexes products from a SQL Server warehouse into Qdrant and exposes similarity search and LLM-backed answers. Some worker and RAG internals are unsampled, so those relationships are included only where the source index or excerpts support them.

Main entry points: [`microservice-ai/src/rag/service.py`](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/service.py) (Product RAG Service), [`worker-recommendation/app/main.py`](https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/main.py) (Task Consumer), [`microservice-ai/src/database.py`](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/database.py) (Warehouse Connection), [`microservice-ai/src/main.py`](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/main.py) (RAG API)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_gateway["Request Orchestration"]
  node_core_routes["Orchestration API<br/>[routes.py]"]
  node_orchestrator["Safety and Intent<br/>[orchestrator.py]"]
  node_producer["Kafka Producer<br/>[kafka_producer.py]"]
end

subgraph group_worker["Recommendation Worker"]
  node_worker_main["Task Consumer<br/>[main.py]"]
  node_product_agent["Product Agent<br/>[product_agent.py]"]
  node_worker_qdrant_client["Vector Search Client<br/>[qdrant_client.py]"]
  node_postgres_client["Result Writer<br/>[postgres_client.py]"]
end

subgraph group_rag["RAG Intelligence"]
  node_rag_main["RAG API<br/>[main.py]"]
  node_rag_router["RAG Endpoints<br/>[router.py]"]
  node_rag_service["Product RAG Service<br/>[service.py]"]
  node_rag_embeddings["Embedding Generation<br/>[embeddings.py]"]
  node_rag_prompts["Prompt Builder<br/>[prompts.py]"]
  node_rag_repository["Product Repository<br/>[repository.py]"]
  node_rag_utils["RAG Utilities<br/>[utils.py]"]
  node_schema_dict["Schema Definitions<br/>[schema_dict.py]"]
  node_qdrant_client["RAG Vector Client<br/>[qdrant_client.py]"]
end

subgraph group_storage["Data Stores"]
  node_task_results[("Task Results<br/>[models.py]")]
  node_rag_db["Warehouse Connection<br/>[database.py]"]
  node_warehouse[("SQL Server Warehouse")]
  node_qdrant[("Qdrant")]
end

node_user(("User"))
node_topic["Product Tasks"]
node_openai["OpenAI API"]
node_kafka["Kafka Broker"]

node_user -->|"submits query"| node_core_routes
node_core_routes -->|"invokes"| node_orchestrator
node_orchestrator -->|"publishes task"| node_producer
node_producer -.->|"sends message"| node_kafka
node_kafka -.->|"routes task"| node_topic
node_topic -.->|"delivers task"| node_worker_main
node_worker_main -->|"processes query"| node_product_agent
node_worker_main -->|"saves result"| node_postgres_client
node_postgres_client -->|"creates record"| node_task_results
node_product_agent -.->|"searches products"| node_worker_qdrant_client
node_worker_qdrant_client -.->|"queries vectors"| node_qdrant
node_rag_main -->|"initializes connection"| node_rag_db
node_rag_main -->|"registers routes"| node_rag_router
node_rag_router -->|"calls operations"| node_rag_service
node_rag_service -->|"generates embeddings"| node_rag_embeddings
node_rag_service -->|"builds prompt"| node_rag_prompts
node_rag_service -->|"loads product data"| node_rag_repository
node_rag_service -->|"extracts response data"| node_rag_utils
node_rag_service -->|"searches and indexes"| node_qdrant_client
node_rag_service -->|"requests completion"| node_openai
node_rag_repository -->|"uses connection"| node_rag_db
node_rag_db -->|"connects"| node_warehouse
node_qdrant_client -->|"stores vectors"| node_qdrant

click node_core_routes "https://github.com/erikhenning927/engineering_ai/blob/main/core-api/app/api/routes.py"
click node_orchestrator "https://github.com/erikhenning927/engineering_ai/blob/main/core-api/app/agent/orchestrator.py"
click node_producer "https://github.com/erikhenning927/engineering_ai/blob/main/core-api/app/services/kafka_producer.py"
click node_worker_main "https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/main.py"
click node_product_agent "https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/agent/product_agent.py"
click node_worker_qdrant_client "https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/db/qdrant_client.py"
click node_postgres_client "https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/db/postgres_client.py"
click node_task_results "https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/db/models.py"
click node_rag_main "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/main.py"
click node_rag_router "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/router.py"
click node_rag_service "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/service.py"
click node_rag_embeddings "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/embeddings.py"
click node_rag_prompts "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/prompts.py"
click node_rag_repository "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/repository.py"
click node_rag_utils "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/utils.py"
click node_schema_dict "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/schema_dict.py"
click node_rag_db "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/database.py"
click node_qdrant_client "https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/qdrant_client.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_core_routes,node_orchestrator,node_producer,node_user toneBlue
class node_worker_main,node_product_agent,node_worker_qdrant_client,node_postgres_client toneAmber
class node_rag_main,node_rag_router,node_rag_service,node_rag_embeddings,node_rag_prompts,node_rag_repository,node_rag_utils,node_schema_dict,node_qdrant_client,node_openai toneMint
class node_task_results,node_rag_db,node_warehouse,node_qdrant,node_topic toneRose
class node_kafka toneIndigo
```

## Components

### Request Orchestration

- [Orchestration API](https://github.com/erikhenning927/engineering_ai/blob/main/core-api/app/api/routes.py): `core-api/app/api/routes.py`
- [Safety and Intent](https://github.com/erikhenning927/engineering_ai/blob/main/core-api/app/agent/orchestrator.py): `core-api/app/agent/orchestrator.py`
- [Kafka Producer](https://github.com/erikhenning927/engineering_ai/blob/main/core-api/app/services/kafka_producer.py): `core-api/app/services/kafka_producer.py`

### Recommendation Worker

- [Task Consumer](https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/main.py): `worker-recommendation/app/main.py`
- [Product Agent](https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/agent/product_agent.py): `worker-recommendation/app/agent/product_agent.py`
- [Vector Search Client](https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/db/qdrant_client.py): `worker-recommendation/app/db/qdrant_client.py`
- [Result Writer](https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/db/postgres_client.py): `worker-recommendation/app/db/postgres_client.py`

### RAG Intelligence

- [RAG API](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/main.py): `microservice-ai/src/main.py`
- [RAG Endpoints](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/router.py): `microservice-ai/src/rag/router.py`
- [Product RAG Service](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/service.py): `microservice-ai/src/rag/service.py`
- [Embedding Generation](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/embeddings.py): `microservice-ai/src/rag/embeddings.py`
- [Prompt Builder](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/prompts.py): `microservice-ai/src/rag/prompts.py`
- [Product Repository](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/repository.py): `microservice-ai/src/rag/repository.py`
- [RAG Utilities](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/utils.py): `microservice-ai/src/rag/utils.py`
- [Schema Definitions](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/schema_dict.py): `microservice-ai/src/rag/schema_dict.py`
- [RAG Vector Client](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/rag/qdrant_client.py): `microservice-ai/src/rag/qdrant_client.py`

### Data Stores

- [Task Results](https://github.com/erikhenning927/engineering_ai/blob/main/worker-recommendation/app/db/models.py): `worker-recommendation/app/db/models.py`
- [Warehouse Connection](https://github.com/erikhenning927/engineering_ai/blob/main/microservice-ai/src/database.py): `microservice-ai/src/database.py`
- **SQL Server Warehouse**
- **Qdrant**

### Other components

- **User**
- **Product Tasks**
- **OpenAI API**
- **Kafka Broker**

## Connections

- User → Orchestration API: submits query (evidence: `core-api/app/api/routes.py`)
- Orchestration API → Safety and Intent: invokes (evidence: `core-api/app/api/routes.py`)
- Safety and Intent → Kafka Producer: publishes task (evidence: `core-api/app/agent/orchestrator.py`)
- Kafka Producer → Kafka Broker: sends message
- Kafka Broker → Product Tasks: routes task
- Product Tasks → Task Consumer: delivers task
- Task Consumer → Product Agent: processes query (evidence: `worker-recommendation/app/main.py`)
- Task Consumer → Result Writer: saves result (evidence: `worker-recommendation/app/main.py`)
- Result Writer → Task Results: creates record (evidence: `worker-recommendation/app/db/postgres_client.py`)
- Product Agent → Vector Search Client: searches products (evidence: `worker-recommendation/app/agent/product_agent.py`)
- Vector Search Client → Qdrant: queries vectors
- RAG API → Warehouse Connection: initializes connection (evidence: `microservice-ai/src/main.py`)
- RAG API → RAG Endpoints: registers routes (evidence: `microservice-ai/src/main.py`)
- RAG Endpoints → Product RAG Service: calls operations (evidence: `microservice-ai/src/rag/router.py`)
- Product RAG Service → Embedding Generation: generates embeddings (evidence: `microservice-ai/src/rag/service.py`)
- Product RAG Service → Prompt Builder: builds prompt (evidence: `microservice-ai/src/rag/service.py`)
- Product RAG Service → Product Repository: loads product data (evidence: `microservice-ai/src/rag/service.py`)
- Product RAG Service → RAG Utilities: extracts response data (evidence: `microservice-ai/src/rag/service.py`)
- Product RAG Service → RAG Vector Client: searches and indexes (evidence: `microservice-ai/src/rag/service.py`)
- Product RAG Service → OpenAI API: requests completion (evidence: `microservice-ai/src/rag/service.py`)
- Product Repository → Warehouse Connection: uses connection (evidence: `microservice-ai/src/rag/repository.py`)
- Warehouse Connection → SQL Server Warehouse: connects (evidence: `microservice-ai/src/database.py`)
- RAG Vector Client → Qdrant: stores vectors (evidence: `microservice-ai/src/rag/qdrant_client.py`)
