# nirdiamant/genai_agents architecture

> Architecture diagram of the GitHub repository nirdiamant/genai_agents, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/nirdiamant/genai_agents
- Repository: https://github.com/nirdiamant/genai_agents

## Overview

This repository is a collection of runnable GenAI-agent tutorials, not one integrated application. A learner chooses a tutorial and follows its example; the collection spans conversational and task-focused agents, LangGraph and multi-agent patterns, human approval, document intake, evaluation, and tool integrations. The sampled standalone examples show MCP price lookup, receipt OCR, and a small Flask page. Notebook internals were not sampled, so their branches are represented as documented learning topics rather than connected into an assumed runtime pipeline.

Main entry points: [`all_agents_tutorials/README.md`](https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/README.md) (Tutorial collection), [`data/grocery_management_agents_system/input/extract_items.js`](https://github.com/nirdiamant/genai_agents/blob/main/data/grocery_management_agents_system/input/extract_items.js) (Receipt OCR), [`all_agents_tutorials/scripts/mcp_server.py`](https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/scripts/mcp_server.py) (MCP price tool), [`data/e2e_testing_agent_app.py`](https://github.com/nirdiamant/genai_agents/blob/main/data/e2e_testing_agent_app.py) (Flask page handler)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_learning["Agent tutorials"]
  node_tutorials["Tutorial collection<br/>[README.md]"]
  node_conversational["Conversational agents"]
  node_task_agents["Task agents"]
end

subgraph group_patterns["Agent patterns"]
  node_agent_graphs["LangGraph agents"]
  node_multi_agent["Multi-agent systems"]
  node_human_approval["Human approval"]
  node_document_intake["Document intake"]
  node_agent_evaluation["Agent evaluation"]
end

subgraph group_examples["Standalone examples"]
  node_mcp_server["MCP price tool<br/>[mcp_server.py]"]
  node_receipt_ocr["Receipt OCR<br/>[extract_items.js]"]
  node_receipt_markdown["Extracted receipt<br/>[grocery_receipt.md]"]
  node_flask_demo["Flask page handler"]
  node_demo_html["Demo registration page"]
end

node_learner(("Learner"))
node_coingecko["CoinGecko API"]
node_llama_ocr["Llama OCR"]

node_learner -->|"explores"| node_tutorials
node_tutorials -->|"includes"| node_conversational
node_tutorials -->|"includes"| node_task_agents
node_tutorials -->|"includes"| node_agent_graphs
node_tutorials -->|"includes"| node_multi_agent
node_tutorials -->|"features"| node_human_approval
node_tutorials -->|"features"| node_document_intake
node_tutorials -->|"features"| node_agent_evaluation
node_mcp_server -->|"requests price"| node_coingecko
node_receipt_ocr -->|"extracts text"| node_llama_ocr
node_receipt_ocr -->|"writes markdown"| node_receipt_markdown
node_flask_demo -->|"reads page"| node_demo_html

click node_tutorials "https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/README.md"
click node_conversational "https://github.com/nirdiamant/genai_agents/tree/main/all_agents_tutorials"
click node_task_agents "https://github.com/nirdiamant/genai_agents/tree/main/all_agents_tutorials"
click node_agent_graphs "https://github.com/nirdiamant/genai_agents/tree/main/all_agents_tutorials"
click node_multi_agent "https://github.com/nirdiamant/genai_agents/tree/main/all_agents_tutorials"
click node_human_approval "https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/human_in_the_loop_approval_agent.ipynb"
click node_document_intake "https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/document_intake_agent_langgraph.ipynb"
click node_agent_evaluation "https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/trace_based_agent_evaluation.ipynb"
click node_mcp_server "https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/scripts/mcp_server.py"
click node_receipt_ocr "https://github.com/nirdiamant/genai_agents/blob/main/data/grocery_management_agents_system/input/extract_items.js"
click node_receipt_markdown "https://github.com/nirdiamant/genai_agents/blob/main/data/grocery_management_agents_system/extracted/grocery_receipt.md"
click node_flask_demo "https://github.com/nirdiamant/genai_agents/blob/main/data/e2e_testing_agent_app.py"
click node_demo_html "https://github.com/nirdiamant/genai_agents/blob/main/data/e2e_testing_agent_register.html"

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_tutorials,node_conversational,node_task_agents toneBlue
class node_agent_graphs,node_multi_agent,node_human_approval,node_document_intake,node_agent_evaluation toneAmber
class node_mcp_server,node_receipt_ocr,node_receipt_markdown,node_flask_demo,node_demo_html,node_coingecko toneMint
class node_learner,node_llama_ocr toneIndigo
```

## Components

### Agent tutorials

- [Tutorial collection](https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/README.md): `all_agents_tutorials/README.md`
- [Conversational agents](https://github.com/nirdiamant/genai_agents/tree/main/all_agents_tutorials): `all_agents_tutorials`
- [Task agents](https://github.com/nirdiamant/genai_agents/tree/main/all_agents_tutorials): `all_agents_tutorials`

### Agent patterns

- [LangGraph agents](https://github.com/nirdiamant/genai_agents/tree/main/all_agents_tutorials): `all_agents_tutorials`
- [Multi-agent systems](https://github.com/nirdiamant/genai_agents/tree/main/all_agents_tutorials): `all_agents_tutorials`
- [Human approval](https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/human_in_the_loop_approval_agent.ipynb): `all_agents_tutorials/human_in_the_loop_approval_agent.ipynb`
- [Document intake](https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/document_intake_agent_langgraph.ipynb): `all_agents_tutorials/document_intake_agent_langgraph.ipynb`
- [Agent evaluation](https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/trace_based_agent_evaluation.ipynb): `all_agents_tutorials/trace_based_agent_evaluation.ipynb`

### Standalone examples

- [MCP price tool](https://github.com/nirdiamant/genai_agents/blob/main/all_agents_tutorials/scripts/mcp_server.py): `all_agents_tutorials/scripts/mcp_server.py`
- [Receipt OCR](https://github.com/nirdiamant/genai_agents/blob/main/data/grocery_management_agents_system/input/extract_items.js): `data/grocery_management_agents_system/input/extract_items.js`
- [Extracted receipt](https://github.com/nirdiamant/genai_agents/blob/main/data/grocery_management_agents_system/extracted/grocery_receipt.md): `data/grocery_management_agents_system/extracted/grocery_receipt.md`
- [Flask page handler](https://github.com/nirdiamant/genai_agents/blob/main/data/e2e_testing_agent_app.py): `data/e2e_testing_agent_app.py`
- [Demo registration page](https://github.com/nirdiamant/genai_agents/blob/main/data/e2e_testing_agent_register.html): `data/e2e_testing_agent_register.html`

### Other components

- **Learner**
- **CoinGecko API**
- **Llama OCR**

## Connections

- Learner → Tutorial collection: explores (evidence: `README.md`)
- Tutorial collection → Conversational agents: includes (evidence: `README.md`)
- Tutorial collection → Task agents: includes (evidence: `README.md`)
- Tutorial collection → LangGraph agents: includes (evidence: `README.md`)
- Tutorial collection → Multi-agent systems: includes (evidence: `README.md`)
- Tutorial collection → Human approval: features (evidence: `README.md`)
- Tutorial collection → Document intake: features (evidence: `README.md`)
- Tutorial collection → Agent evaluation: features (evidence: `README.md`)
- MCP price tool → CoinGecko API: requests price (evidence: `all_agents_tutorials/scripts/mcp_server.py`)
- Receipt OCR → Llama OCR: extracts text (evidence: `data/grocery_management_agents_system/input/extract_items.js`)
- Receipt OCR → Extracted receipt: writes markdown (evidence: `data/grocery_management_agents_system/input/extract_items.js`)
- Flask page handler → Demo registration page: reads page (evidence: `data/e2e_testing_agent_app.py`)
