# m270706/agentic-rag-project- architecture

> Architecture diagram of the GitHub repository m270706/agentic-rag-project-, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/m270706/agentic-rag-project-
- Repository: https://github.com/m270706/agentic-rag-project-

## Overview

This is a personal RAG exploration project, with notebooks as its documented product surface; `main.py` currently only prints a greeting. The principal documented workflow is preparing text as chunks and embeddings, then experimenting with agentic retrieval that can double-check before answering. README also identifies Groq and three vector-store options, including a separate Typesense notebook. Notebook internals were not sampled, so connections beyond those explicit README descriptions are shown as unverified rather than asserted as implementation calls.

Main entry points: [`1-agenticrag.ipynb`](https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb) (Agentic RAG), [`notebook/document.ipynb`](https://github.com/m270706/agentic-rag-project-/blob/main/notebook/document.ipynb) (Text Chunking), [`typesense.ipynb`](https://github.com/m270706/agentic-rag-project-/blob/main/typesense.ipynb) (Typesense Experiment), [`data`](https://github.com/m270706/agentic-rag-project-/tree/main/data) (Document Corpus)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_prep["Document Preparation"]
  node_documents["Document Corpus"]
  node_chunking["Text Chunking<br/>[document.ipynb]"]
  node_embeddings["Text Embeddings<br/>[document.ipynb]"]
end

subgraph group_agent["Agentic RAG"]
  node_agentnotebook["Agentic RAG<br/>[1-agenticrag.ipynb]"]
  node_langgraph["LangGraph<br/>[1-agenticrag.ipynb]"]
  node_langchain["LangChain<br/>[1-agenticrag.ipynb]"]
  node_doublecheck["Answer Double-check<br/>[1-agenticrag.ipynb]"]
  node_groq{{"Groq"}}
end

subgraph group_stores["Vector Store Experiments"]
  node_chromadb[("ChromaDB<br/>[1-agenticrag.ipynb]")]
  node_faiss[("FAISS<br/>[1-agenticrag.ipynb]")]
  node_typesense[("Typesense<br/>[typesense.ipynb]")]
  node_typesensenotebook["Typesense Experiment<br/>[typesense.ipynb]"]
end

node_user(("User"))
node_main["Greeting Script<br/>[main.py]"]

node_user -->|"explores preparation"| node_chunking
node_user -->|"runs experiments"| node_agentnotebook
node_user -->|"opens separately"| node_typesensenotebook
node_user -->|"runs script"| node_main
node_documents -.->|"chunks text"| node_chunking
node_chunking -->|"turns into numbers"| node_embeddings
node_agentnotebook -->|"tests agents"| node_langgraph
node_agentnotebook -->|"uses basics"| node_langchain
node_agentnotebook -->|"loops to check"| node_doublecheck
node_doublecheck -->|"revisits work"| node_agentnotebook
node_agentnotebook -.->|"generates answers"| node_groq
node_agentnotebook -.->|"experiments with"| node_chromadb
node_agentnotebook -.->|"experiments with"| node_faiss
node_typesensenotebook -->|"experiments with"| node_typesense

click node_documents "https://github.com/m270706/agentic-rag-project-/tree/main/data"
click node_chunking "https://github.com/m270706/agentic-rag-project-/blob/main/notebook/document.ipynb"
click node_embeddings "https://github.com/m270706/agentic-rag-project-/blob/main/notebook/document.ipynb"
click node_agentnotebook "https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb"
click node_langgraph "https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb"
click node_langchain "https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb"
click node_doublecheck "https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb"
click node_chromadb "https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb"
click node_faiss "https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb"
click node_typesense "https://github.com/m270706/agentic-rag-project-/blob/main/typesense.ipynb"
click node_typesensenotebook "https://github.com/m270706/agentic-rag-project-/blob/main/typesense.ipynb"
click node_main "https://github.com/m270706/agentic-rag-project-/blob/main/main.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_documents,node_chunking,node_embeddings,node_user toneBlue
class node_agentnotebook,node_langgraph,node_langchain,node_doublecheck,node_groq toneAmber
class node_chromadb,node_faiss,node_typesense,node_typesensenotebook toneMint
class node_main toneTeal
```

## Components

### Document Preparation

- [Document Corpus](https://github.com/m270706/agentic-rag-project-/tree/main/data): `data`
- [Text Chunking](https://github.com/m270706/agentic-rag-project-/blob/main/notebook/document.ipynb): `notebook/document.ipynb`
- [Text Embeddings](https://github.com/m270706/agentic-rag-project-/blob/main/notebook/document.ipynb): `notebook/document.ipynb`

### Agentic RAG

- [Agentic RAG](https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb): `1-agenticrag.ipynb`
- [LangGraph](https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb): `1-agenticrag.ipynb`
- [LangChain](https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb): `1-agenticrag.ipynb`
- [Answer Double-check](https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb): `1-agenticrag.ipynb`
- **Groq**

### Vector Store Experiments

- [ChromaDB](https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb): `1-agenticrag.ipynb`
- [FAISS](https://github.com/m270706/agentic-rag-project-/blob/main/1-agenticrag.ipynb): `1-agenticrag.ipynb`
- [Typesense](https://github.com/m270706/agentic-rag-project-/blob/main/typesense.ipynb): `typesense.ipynb`
- [Typesense Experiment](https://github.com/m270706/agentic-rag-project-/blob/main/typesense.ipynb): `typesense.ipynb`

### Other components

- **User**
- [Greeting Script](https://github.com/m270706/agentic-rag-project-/blob/main/main.py): `main.py`

## Connections

- User → Text Chunking: explores preparation (evidence: `README.md`)
- User → Agentic RAG: runs experiments (evidence: `README.md`)
- User → Typesense Experiment: opens separately (evidence: `README.md`)
- User → Greeting Script: runs script (evidence: `README.md`)
- Document Corpus → Text Chunking: chunks text
- Text Chunking → Text Embeddings: turns into numbers (evidence: `README.md`)
- Agentic RAG → LangGraph: tests agents (evidence: `README.md`)
- Agentic RAG → LangChain: uses basics (evidence: `README.md`)
- Agentic RAG → Answer Double-check: loops to check (evidence: `README.md`)
- Answer Double-check → Agentic RAG: revisits work (evidence: `README.md`)
- Agentic RAG → Groq: generates answers (evidence: `README.md`)
- Agentic RAG → ChromaDB: experiments with (evidence: `README.md`)
- Agentic RAG → FAISS: experiments with (evidence: `README.md`)
- Typesense Experiment → Typesense: experiments with (evidence: `README.md`)
