# prakhar-pandey28/turium_ai_project architecture

> Architecture diagram of the GitHub repository prakhar-pandey28/turium_ai_project, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-02-11). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/prakhar-pandey28/turium_ai_project
- Repository: https://github.com/prakhar-pandey28/turium_ai_project

## Overview

##### Project Type and Purpose
- This is a full-stack, production-style Retrieval-Augmented Generation (RAG) web application.
- Purpose: let users ingest short text notes or URLs, store them in a vectorized SQLite store, and ask questions against that content via a FastAPI backend and a React+Vite frontend.

##### File Structure
- Top level:
- README.md, .gitignore
- backend/ – Python FastAPI service
- frontend/vite-project/ – React application powered by Vite
- backend/ contains:
- main.py – FastAPI app entrypoint
- chunker.py, embeddings.py, html_parser.py, llm.py, vector.py, db.py – core pipeline modules
- Dockerfile, render.yaml, requirements.txt, runtime.txt – deployment/config
- frontend/vite-project/ contains the standard Vite + React scaffold:
- src/ with App.jsx, main.jsx, style sheets, assets
- index.html, package.json, vite.config.js
- No other microservices—backend monolith handles both ingestion and query.

##### README Insights
- Ingestion pipeline using Jina AI Reader, chunking strategy, and embeddings.
- RAG pipeline using cosine similarity over JSON-serialized vectors in SQLite and Groq LLM API.
- Deployment on Render (backend) and Vercel (frontend).

##### Main Components
a. User / Frontend (React + Vite)
b. Backend (FastAPI monolith)
· Ingestion sub-components: URL fetcher (Jina AI Reader), chunker, embedding client, vector store interface
· Query sub-components: embedding client, vector search, LLM client
c. Data Store: SQLite (vectors stored as JSON blobs plus metadata)
d. External Services:
· Jina AI Reader (url → markdown)
· Jina AI Embeddings API (text chunks → embeddings)
· Groq LLM API (question + context → answer)

##### Relationships and Data Flow
- Frontend ↔ Backend via HTTP/HTTPS (POST /ingest, GET /items, POST /query)
- Ingestion Flow:
1. Frontend posts text or URL → Backend API
2. For URL: HTTP fetch → Jina AI Reader → clean markdown → chunker
3. For text: chunker directly
4. chunker → embeddings API → vectors → store in SQLite
- Query Flow:
1. Frontend posts question → Backend API
2. Backend sends question to embeddings API → query vector
3. In-memory cosine similarity search over SQLite vectors → top-k chunks
4. top-k chunks + question → Groq API → answer → Backend → Frontend

##### Architectural Patterns & Principles
- Layered separation:
- Presentation (React frontend)
- API Layer (FastAPI)
- Pipeline Layer (ingestion vs. query logic)
- Persistence Layer (SQLite)
- Monolith backend with clear module boundaries (chunker, embeddings, vector search, LLM)
- External dependencies abstracted behind thin client modules (embeddings, HTML parsing, LLM)
- Configuration as code: Dockerfile, render.yaml, environment variable examples

## Diagram (Mermaid)

```mermaid
graph TB
    classDef frontendClass fill:#cce5ff,stroke:#333,stroke-width:1px;
    classDef backendClass fill:#d4edda,stroke:#333,stroke-width:1px;
    classDef externalClass fill:#fff3cd,stroke:#333,stroke-width:1px;
    classDef dbClass fill:#e2e3e5,stroke:#333,stroke-width:1px;

    User((User)) 
    User -->|interacts via browser| FE["React+Vite Frontend"]:::frontendClass
    FE -->|HTTP POST /ingest| API["FastAPI API\n(/ingest, /items, /query)"]:::backendClass
    FE -->|HTTP GET /items| API
    FE -->|HTTP POST /query| API

    subgraph "Frontend"
        FE
        FE_main["main.jsx"]:::frontendClass
        FE_app["App.jsx"]:::frontendClass
    end

    subgraph "Backend (FastAPI)"
        API
        subgraph "Ingestion Pipeline"
            HTML["HTML Parser\n(Jina AI Reader wrapper)"]:::backendClass
            Chunker["Chunker\n(800-char windows, 100-char overlap)"]:::backendClass
            EmbClient["Embeddings Client\n(Jina Embeddings API)"]:::backendClass
            VectorStore["Vector Store Interface"]:::backendClass
        end
        subgraph "RAG Pipeline"
            EmbQuery["Embeddings Client\n(Jina Embeddings API)"]:::backendClass
            VectorSearch["Vector Search\n(cosine similarity)"]:::backendClass
            LLM["LLM Client\n(Groq API)"]:::backendClass
        end
        DB["SQLite\n(JSON vectors + metadata)"]:::dbClass
    end

    %% Ingestion Flow
    API -->|ingest request| HTML
    HTML -->|markdown| Chunker
    Chunker -->|text chunks| EmbClient
    EmbClient -->|JSON embeddings| VectorStore
    VectorStore --> DB

    %% Query Flow
    API -->|query request| EmbQuery
    EmbQuery -->|query vector| VectorSearch
    VectorSearch -->|top-k chunks| LLM
    LLM -->|answer| API
    VectorSearch -->|load vectors| DB

    %% External Services
    JAR["Jina AI Reader"]:::externalClass
    JE["Jina Embeddings API"]:::externalClass
    Groq["Groq LLM API"]:::externalClass

    HTML -->|HTTP fetch| JAR
    EmbClient -->|HTTP text→emb| JE
    EmbQuery -->|HTTP text→emb| JE
    LLM -->|HTTP q+ctx→ans| Groq

    %% Click Events
    click FE "https://github.com/prakhar-pandey28/turium_ai_project/tree/main/frontend/vite-project"
    click FE_main "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/frontend/vite-project/src/main.jsx"
    click FE_app "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/frontend/vite-project/src/App.jsx"
    click HTML "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/html_parser.py"
    click Chunker "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/chunker.py"
    click EmbClient "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/embeddings.py"
    click VectorStore "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/vector.py"
    click VectorSearch "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/vector.py"
    click LLM "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/llm.py"
    click API "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/main.py"
    click Dockerfile "https://github.com/prakhar-pandey28/turium_ai_project/tree/main/backend/Dockerfile"
    click render "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/render.yaml"
    click requirements "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/requirements.txt"
    click runtime "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/backend/runtime.txt"
    click viteconfig "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/frontend/vite-project/vite.config.js"
    click package "https://github.com/prakhar-pandey28/turium_ai_project/blob/main/frontend/vite-project/package.json"
```
