# kaijiezhu11/searchanything architecture

> Architecture diagram of the GitHub repository kaijiezhu11/searchanything, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-11-13). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/kaijiezhu11/searchanything
- Repository: https://github.com/kaijiezhu11/searchanything

## Overview

##### Project type and purpose
- This is a monolithic, full-stack Python application (“SearchAnything”) that provides a local semantic search engine for both text and images. It offers two frontends:
- A command-line interface (anything.py) for inserting, searching, and deleting files.
- A Streamlit web interface (app.py) for friendly, browser-based search.
- It supports ingesting files (pdf, txt, md, jpg, jpeg, png), parsing them into text or raw image data, embedding them via AI models, storing embeddings in a local database, and retrieving nearest neighbors by cosine similarity.

##### File structure
- Top-level scripts:
- anything.py – CLI entry point
- app.py – Streamlit UI entry point
- index.py – likely core orchestration of insert/search
- database.py – database schema and access (SQLite3)
- config.py – model paths, DB paths, hyperparameters
- monitor.py – file-system watcher (planned/partial)
- asr.py – placeholder for audio support (future)
- utils.py – shared helpers (logging, file I/O)
- test.py – simple smoke tests
- process/ (parsing pipeline):
- parser_base.py – abstract parser interface
- pdfparser.py, mdparser.py, txtparser.py – text extraction
- imgparser.py – image loading/preprocessing
- docparser.py – orchestrator calling the specific parser
- tools/search4files.py – helper to locate files on disk
- env.yaml – Conda environment spec

##### README for insights
- Two-step architecture:
a. Embedding: transforms each document or image into a fixed-size vector using sentence-transformers (all-mpnet-base-v2 for text, clip-ViT-B-32 for images).
b. Save & Retrieve: store embeddings + metadata in SQLite; at search time embed the query, compute cosine similarity against stored embeddings, and return top matches.
- Emphasizes running fully locally for privacy.

1. User Interfaces
– CLI (anything.py)
– Web UI (app.py / Streamlit)
2. Core Service / Orchestrator (index.py, monitor.py)
3. Parser Pipeline (process/)
4. Embedding Service (sentence-transformers models)
5. Database (SQLite3)
6. File System (raw documents & images)
7. External Dependencies (NLTK, sentence-transformers, Streamlit)
- UI → Core Service: user issues “insert”/“search” commands
- Core Service → Parser Pipeline: load file(s) from File System
- Parser Pipeline → Embedding Service: extracted text/image → model → embedding vector
- Embedding Service → Database: insert (filepath, metadata, vector)
- On search: Core Service → Embedding Service: embed query → vector
- Core Service → Database: fetch all embeddings → compute cosine similarity → filter & sort
- Core Service → UI: return ranked results
- Monitor → Core Service: file‐system events trigger auto‐insert/delete (future)
c. Architectural patterns & design principles:
– Pipeline pattern (parse → embed → store/retrieve)
– Separation of concerns (UI, orchestration, parsing, embedding, persistence)
– Modular plugin style for parsers (parser_base + concrete parsers)
d. Key technologies & libraries:
– Python 3.x, Conda env
– sentence-transformers (all-mpnet-base-v2, clip-ViT-B-32)
– SQLite3 (database.py)
– Streamlit (app.py)
– NLTK (punkt tokenizer)
– Watchdog or custom logic (monitor.py)

##### Detail
- Parser_base → individual parsers relationship (inheritance/plugin).
- That index.py calls database.py and utils.py.
- Config.py feeding settings into Core Service and Embedding Service.

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% User Interfaces
    subgraph "User Interfaces"
        CLI["CLI Interface\n(anything.py)"]:::ui
        WebUI["Streamlit Web UI\n(app.py)"]:::ui
    end

    %% Core and Supporting Modules
    Config["Configuration\n(config.py)"]:::core
    Core["Core Service\n(index.py)"]:::core
    Monitor["File-System Monitor\n(monitor.py)"]:::core
    SearchTool["File Locator Tool\n(tools/search4files.py)"]:::core
    Utils["Utils\n(utils.py)"]:::core
    Test["Test Harness\n(test.py)"]:::core

    %% Parser Pipeline
    subgraph "Parser Pipeline" 
        direction TB
        Base["Base Parser Interface\n(parser_base.py)"]:::pipeline
        DocParser["Document Orchestrator\n(docparser.py)"]:::pipeline
        PDF["PDF Parser\n(pdfparser.py)"]:::pipeline
        MD["Markdown Parser\n(mdparser.py)"]:::pipeline
        TXT["Text Parser\n(txtparser.py)"]:::pipeline
        PPT["PowerPoint Parser\n(pptparser.py)"]:::pipeline
        IMG["Image Parser\n(imgparser.py)"]:::pipeline
    end

    %% Embedding and Persistence
    Embed["Embedding Service\n(sentence-transformers)"]:::external
    DB[("SQLite Database\n(database.py)")]:::persistence
    FS["File System\n(Raw Documents & Images)"]:::persistence

    %% Environment and External Dependencies
    Env["Environment Spec\n(env.yaml)"]:::external
    subgraph "External Dependencies"
        direction TB
        ST["Streamlit"]:::external
        NLTK["NLTK"]:::external
        Watchdog["Watchdog"]:::external
    end

    %% Data Flows
    CLI -->|"commands"| Core
    WebUI -->|"requests"| Core
    Monitor -->|"file events"| Core
    SearchTool -->|"locate files"| FS

    Core -->|"load config"| Config
    Config --> Core
    Config --> Embed

    Core -->|"use utils"| Utils
    Core -->|"invoke parser"| DocParser
    FS --> DocParser

    DocParser --> PDF
    DocParser --> MD
    DocParser --> TXT
    DocParser --> PPT
    DocParser --> IMG

    DocParser -->|"parsed text/image"| Embed
    Embed -->|"vectors"| DB

    Core -->|"embed query"| Embed
    Core -->|"query embeddings"| DB
    Core -->|"return results"| CLI
    Core -->|"return results"| WebUI

    ST --> WebUI
    NLTK --> DocParser
    Watchdog --> Monitor
    FS --> Monitor

    Test -->|"runs on"| Core
    Env -->|"defines deps"| Core

    %% Click Events
    click CLI "https://github.com/kaijiezhu11/searchanything/blob/main/anything.py"
    click WebUI "https://github.com/kaijiezhu11/searchanything/blob/main/app.py"
    click Core "https://github.com/kaijiezhu11/searchanything/blob/main/index.py"
    click Monitor "https://github.com/kaijiezhu11/searchanything/blob/main/monitor.py"
    click SearchTool "https://github.com/kaijiezhu11/searchanything/blob/main/tools/search4files.py"
    click Utils "https://github.com/kaijiezhu11/searchanything/blob/main/utils.py"
    click Test "https://github.com/kaijiezhu11/searchanything/blob/main/test.py"
    click Config "https://github.com/kaijiezhu11/searchanything/blob/main/config.py"
    click Base "https://github.com/kaijiezhu11/searchanything/blob/main/process/parser_base.py"
    click DocParser "https://github.com/kaijiezhu11/searchanything/blob/main/process/docparser.py"
    click PDF "https://github.com/kaijiezhu11/searchanything/blob/main/process/pdfparser.py"
    click MD "https://github.com/kaijiezhu11/searchanything/blob/main/process/mdparser.py"
    click TXT "https://github.com/kaijiezhu11/searchanything/blob/main/process/txtparser.py"
    click PPT "https://github.com/kaijiezhu11/searchanything/blob/main/process/pptparser.py"
    click IMG "https://github.com/kaijiezhu11/searchanything/blob/main/process/imgparser.py"
    click DB "https://github.com/kaijiezhu11/searchanything/blob/main/database.py"
    click Env "https://github.com/kaijiezhu11/searchanything/blob/main/env.yaml"

    %% Styles
    classDef ui fill:#D6EAF8,stroke:#3498DB,color:#154360;
    classDef core fill:#D5F5E3,stroke:#27AE60,color:#1E8449;
    classDef pipeline fill:#FDEDEC,stroke:#E74C3C,color:#922B21;
    classDef persistence fill:#F4F6F7,stroke:#BDC3C7,color:#566573;
    classDef external fill:#F5EEF8,stroke:#9B59B6,color:#6C3483;
```
