# brocoder07/docuchat---rag-application architecture

> Architecture diagram of the GitHub repository brocoder07/docuchat---rag-application, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-10-29). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/brocoder07/docuchat---rag-application
- Repository: https://github.com/brocoder07/docuchat---rag-application

## Overview

##### Project type and purpose
- This is a full-stack Retrieval-Augmented Generation (RAG) application named DocuChat.
- Purpose: Let users upload multi-format documents, process and store them as embeddings, then query them conversationally via a local LLM.

##### File structure
- Top-level directories:
- src/api      → FastAPI backend (routes, models, services)
- src/frontend → Streamlit UI (components, services, utils)
- src/context, src/document_processor, src/embedding_manager, src/chroma_manager, src/llm_integration, src/rag_pipeline → Core RAG pipeline modules
- data/vector_store → ChromaDB persistence
- scripts → Utility/testing scripts
- config files (.streamlit, src/config.py, src/api/core/config.py)
- Architectural patterns:
- Layered separation: frontend ↔ backend ↔ pipeline ↔ persistence ↔ external LLM
- Modular pipeline stages for chunking, embedding, storage, retrieval, and LLM inference.

##### README insights
- Architecture overview confirms 4 layers:
1. Streamlit UI
2. FastAPI API
3. RAG Pipeline (Document Processor, Embedding Manager, ChromaDB, Ollama LLM)
4. Data store & external service (ChromaDB, Ollama)

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% External User
    User(("User")):::external

    %% Frontend Layer
    subgraph "Streamlit UI"
        direction TB
        App["app.py"]:::frontend
        ChatArea["chat_area.py"]:::frontend
        QuickQuestions["quick_questions.py"]:::frontend
        Sidebar["sidebar.py"]:::frontend
        UploadArea["upload_area.py"]:::frontend
        APIClient["api_client.py"]:::frontend
        Settings["settings.py"]:::config
        SessionState["session_state.py"]:::frontend
    end

    %% API Layer
    subgraph "FastAPI API"
        direction TB
        Main["main.py"]:::api
        ConfigCore["config.py"]:::config
        ChatRoute["chat.py"]:::api
        DebugRoute["debug.py"]:::api
        DocumentsRoute["documents.py"]:::api
        HealthRoute["health.py"]:::api
        Schemas["schemas.py"]:::api
        RagService["rag_service.py"]:::api
    end

    %% RAG Pipeline
    subgraph "RAG Pipeline"
        direction TB
        RAGOrchestrator["rag_pipeline.py"]:::pipeline
        DocumentProcessor["document_processor.py"]:::pipeline
        AdaptiveContext["adaptive_context_builder.py"]:::pipeline
        BoundaryDetector["universal_boundary_detector.py"]:::pipeline
        EmbeddingManager["embedding_manager.py"]:::pipeline
        ChromaManager["chroma_manager.py"]:::pipeline
        LLMIntegration["llm_integration.py"]:::pipeline
    end

    %% Persistence & External
    subgraph "Persistence & External"
        direction TB
        VectorStore[(ChromaDB Storage)]:::storage
        Ollama[(Ollama LLM Server)]:::external
    end

    %% Config & Scripts Side Boxes
    subgraph "Configuration Files"
        direction TB
        FrontendConfig[".streamlit/config.toml"]:::config
        ConfigRoot["config.py"]:::config
    end

    subgraph "Utility & Testing Scripts"
        direction TB
        CheckEnv["check_environment.py"]:::scripts
        ResetChroma["reset_chroma.py"]:::scripts
        TestMigration["test_chroma_migration.py"]:::scripts
        TestEmbeddings["test_embeddings.py"]:::scripts
        TestFullMigration["test_full_migration.py"]:::scripts
    end

    %% Connections
    User -->|"interacts"| App
    App -->|"uses components"| ChatArea
    App --> QuickQuestions
    App --> Sidebar
    App --> UploadArea
    App --> APIClient

    APIClient -->|"HTTP/JSON"| Main
    Main --> ChatRoute
    Main --> DebugRoute
    Main --> DocumentsRoute
    Main --> HealthRoute
    Main --> Schemas
    Main --> RagService

    RagService -->|"invoke pipeline"| RAGOrchestrator
    RAGOrchestrator --> DocumentProcessor
    DocumentProcessor --> AdaptiveContext
    DocumentProcessor --> BoundaryDetector
    RAGOrchestrator --> EmbeddingManager
    EmbeddingManager --> ChromaManager
    ChromaManager --> VectorStore
    RAGOrchestrator --> LLMIntegration
    LLMIntegration --> Ollama
    Ollama -->|response| RAGOrchestrator
    RAGOrchestrator -->|results| RagService
    RagService -->|response| Main
    Main -->|HTTP/JSON| APIClient
    APIClient -->|display results| App

    %% Click Events for Frontend
    click App "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/frontend/app.py"
    click ChatArea "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/frontend/components/chat_area.py"
    click QuickQuestions "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/frontend/components/quick_questions.py"
    click Sidebar "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/frontend/components/sidebar.py"
    click UploadArea "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/frontend/components/upload_area.py"
    click APIClient "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/frontend/services/api_client.py"
    click Settings "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/frontend/config/settings.py"
    click SessionState "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/frontend/utils/session_state.py"

    %% Click Events for API
    click Main "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/api/main.py"
    click ConfigCore "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/api/core/config.py"
    click ChatRoute "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/api/routes/chat.py"
    click DebugRoute "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/api/routes/debug.py"
    click DocumentsRoute "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/api/routes/documents.py"
    click HealthRoute "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/api/routes/health.py"
    click Schemas "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/api/models/schemas.py"
    click RagService "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/api/services/rag_service.py"

    %% Click Events for Pipeline
    click DocumentProcessor "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/document_processor.py"
    click AdaptiveContext "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/context/adaptive_context_builder.py"
    click BoundaryDetector "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/context/universal_boundary_detector.py"
    click EmbeddingManager "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/embedding_manager.py"
    click ChromaManager "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/chroma_manager.py"
    click LLMIntegration "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/llm_integration.py"
    click RAGOrchestrator "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/rag_pipeline.py"

    %% Click Events for Persistence
    click VectorStore "https://github.com/brocoder07/docuchat---rag-application/tree/main/data/vector_store/"

    %% Click Events for Config & Scripts
    click FrontendConfig "https://github.com/brocoder07/docuchat---rag-application/blob/main/.streamlit/config.toml"
    click ConfigRoot "https://github.com/brocoder07/docuchat---rag-application/blob/main/src/config.py"

    click CheckEnv "https://github.com/brocoder07/docuchat---rag-application/blob/main/scripts/check_environment.py"
    click ResetChroma "https://github.com/brocoder07/docuchat---rag-application/blob/main/scripts/reset_chroma.py"
    click TestMigration "https://github.com/brocoder07/docuchat---rag-application/blob/main/scripts/test_chroma_migration.py"
    click TestEmbeddings "https://github.com/brocoder07/docuchat---rag-application/blob/main/scripts/test_embeddings.py"
    click TestFullMigration "https://github.com/brocoder07/docuchat---rag-application/blob/main/scripts/test_full_migration.py"

    %% Styles
    classDef external fill:#dddddd,stroke:#999999,stroke-width:1px
    classDef frontend fill:#cce5ff,stroke:#4d90fe,stroke-width:1px
    classDef api fill:#d4edda,stroke:#28a745,stroke-width:1px
    classDef pipeline fill:#ffe5b4,stroke:#ff8c00,stroke-width:1px
    classDef storage fill:#eeeeee,stroke:#999999,stroke-width:1px,stroke-dasharray: 5 5
    classDef config fill:#f0f0f0,stroke:#666666,stroke-width:1px,stroke-dasharray: 2 2
    classDef scripts fill:#f8d7da,stroke:#dc3545,stroke-width:1px
```
