# vinaymaurya14/langchain_fastapi_agent architecture

> Architecture diagram of the GitHub repository vinaymaurya14/langchain_fastapi_agent, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-14). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/vinaymaurya14/langchain_fastapi_agent
- Repository: https://github.com/vinaymaurya14/langchain_fastapi_agent

## Overview

##### Project Type & Purpose
- This is a small full-stack AI application:
- A FastAPI-based backend (“app/main.py”) exposing REST endpoints for email classification and response generation.
- A Gradio-based frontend (“app.py”) providing a user-friendly web UI.
- A core “agent” module (“app/agent.py”) that uses LangChain and the OpenAI API to do the actual NLP work.

##### Main Components
a. Gradio Frontend (app.py)
- Web UI listening on port 7860.
- Takes raw email text as input, displays classification + generated response.
- Sends HTTP requests to the backend’s `/classify-email/` endpoint.
b. FastAPI Backend (app/main.py)
- Uvicorn server on port 8000.
- Defines `/classify-email/` endpoint.
- Uses Pydantic models (app/models.py) to validate request/response schemas.
c. Core Agent (app/agent.py)
- Encapsulates business logic: constructs LangChain prompts, calls OpenAI via openai-python SDK.
- Returns a structure containing “category” + “response_text.”
d. Configuration (.env)
- Holds `OPENAI_API_KEY`, loaded at startup.
e. External Service
- OpenAI’s REST API for GPT models.

##### Relationships & Data Flow
- User → Gradio UI (HTTP/websocket) →
- Gradio UI → FastAPI Backend (`POST /classify-email/` with email text) →
- FastAPI Controller → Pydantic Model Validation → Agent Service →
- LangChain Wrapper → OpenAI API →
- OpenAI Response → Agent Formats Output → FastAPI Serializes via Pydantic →
- FastAPI → Gradio UI → User

##### Architectural Patterns & Design Principles
- Separation of concerns:
- Presentation layer (Gradio)
- API layer (FastAPI controllers + Pydantic models)
- Service layer (Agent + LangChain)
- Configuration layer (.env)
- Dependency injection of API key into Agent at startup.
- Stateless microservice: no database; each request stands alone.

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% User and Presentation Layer
    User((User))
    UI[/Gradio Frontend/]:::frontend

    %% Backend API Layer
    FastAPI["FastAPI Server\n(app/main.py)"]:::backend
    Models["Pydantic Models\n(app/models.py)"]:::backend
    Init["Package Init\n(app/__init__.py)"]:::backend

    %% Core Service Layer
    Agent["Agent Module\n(app/agent.py)"]:::core
    Env[(.env Config)]:::config

    %% External Service
    OpenAI[(OpenAI API)]:::external

    %% Documentation & Dependencies
    README["Project Docs\n(README.md)"]:::docs
    Req["Dependencies\n(requirements.txt)"]:::docs

    %% Data Flow
    User -->|"opens UI\n(port 7860)"| UI
    UI -->|"POST /classify-email/\n(port 8000)"| FastAPI
    FastAPI -->|"validate via Pydantic"| Models
    FastAPI -->|"invoke Agent"| Agent
    Env -->|"load API key"| Agent
    Agent -->|"HTTPS POST\n(GPT request)"| OpenAI
    OpenAI -->|"response JSON"| Agent
    Agent -->|"format output"| FastAPI
    FastAPI -->|"return JSON"| UI
    UI --> User

    %% Click Events
    click FastAPI "https://github.com/vinaymaurya14/langchain_fastapi_agent/blob/main/app/main.py"
    click Models "https://github.com/vinaymaurya14/langchain_fastapi_agent/blob/main/app/models.py"
    click Agent "https://github.com/vinaymaurya14/langchain_fastapi_agent/blob/main/app/agent.py"
    click Init "https://github.com/vinaymaurya14/langchain_fastapi_agent/blob/main/app/__init__.py"
    click Req "https://github.com/vinaymaurya14/langchain_fastapi_agent/blob/main/requirements.txt"
    click README "https://github.com/vinaymaurya14/langchain_fastapi_agent/blob/main/README.md"

    %% Styles
    classDef frontend fill:#ccffcc,stroke:#009900,color:#000000;
    classDef backend fill:#cce5ff,stroke:#0066cc,color:#000000;
    classDef core fill:#e5ccff,stroke:#9933cc,color:#000000;
    classDef external fill:#ffe5cc,stroke:#cc6600,color:#000000;
    classDef config fill:#ffffcc,stroke:#999900,color:#000000;
    classDef docs fill:#f0f0f0,stroke:#888888,color:#000000;
```
