# AgentBuilder

**Repository Path**: z4rek/agent-builder

## Basic Information

- **Project Name**: AgentBuilder
- **Description**: No description available
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-07-06
- **Last Updated**: 2026-07-07

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Agent Builder

An AI-powered RAG (Retrieval-Augmented Generation) application built with FastAPI, featuring a modular pipeline architecture for building intelligent question-answering systems.

## Overview

Agent Builder is a comprehensive framework for building RAG-based applications. It implements a complete pipeline from data ingestion to agent-based generation, organized into five distinct stages:

- **Stage 01: Ingestion** - Data loading, cleaning, splitting, and storage
- **Stage 02: Retrieval** - Hybrid, keyword, and vector search with reranking
- **Stage 03: Augmentation** - Context building, citation, and query rewriting
- **Stage 04: Generation** - LLM integration with streaming support
- **Stage 05: Agent** - Memory, planning, ReAct, and reflection mechanisms

## Features

- **FastAPI-based REST API** - High-performance async web service
- **Modular Architecture** - Each stage is separated into independent modules
- **In-Memory RAG Service** - Built-in TF-IDF vector search with cosine similarity
- **Complete RAG Pipeline** - From document ingestion to answer generation
- **Health Monitoring** - Built-in health check endpoints
- **Structured Logging** - Request tracing with trace IDs

## Installation

```bash
pip install -r requirements.txt
```

## Running the Application

### Windows
```bash
start.bat
```

### Manual Start
```bash
uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload
```

## API Endpoints

| Method | Endpoint | Description |
|--------|----------|--------------|
| GET | `/health` | Health check |
| POST | `/documents` | Add a new document |
| GET | `/documents` | List all documents |
| DELETE | `/documents` | Clear all documents |
| POST | `/search` | Search documents by query |
| POST | `/ask` | Ask a question (RAG QA) |

## Usage Example

### Add a Document
```bash
curl -X POST "http://localhost:8000/documents" \
  -H "Content-Type: application/json" \
  -d '{"content": "Your document text here", "metadata": {"source": "example"}}'
```

### Search Documents
```bash
curl -X POST "http://localhost:8000/search" \
  -H "Content-Type: application/json" \
  -d '{"query": "your search query", "top_k": 5}'
```

### Ask a Question
```bash
curl -X POST "http://localhost:8000/ask" \
  -H "Content-Type: application/json" \
  -d '{"query": "What is the main topic?", "top_k": 5}'
```

## Project Structure

```
app/
├── config/              # Configuration and settings
│   ├── config.py       # Application settings
│   └── logging_config.py
├── main.py             # FastAPI application entry point
└── testRAG/            # RAG implementation
    ├── router.py       # API routes
    ├── schemas.py      # Pydantic models
    ├── service.py      # RAG service logic
    ├── stage_01_ingestion/    # Data ingestion
    ├── stage_02_retrieval/     # Retrieval
    ├── stage_03_augmentation/ # Augmentation
    ├── stage_04_generation/   # Generation
    └── stage_05_agent/        # Agent
```

## Configuration

Configuration is managed through the `Settings` class in `app/config/config.py`. The application uses environment-based configuration with caching for optimal performance.

## License

See project repository for license information.