# Essay Writer Agent

An AI-powered agent that helps write well-structured essays based on your provided topic and references from PDF documents.

## Features

- Automated essay planning and research
- PDF document ingestion and vector-based retrieval
- Multi-stage writing process with critiques and revisions
- LangGraph-based agent architecture

## Installation

Clone the repository:

```bash
git clone https://github.com/yourusername/essay-writer-agent.git
cd essay-writer-agent
```

Create a virtual environment and install dependencies:

```bash
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -e .
```

## Configuration

Copy the example environment file and set your variables:

```bash
cp .env.example .env
```

Edit the `.env` file with your API keys and configuration settings.

## Usage

### 1. Add your PDF documents

Place your PDF reference documents in the `documents/` directory.

### 2. Build the vector store

```bash
python -m essay_writer.vector_store.pdf_store build
```

### 3. Run the essay writer agent

```bash
python scripts/run_agent.py --topic "Your essay topic" --max-revisions 3
```

### Using as a library

```python
from essay_writer.agent.graph import create_essay_agent

agent = create_essay_agent()
result = agent.invoke({
    'task': "What is the difference between LangChain and LangSmith",
    'max_revisions': 2
})

print(result['draft'])  # Print the final essay
```

## Development

Run tests:

```bash
pytest
```

## License

MIT