llm-attachment-validator

KO | EN

gitlite — search

#javascript #hacktoberfest #typescript #golang #go #machine-learning #rust #docker #macos #vue #awesome-list #pytorch #mcp #ios

llm-attachment-validator

(★ 19)

LLM-powered pipeline for parsing .eml files, extracting HTML bodies, classifying email attachments as relevant or irrelevant based solely on HTML context, and evaluating results against ground truth using automated metrics.

llm-attachment-validator 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# LLM Attachment Validator 🚀

A document intelligence pipeline that classifies email attachments from `.eml` files as **relevant** or **irrelevant**, using only the email's HTML body context.

This project demonstrates a **production-style LLM pipeline** for contextual document understanding and evaluation.

The system leverages the **Anthropic Claude API** for contextual reasoning and includes an evaluation module for benchmarking performance against ground truth data.

---

## ✨ Core Features

- **Intelligent Classification**  
  Analyzes email HTML bodies to determine if each attachment is contextually relevant.

- **Pure Contextual Reasoning**  
  Classification relies **exclusively on the email body**, simulating real-world scenarios where attachment metadata is unavailable.

- **Structured Output**  
  Generates clear, machine-readable JSON results for every email processed.

- **Built-in Evaluation**  
  Compare predictions against ground truth data using standard classification metrics:

- Accuracy
  - Precision
  - Recall
  - F1 Score

- **Extensible Design**  
  Modular design allows experimentation with prompts, models, and classification logic.

---

## 🧠 How It Works

The validation process follows strict rules to ensure the focus remains on contextual understanding:

1. **Input**  
   An `.eml` file is provided.

2. **Extraction**

The system extracts:

- The **full HTML body**
   - A **list of attachment filenames**

The system intentionally ignores:

- Attachment content  
   - MIME types  
   - Email headers

3. **Reasoning (Claude API)**

The HTML body and attachment list are sent to the Claude model with a carefully engineered prompt.

The model must infer relevance based **only on the text and structure of the email.**

4. **Decision**

Each attachment is classified as:

- **relevant**
     - Materially referenced
     - Important to the email topic

- **irrelevant**
     - Logos
     - Signature images
     - Decorative elements

5. **Output**

A JSON file is created listing attachments under:

- `relevant`
   - `irrelevant`

---

## 📁 Project Structure

```text
llm-attachment-validator/
│
├── examples/                 # Input .eml files
│   ├── example_00001.eml
│   ├── example_00002.eml
│   └── ...
│
├── ground_truth/             # Ground-truth JSON files
│   ├── attachments_00001.json
│   ├── attachments_00002.json
│   └── ...
│
├── output/                   # Generated classification results
│
├── classify_attachments.py   # Runs attachment classification
├── evaluate.py               # Evaluates predictions vs ground truth
├── requirements.txt          # Python dependencies
└── README.md                 # Project documentation
```

---

## ⚙️ Getting Started

### Prerequisites

- Python 3.9+
- Anthropic API Key

---

### Installation

Clone the repository:

```bash
git clone https://github.com/NikolaPantel/llm-attachment-validator.git
cd llm-attachment-validator
```

Create a virtual environment:

```bash
python -m venv venv
```

Activate environment:

Mac/Linux:

```bash
source venv/bin/activate
```

Windows:

```bash
venv\Scripts\activate
```

Install dependencies:

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

requirements.txt:

```text
anthropic
beautifulsoup4
tqdm
scikit-learn
```

---

### Set API Key

macOS / Linux:

```bash
export ANTHROPIC_API_KEY="your-api-key-here"
```

Windows:

```bash
set ANTHROPIC_API_KEY=your-api-key-here
```

---

## 🚦 Usage

### Classify Attachments

Place `.eml` files in:

```
examples/
```

Run:

```bash
python classify_attachments.py
```

Results are saved in:

```
output/
```

---

### Example Output

`output/attachments_00001.json`

```json
{
  "relevant": [
    "quarterly_report_q1_2026.pdf"
  ],
  "irrelevant": [
    "company_logo.png",
    "email_signature_banner.jpg"
  ]
}
```

---

### Evaluate Performance

Place ground truth files in:

```
ground_truth/
```

Run:

```bash
python evaluate.py
```

Metrics include:

- Accuracy
- Precision
- Recall
- F1 Score

---

## 📊 Project Purpose

This project was built to demonstrate:

- LLM pipeline design
- Prompt engineering
- Email parsing
- Structured output generation
- Evaluation frameworks
- Production-style project organization

---

## 📜 License

---

## 📬 Contact

Nikola Pantel  
GitHub: https://github.com/NikolaPantel

Project Link:

https://github.com/NikolaPantel/llm-attachment-validator

llm-attachment-validator

llm-attachment-validator 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

llm-attachment-validator

llm-attachment-validator 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README