---
license: apache-2.0

---


## Installation

To install the necessary dependencies, run:

```bash
pip install huggingface_hub torch transformers datasets argparse
```


### Download the Repository

Use the `huggingface_hub` to download the repository:

```python
from huggingface_hub import snapshot_download

# Download the repository
repo_path = snapshot_download("RobbiePasquale/lightbulb")

print(f"Repository downloaded to: {repo_path}")
```


### 1. Train a Web Search Agent


**Usage:**
```bash
python main_menu.py --task train_agent
```

### 2. Use a Web Search Agent (Inference)

**Description:**  
Utilizes the trained web search agent to process queries, perform web searches, and generate summarized responses.

**Usage:**
```bash
python main_menu.py --task test_agent
```

**Options:**
- **Interactive Mode:**
  ```bash
  python main_menu.py --task test_agent
  ```
- **Single Query Mode:**
  ```bash
  python main_menu.py --task test_agent --query "Your query here"
  ```

### 3. Train Language Model

**Usage:**
```bash
python main_menu.py --task train_llm_world --model_name gpt2 --dataset_name wikitext --num_epochs 5 --batch_size 8 --max_length 256
```

**Key Arguments:**
- `--model_name`: Pretrained model (e.g., `gpt2`, `bert`).
- `--dataset_name`: Dataset from Hugging Face (e.g., `wikitext`).
- `--num_epochs`: Number of training epochs.
- `--batch_size`: Number of samples per batch.
- `--max_length`: Maximum sequence length.

### 4. Inference Using Language Model

**Usage:**
```bash
python main_menu.py --task inference_llm --query "Your query here"
```

### 5. Train World Model

**Description:**  
Develops a comprehensive World Model that encapsulates state representations, dynamics, and prediction networks to simulate and predict state transitions within the Tree of Thought framework.

**Usage:**
```bash
python main_menu.py --task train_world_model --additional_args
```

### 6. Inference with Language World Model

**Usage:**
```bash
python main_menu.py --task inference_world_model --query "Your query here"
```

### 7. Advanced Inference


**Usage:**
```bash
python main_menu.py --task advanced_inference --query "Your complex query here"
```


### Training the World Model

```bash
python main_menu.py --task train_llm_world --model_name gpt2 --dataset_name wikitext --num_epochs 5 --batch_size 8 --max_length 256
```

### Training the Web Search Agent

```bash
python main_menu.py --task train_agent
```

### Use the Web Search Agent in Interactive Mode

```bash
python main_menu.py --task test_agent
```

### Use the Web Search Agent with a Single Query

```bash
python main_menu.py --task test_agent --query "What are the impacts of renewable energy on global sustainability?"
```

### Inference with World Model and Tree of Thought

```bash
python main_menu.py --task advanced_inference --query "Analyze the economic effects of artificial intelligence in the next decade."
```


## Citation

If you use LightBulb in your research, please cite the author:

```
@misc{RobbiePasquale_lightbulb,
  author       = {Robbie Pasquale},
  title        = {LightBulb: An Autonomous Web Search and Language Model Framework},
  year         = {2024},
  publisher    = {Huggingface},
  howpublished = {\url{https://huggingface.co/RobbiePasquale/lightbulb}},
}
```


## License

This project is licensed under the Apache 2.0 License.

---