ChatBot with Ollama API

This is a simple Python-based chatbot using the Ollama API and the Qwen 3 1.7B model. The chatbot maintains conversation history and streams responses in real-time.

---

Features

• Interactive command-line chat interface.
• Uses Qwen 3 1.7B model via Ollama.
• Streams responses as the model generates text.
• Maintains full conversation history.
• Easy exit with commands like exit or quit.

---

Requirements

• Python 3.8 or higher
• Ollama Python SDK
• Internet connection (for Ollama API access, if not using local model)

---

Installation

1. Clone the repository:

git clone https://github.com/behshadrhp/ShadBot.git
cd ShadBot

2. Create a virtual environment (optional but recommended):

python -m venv venv
source venv/bin/activate  # Linux/Mac
venv\Scripts\activate     # Windows

3. Install dependencies:

pip install ollama

4. Ensure Ollama CLI is installed and the model qwen3:1.7b is available:

# install ollama in linux
curl -fsSL https://ollama.com/install.sh | sh

# install model
ollama pull qwen3:1.7b

# list of models
ollama list

---

Usage

Run the chatbot script:

python main.py

Then interact in the terminal:

You: Hello!
Bot: Hi there! How can I help you today?

To exit the chatbot, type:

exit

or

quit

---

Code Overview

• history: Stores all messages exchanged between the user and the bot.
• ai_model: Model used (qwen3:1.7b).
• Streaming: Messages from the bot are streamed in real-time for a responsive experience.
• Conversation memory: Appends every user and bot message to history to maintain context.

Key Part of the Script:

response = ollama.chat(
    stream=True,
    model=ai_model,
    messages=history,
    think=False,
)

• stream=True enables real-time streaming.
• think=False disables the "thinking" animation.

---

Contributing

1. Fork the repository.
2. Create a branch (git checkout -b feature-name).
3. Commit your changes (git commit -m 'Add some feature').
4. Push to the branch (git push origin feature-name).
5. Open a pull request.

---

License

This project is licensed under the MIT License.

---

Notes

• Make sure your Ollama CLI is set up correctly before running the script.
• For large conversations, consider limiting history to improve performance.
• This chatbot runs in the terminal and does not include a GUI by default.