🤖 LLM Playground:
🌱 Exploring Language Models & Chatbots

Welcome to the LLM Playground repository!🎉
I've documented my step-by-step experiments with LLMs, exploring various frameworks and platforms through practical implementations.

• This repository provides a hands-on collection of practical LLM applications, including chatbots, AI agents, SQL and RAG implementations.
• You'll find examples of model fine-tuning, vector databases, and various LLM integrations using tools like LangChain, CrewAI, and OpenAI more.
• The projects range from basic chatbots to advanced applications using AWS, NVIDIA, and custom agents for specific tasks.

🚨 What You Will Find:

• Practical implementations of LLMs and chatbots
• Integration examples with popular services:
  • OpenAI & ChatGPT
  • Groq (Gemma Models)
  • HuggingFace Models
  • Codellama & Gradio
  • CrewAI Agents
  • NVIDIA NIM
  • AWS Bedrock & SageMaker Integration
• Advanced features like:
  • Vector embeddings & FAISS
  • RAG (Retrieval Augmented Generation)
  • Hybrid Search
  • Database integrations
  • LCEL (LangChain Expression Language)
  • LangGraph implementations

🎯 Key Features:

• Basic to advanced chatbot implementations
• Text summarization and Q&A systems
• Integration with various databases:
  • SQL & SQLite
  • Vector DBs (ChromaDB, FAISS, GraphDB, Pinecone)
  • AstraDB
• Mathematical computing with LLMs
• Hybrid search implementations
• AWS and Cloud integrations
• Graph-based LLM applications
• Agent-based systems:
  • Search Engine Agents
  • RAG Paper QA
  • Multi-agent conversations
• Advanced optimization:
  • Fine-tuning methods
  • Performance optimization

📁 Each project folder contains:

• app.py: Streamlit/Gradio application file
• notebook.ipynb: Detailed Jupyter notebook with explanations
• UI.png: Application screenshot/demo image
• requirements.txt: Project-specific dependencies

⬇️ Installation

To explore these projects locally:

git clone https://github.com/Duygu-Jones/LLM_Playground.git
cd LLM_Playground

🚀 Getting Started

1. Environment Setup

   • Create a .env file in the project root
   • Add your API keys:

     GROQ_API_KEY= "your_groq_api_key"
     OPENAI_API_KEY= "your_openai_api_key"
     

2. Dependencies Installation

   • Global dependencies:

     pip install -r requirements.txt

3. Running Applications

   • Each project can be run independently:

     cd [project_folder]
     streamlit run app.py

   • Open browser at http://localhost:...

🤝 Contributing

Contributions are welcome! If you have improvements or additional examples to share:

1. Fork the repository
2. Create your feature branch
3. Submit a pull request

🌱 About Me

I'm Duygu Jones, a Machine Learning/AI Engineer passionate about LLMs and AI applications.

♻️ Connect with me:

• LinkedIn: Linkedin/duygujones
• Website: duygujones.com
• Kaggle: kaggle.com/duygujones
• GitHub: github.com/Duygu-Jones
• Medium: medium.com/@duygujones

💫 If you find this repository helpful, please give it a ⭐ star!

---

📜 License

This repository is licensed under the MIT License. See the LICENSE file for details.