A daily learning journal for hands-on experiments with AI agents and LLMs (Gemini, Groq, etc). For developers interested in agentic workflows, prompt engineering, and automated evaluation.
- Jupyter Notebooks (in
Foundation/): Step-by-step explorations, API usage, and daily progress. - foundation.py: Core logic for chatbot and LLM evaluation.
- Personal chatbot: Example using your own summary and LinkedIn data.
- LLM comparison & evaluation: Run prompts through different models and compare results.
- Clone this repo & install dependencies (
pip install -r requirements.txt). - Add your API keys in a
.envfile:GEMINI_API_KEY=your_gemini_key GROK_API_KEY=your_grok_key - Open any notebook in
Foundation/and start experimenting!
- LLM API integration (Gemini, Groq)
- Agentic prompt chaining
- Automated response evaluation
- Push notification (Pushover) demo
This repo is a personal playground and updated regularly.