Foundations
- A Grand Unified Theory of the AI Hype Cycle
- Foundation Model
- Model Context Protocol
- Model Selection
- Quantization in LLM
Prompt Engineering
- Adversarial Prompting
- Easy Prompt Engineering For Business Use And Mitigating Risks In Llms
- How to Talk to ChatGPT Effectively
- Journey of Thought Prompting
Model Training & Fine-tuning
- Exploring Machine Learning Approaches For Fine Tuning Llama Models
- RLHF with Open Assistant
- Reinforcement Learning
- Reward Model
- Proximal Policy Optimization
- Q Learning
Retrieval & Caching
- Caching with RAG System
- Chunking Strategies to Overcome Context Limitation in LLM
- Dealing with Long-Term Memory in AI Chatbot
- Hybrid Search
- Raptor LLM Retrieval
- Re-ranking in RAG
- LLM Query Caching
- Select Vector Database for LLM
- Multimodal in RAG
- Workaround with OpenAI's Token Limit with Langchain
- Working with Langchain Document Loaders
Evaluation & Metrics
- Evaluation Guideline for LLM Application
- LLM as a Judge
- Feedback Mechanism
- Logs Pillar
- Metric Pillar
- Observability in AI Platforms
- Trace Pillar
- Thumbs Up and Thumbs Down Pattern
AI Agents & Workflows
- Building Agent Supervisors to Generate Insights
- Multi-agent Collaboration for Task Completion
- ReAct (Reason + Act) in LLM
- ReWOO in LLM
- Function Calling
- Supervisor AI Agents
