Applied LLMs
Putting language models to work: retrieval, prompting, evaluation and the behavior you only learn in production.
Best notes
Reports
Case studies
Writing
Research notes
- How to use Claude to build the system prompt
- Prompt formula
- Mental models for prompting
- Natural language to database queries: Text-to-MongoDB
- Model selection
- Evaluation guidelines for LLM applications
- Prevent prompt injection
- Evaluating caching in RAG systems
Show all 48 notes
- Evaluating search engine in RAG systems
- Streamlining internal tool development with managed LLMOps: A Dify case study
- Thumbs up and thumbs down pattern
- Design feedback mechanism for LLM applications
- A grand unified theory of the AI hype cycle
- Select vector database for LLM
- LSTM
- Quantization for large language models
- GraphRAG - building a knowledge graph for RAG system
- Guardrails in llm
- ReAct(reason + act) in LLM
- ReWOO: Reasoning without observation - a deeper look
- Logging
- Metrics
- Observability in AI platforms
- Tracing
- Intent classification by LLM
- LLM as a judge
- Use cases for LLM applications
- The rise of AI applications with LLM
- Journey of thought prompting: Harnessing AI to craft better prompts
- LLM tracing in AI system
- What is Generative UI?
- Re-ranking in RAG
- RAPTOR: Tree-based retrieval for language models
- Proximal policy optimization
- Multimodal: in rag
- How to talk to ChatGPT effectively
- History of structured outputs for LLMs
- Developing rapidly with generative AI
- Story map for LLMs
- Adversarial prompting in prompt engineering
- Chunking strategies to overcome context limitation in LLM
- Storing long-term memory in ChatGPT using VectorDB
- LLM's accuracy - self refinement
- Reward model
- Q learning
- Query caching for large language models
- Introduction to reinforcement learning and its application with LLMs
- Foundation models: the latest advancement in AI
Playbooks
Tags in this topic
ai86, llm69, prompt6, rag5, vector-database5, feedback4, machine-learning4, observability4, craftsmanship3, evaluation3, pillar3, reinforcement-learning3
Writers
zlatanpham11, nnhuyhoang10, datnguyennnx9, monotykamary9, tieubao8, thanhpn5, innnotruong2, lmquang2