Authoritative Sources
The definitions, principles, and practices in this pack are grounded in the following primary and widely recognised sources for building, evaluating, and operating LLM applications. Where a concept has a canonical originator (for example RAG or the Model Context Protocol), the original or maintained reference is cited.
Provider Documentation
- Anthropic - Claude Documentation (prompt engineering, tool use, prompt caching). https://docs.anthropic.com/
- Anthropic - Building Effective Agents (workflows vs agents). https://www.anthropic.com/research/building-effective-agents
- OpenAI - API Documentation (function calling, structured outputs, embeddings). https://platform.openai.com/docs/
- Google - Gemini API Documentation. https://ai.google.dev/gemini-api/docs
- Microsoft - Azure OpenAI Service Documentation. https://learn.microsoft.com/en-us/azure/ai-services/openai/
Standards and Protocols
- Model Context Protocol - Specification and Introduction. https://modelcontextprotocol.io/
- Model Context Protocol - GitHub organisation. https://github.com/modelcontextprotocol
Retrieval-Augmented Generation
- Lewis et al. - Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (original RAG paper). https://arxiv.org/abs/2005.11401
- LangChain - Retrieval and RAG documentation. https://python.langchain.com/docs/concepts/rag/
- LlamaIndex - Documentation (ingestion, indexing, retrieval). https://docs.llamaindex.ai/
Vector Search and Embeddings
- pgvector - open-source vector similarity search for PostgreSQL. https://github.com/pgvector/pgvector
- Sentence-Transformers (SBERT) - embeddings, bi-encoders, and cross-encoder re-rankers. https://www.sbert.net/
- HNSW - Malkov & Yashunin, Efficient and robust approximate nearest neighbor search using HNSW graphs. https://arxiv.org/abs/1603.09320
- Reciprocal Rank Fusion - Cormack et al. (original RRF method). https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf
Evaluation
- RAGAS - Evaluation framework for RAG pipelines. https://docs.ragas.io/
- promptfoo - LLM evaluation and red-teaming tooling. https://www.promptfoo.dev/docs/intro/
- DeepEval - LLM evaluation framework. https://docs.confident-ai.com/
Prompting and Agents
- ReAct - Yao et al., Synergizing Reasoning and Acting in Language Models. https://arxiv.org/abs/2210.03629
- Chain-of-Thought - Wei et al., Chain-of-Thought Prompting Elicits Reasoning in LLMs. https://arxiv.org/abs/2201.11903
- DSPy - Programming, not prompting, foundation models. https://dspy.ai/
Security
- OWASP Top 10 for Large Language Model Applications. https://owasp.org/www-project-top-10-for-large-language-model-applications/
- NIST AI Risk Management Framework. https://www.nist.gov/itl/ai-risk-management-framework