Fonti

Fonti Autorevoli

Le definizioni, le tecniche e le pratiche di questo pack sono ancorate alle seguenti fonti primarie e ampiamente riconosciute. Dove una tecnica ha un ideatore canonico (ad esempio RAG, HNSW o RRF), si cita il paper originale o la documentazione mantenuta.

Paper Fondamentali

  • Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks - Lewis et al., 2020 (arXiv:2005.11401). https://arxiv.org/abs/2005.11401
  • Dense Passage Retrieval for Open-Domain Question Answering - Karpukhin et al., 2020 (arXiv:2004.04906). https://arxiv.org/abs/2004.04906
  • Efficient and robust approximate nearest neighbor search using HNSW graphs - Malkov & Yashunin, 2018 (arXiv:1603.09320). https://arxiv.org/abs/1603.09320
  • Reciprocal Rank Fusion outperforms Condorcet and individual rank learning methods - Cormack et al., 2009 (SIGIR). https://plg.uwaterloo.ca/~gvcormack/cormacksigir09-rrf.pdf
  • Precise Zero-Shot Dense Retrieval without Relevance Labels (HyDE) - Gao et al., 2022 (arXiv:2212.10496). https://arxiv.org/abs/2212.10496
  • Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection - Asai et al., 2023 (arXiv:2310.11511). https://arxiv.org/abs/2310.11511
  • Corrective Retrieval Augmented Generation (CRAG) - Yan et al., 2024 (arXiv:2401.15884). https://arxiv.org/abs/2401.15884
  • From Local to Global: A Graph RAG Approach to Query-Focused Summarization - Edge et al., 2024 (arXiv:2404.16130). https://arxiv.org/abs/2404.16130

Documentazione di Provider e Framework

  • Anthropic - Introducing Contextual Retrieval. https://www.anthropic.com/news/contextual-retrieval
  • Anthropic - Building effective agents. https://www.anthropic.com/engineering/building-effective-agents
  • Anthropic - Model Context Protocol (MCP). https://modelcontextprotocol.io/
  • OpenAI - Guida agli embedding. https://platform.openai.com/docs/guides/embeddings
  • OpenAI - Guida a retrieval e RAG. https://platform.openai.com/docs/guides/retrieval
  • LangChain - Concetti e tutorial RAG. https://python.langchain.com/docs/concepts/rag/
  • LlamaIndex - Documentazione. https://docs.llamaindex.ai/

Retrieval e Vector Store

  • pgvector - ricerca di similarità vettoriale open source per PostgreSQL. https://github.com/pgvector/pgvector
  • Qdrant - Documentazione. https://qdrant.tech/documentation/
  • Weaviate - Documentazione. https://weaviate.io/developers/weaviate
  • Milvus - Documentazione. https://milvus.io/docs
  • Redis - Ricerca vettoriale con RediSearch. https://redis.io/docs/latest/develop/interact/search-and-query/advanced-concepts/vectors/
  • BM25 / Okapi BM25 - panoramica. https://en.wikipedia.org/wiki/Okapi_BM25

Embedding e Re-ranking

  • Sentence-Transformers (SBERT) - Documentazione. https://www.sbert.net/
  • Sentence-Transformers - Cross-Encoders (re-ranking). https://www.sbert.net/examples/applications/cross-encoder/README.html
  • MTEB: Massive Text Embedding Benchmark - Muennighoff et al., 2022 (arXiv:2210.07316). https://arxiv.org/abs/2210.07316

Valutazione

  • RAGAS - Documentazione. https://docs.ragas.io/
  • RAGAS: Automated Evaluation of Retrieval Augmented Generation - Es et al., 2023 (arXiv:2309.15217). https://arxiv.org/abs/2309.15217
  • promptfoo - Documentazione. https://www.promptfoo.dev/docs/intro/
  • DeepEval - Documentazione. https://docs.confident-ai.com/

Sicurezza

  • OWASP Top 10 for Large Language Model Applications. https://owasp.org/www-project-top-10-for-large-language-model-applications/