Search private knowledge
Build a RAG knowledge base
Find skills for document ingestion, retrieval, embeddings, knowledge indexing, and grounded answer workflows.
Agent prompt
Find the best skill for building a RAG knowledge base over documents with retrieval, citations, and verification steps.
Best first install
RAG Techniques
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
Install with one command
$ npx skills add NirDiamant/RAG_TechniquesInstall targets
Install this skill in your agent workflow
Copy the registry command or an agent-specific install prompt for Codex, Claude Code, and Cursor.
OpenAgentSkill CLI
Use the registry command when your workflow supports the OpenAgentSkill installer.
$ npx skills add NirDiamant/RAG_TechniquesDecision guide
Use and avoid conditions
Success criteria
- Supports source attribution
- Can test retrieval quality
- Separates ingestion from answer generation
Do not use when
- Source documents are not curated
- Answers require real-time data
- Private data cannot leave the workspace
Alternatives
Compare before installing
USearch
830Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
Meilisearch
828A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
Oceanbase
807The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.
Dingo
806A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.
Examples
801Jupyter Notebooks to help you get hands-on with Pinecone vector databases
Weaviate
792Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.