Reciprocal Rank Fusion (RRF) retriever

An Elasticsearch hybrid-search retriever that combines lexical BM25 scores with vector-search scores. It applies min-max normalization to scale the scores to 0–1 and exposes tunable weights for controlling the contribution of each retrieval method.

Cohere is an enterprise AI company that develops language, speech, translation, embedding, document-parsing, and retrieval models and solutions. Its Rerank model is a retrieval-optimization service that scores and reorders vector-search results so that more relevant items can be selected as context for an answering model. Cohere also offers enterprise deployment options including dedicated, private, on-premises, or isolated-VPC inference.

Ratel is an in-process context-engineering platform for AI agents. It catalogs tools, skills, and persistent facts, then searches the catalog on each turn and progressively discloses only the capabilities relevant to the request instead of placing every tool schema and instruction in the context window. Its retrieval supports BM25, semantic, and hybrid ranking without requiring a vector database. The project includes a Rust core, TypeScript and Python SDKs, an MCP server, and a CLI. Tools can be registered directly or ingested from an MCP server; skills can associate instructions with tools, while registered facts are re-injected when they are no longer fresh in the conversation. The repository describes the system as reducing token usage and mitigating tool overload.

Qdrant is an open-source vector search engine written in Rust for storing vectors with JSON payloads and querying them through an API. It performs vector similarity search using HNSW traversal, applies metadata filters during retrieval, and supports dense, sparse, hybrid, and multivector search, along with reranking methods such as ColBERT and maximum marginal relevance. Qdrant can run on-premises, in hybrid or private deployments, at the edge through Qdrant Edge, or as the fully managed Qdrant Cloud service. The project is used for AI retrieval and supports synchronization between local or edge deployments and cloud-based memory.

elastic-vectorsearch-workshop is a public workshop repository containing instructor guidance, Elasticsearch queries, Python notebooks, corpus data, and agent setup code for practical vector, lexical, hybrid, and reranked search labs. It teaches semantic retrieval with Elasticsearch embeddings, BM25 search, and hybrid retrieval using reciprocal rank fusion and MinMax-normalized linear combinations, including judgment-set evaluation and weight sweeps. Later labs connect the retriever to an LLM and Elastic Agent Builder, demonstrating how retrieval quality affects generated answers, citations, and multi-hop agent workflows. The repository includes five lab notebooks, an Instruqt track, ingestion and validation scripts, and pre-event checks for corpus behavior, inference endpoints, and the workshop environment.