Leaderboard

RankNameEloVotesTimes TestedDescriptionTrophy
1Similarity Score Retriever55999177Sets a similarity score threshold and only returns documents with a score above that threshold.
2BM 255474786BM25 is a ranking function used to estimate the relevance of documents.
3Vector Store Retriever54296177Simplest method, creates text embeddings.
4Reciprocal Rerank Fusion5293668Retrieved nodes will be reranked according to the Reciprocal Rerank Fusion.
5Auto Merging Retriever5253159Looks at a set of leaf nodes and recursively “merges” subsets of leaf nodes.
6Multi Query Retriever49786173Generates multiple queries from one, for complex questions.
7Knowledge Graph RAG4892347Knowledge-enabled RAG approach to retrieve information from Knowledge Graph.
8Contextual Compression Retriever46799212Extracts most relevant information from documents.
9Llama Vector Store4442454Vector stores contain embedding vectors of ingested document chunks.
10Parent Document Retriever43889203Indexes multiple chunks, retrieves whole document.