1 | Similarity Score Retriever | 559 | 99 | 177 | Sets a similarity score threshold and only returns documents with a score above that threshold. | |
2 | BM 25 | 547 | 47 | 86 | BM25 is a ranking function used to estimate the relevance of documents. | |
3 | Vector Store Retriever | 542 | 96 | 177 | Simplest method, creates text embeddings. | |
4 | Reciprocal Rerank Fusion | 529 | 36 | 68 | Retrieved nodes will be reranked according to the Reciprocal Rerank Fusion. | |
5 | Auto Merging Retriever | 525 | 31 | 59 | Looks at a set of leaf nodes and recursively “merges” subsets of leaf nodes. | |
6 | Multi Query Retriever | 497 | 86 | 173 | Generates multiple queries from one, for complex questions. | |
7 | Knowledge Graph RAG | 489 | 23 | 47 | Knowledge-enabled RAG approach to retrieve information from Knowledge Graph. | |
8 | Contextual Compression Retriever | 467 | 99 | 212 | Extracts most relevant information from documents. | |
9 | Llama Vector Store | 444 | 24 | 54 | Vector stores contain embedding vectors of ingested document chunks. | |
10 | Parent Document Retriever | 438 | 89 | 203 | Indexes multiple chunks, retrieves whole document. | |