Rankers
Rankers rank documents by specific criteria using pre-trained models. They're used in query pipelines after retrievers to improve retrieval results.
Available rankers:
- CohereRanker: Ranks documents based on their similarity to the query using Cohere models.
- DeepsetNvidiaRanker: Ranker using Triton models hosted on custom infrastructure for optimal performance.
- FastembedRanker: Uses Fastembed models to rank documents.
- JinaRanker: Uses Jina models to rank documents.
- LostInTheMiddleRanker: Puts the most relevant documents and the beginning and at the end of input for an LLM.
- MetaFieldGroupingRanker: Groups documents based on metadata keys.
- MetaFieldRanker: Ranks documents based on a value of their metadata field.
- NvidiaRanker: Ranks documents using models hosted by NVIDIA.
- SentenceTransformersDiversityRanker: Ranks documents to maximize their diversity.
- TransformersSimilarityRanker: Uses a cross-encoder model to embed both the query and the documents and then rank documents by their similarity to the query.
Updated 4 days ago