Retrievers#
Note
The retriever interface is a generic interface that makes it easy to combine documents with language models. This interface exposes a get_relevant_documents method which takes in a query (a string) and returns a list of documents.
Please see below for a list of all the retrievers supported.
- Arxiv
- AWS Kendra
- Azure Cognitive Search
- ChatGPT Plugin
- Self-querying with Chroma
- Cohere Reranker
- Contextual Compression
- Stringing compressors and document transformers together
- Databerry
- ElasticSearch BM25
- kNN
- Metal
- Pinecone Hybrid Search
- PubMed Retriever
- Self-querying with Qdrant
- Self-querying
- SVM
- TF-IDF
- Time Weighted VectorStore
- VectorStore
- Vespa
- Weaviate Hybrid Search
- Self-querying with Weaviate
- Wikipedia
- Zep