Retrievers
Retrievers fetch documents relvant to the query from the document store. They're used in query pipelines.
When given a query, a retriever sifts through the documents in the document store, scores each documents for its relevance to the query, and returns top candidates.
Retriever and document store are tightly coupled. When configuring a retriever, you must always specify and configure the document store.
For more information about Retrievers, see Haystack documentation.
Available retrievers:
| Retriever | Compatible document store | Description |
|---|---|---|
| DeepsetSnowflakeRetriever | Snowflake | Connects to your Snowflake database to retrieve the table related to user query. |
| FilterRetriever Parameters | Any | Retrieves all documents that match given filters, for example specific metadata field values. |
| OpenSearchBM25Retriever | OpenSearch | A keyword retriever that looks for keywords shared between the documents and the query. |
| OpenSearchEmbeddingRetriever | OpenSearch | A vector retriever that compares query and document embeddings and returns documents that are most similar to the query. |
| SentenceWindowRetrieval | Any | A retriever that enhances context by retrieving surrounding documents. Meant to be used with other retrievers. |
Updated about 1 month ago