Ask a question to get started
Enter to send•Shift+Enter new line
AzureSearchVectorStoreRetriever()
BaseRetriever
Azure Search instance used to find similar documents.
Type of search to perform. Options are "similarity", "hybrid", "semantic_hybrid", "similarity_score_threshold", "hybrid_score_threshold", or "semantic_hybrid_score_threshold".
Number of documents to return.
Search params. score_threshold: Minimum relevance threshold for similarity_score_threshold fetch_k: Amount of documents to pass to MMR algorithm (Default: 20) lambda_mult: Diversity of results returned by MMR; 1 for minimum diversity and 0 for maximum. (Default: 0.5) filter: Filter by document metadata
Validate search type.
Retriever that uses Azure Cognitive Search.
Azure Cognitive Search
