Ask a question to get started
Enter to send•Shift+Enter new line
AsyncAzureCosmosDBNoSqlVectorStoreRetriever()
VectorStoreRetriever
Azure Search instance used to find similar documents.
Type of search to perform. Options are "vector", "hybrid", "full_text_ranking", "full_text_search".
Number of documents to return.
Search params. with_embedding: offset_limit: projection_mapping: full_text_rank_filter: where: weights: score_threshold: Minimum relevance threshold for vector_score_threshold and hybrid_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.
Async retriever that uses Azure CosmosDB No Sql Search.
Azure CosmosDB No Sql Search
