now.executor.indexer.qdrant.executor module#

class now.executor.indexer.qdrant.executor.NOWQdrantIndexer15(dim, columns=None, metric='cosine', limit=10, traversal_paths='@c', max_values_per_tag=10, *args, **kwargs)[source]#

Bases: now.executor.abstract.base_indexer.base_indexer.NOWBaseIndexer

NOWQdrantIndexer15 indexes Documents into a Qdrant server using DocumentArray with storage=’qdrant’.

  • dim (int) – Dimensionality of vectors to index.

  • columns (Optional[List]) – List of tuples of the form (column_name, str_type). Here str_type must be a string that can be

parsed as a valid Python type. :type metric: str :param metric: Distance metric type. Can be ‘euclidean’, ‘inner_product’, or ‘cosine’ :type limit: int :param limit: Number of results to get for each query document in search :type traversal_paths: str :param traversal_paths: Default traversal paths on docs :type max_values_per_tag: int :param max_values_per_tag: Maximum number of values per tag (used for search), e.g. ‘@r’, ‘@c’, ‘@r,c’


Calls the constructor of the specialized indexer


Iterator which iterates through the documents of self._index and yields batches

convert_filter_syntax(search_filter={}, search_filter_not={})[source]#

Supports exact matches and range filter.

index(docs, parameters, **kwargs)[source]#

Index new documents

delete(documents_to_delete, parameters={}, **kwargs)[source]#

Delete endpoint to delete document/documents from the index. Filter conditions can be passed to select documents for deletion.

search(docs, parameters, limit, search_filter, **kwargs)[source]#

Perform a vector similarity search and retrieve Document matches.

now.executor.indexer.qdrant.executor.setup_qdrant_server(workspace, logger)[source]#