MongoDb

Parameter	Type	Default	Description
`collection_name`	`str`	Required	Name of the MongoDB collection to store vectors and metadata
`db_url`	`Optional[str]`	`"mongodb://localhost:27017/"`	MongoDB connection string
`database`	`str`	`"ai"`	Name of the MongoDB database
`embedder`	`Optional[Embedder]`	`OpenAIEmbedder()`	Embedder instance to generate embeddings
`distance_metric`	`str`	`Distance.cosine`	Distance metric to use for similarity search
`overwrite`	`bool`	`False`	Whether to overwrite existing collection and index
`cosmos_compatibility`	`bool`	`False`	Whether to enable support for azure cosmos db mongodb vcore
`wait_until_index_ready_in_seconds`	`Optional[float]`	`None`	Time in seconds to wait until the index is ready
`wait_after_insert_in_seconds`	`Optional[float]`	`None`	Time in seconds to wait after inserting documents
`max_pool_size`	`int`	`100`	Maximum number of connections in the connection pool
`retry_writes`	`bool`	`True`	Whether to retry write operations
`client`	`Optional[MongoClient]`	`None`	An existing MongoClient instance.
`search_index_name`	`str`	`"vector_index_1"`	Name of the search index
`cosmos_compatibility`	`bool`	`False`	Whether to use Azure Cosmos DB Mongovcore compatibility mode.
`search_type`	`str`	`vector`	The search type to use when searching for documents.
`hybrid_vector_weight`	`float`	`0.5`	Default weight for vector search results in hybrid search.
`hybrid_keyword_weight`	`float`	`0.5`	Default weight for keyword search results in hybrid search.
`hybrid_rank_constant`	`int`	`60`	Default rank constant (k) for Reciprocal Rank Fusion in hybrid search. This constant is added to the rank before taking the reciprocal, helping to smooth scores. A common value is 60.

Agno SDK Reference

AgentOS API Reference