MongoDB Vector Database

Use MongoDB as a vector database for your Knowledge Base.

Setup

Follow the instructions in the MongoDB Setup Guide to get connection string

Install MongoDB packages

1uv pip install "pymongo[srv]"

Example

1from kern.agent import Agent
2from kern.knowledge.knowledge import Knowledge
3from kern.vectordb.mongodb import MongoVectorDb
4
5# MongoDB Atlas connection string
6"""
7Example connection strings:
8"mongodb+srv://<username>:<password>@cluster0.mongodb.net/?retryWrites=true&w=majority"
9"mongodb://localhost/?directConnection=true"
10"""
11mdb_connection_string = ""
12
13knowledge_base = Knowledge(
14    vector_db=MongoVectorDb(
15        collection_name="recipes",
16        db_url=mdb_connection_string,
17        wait_until_index_ready_in_seconds=60,
18        wait_after_insert_in_seconds=300
19    ),
20)  # adjust wait_after_insert_in_seconds and wait_until_index_ready_in_seconds to your needs
21
22if __name__ == "__main__":
23    knowledge_base.insert(
24        url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
25    )
26
27    agent = Agent(knowledge=knowledge_base)
28    agent.print_response("How to make Thai curry?", markdown=True)

Async Support ⚡

MongoDB also supports asynchronous operations, enabling concurrency and leading to better performance.

1import asyncio
2
3from kern.agent import Agent
4from kern.knowledge.knowledge import Knowledge
5from kern.vectordb.mongodb import MongoVectorDb
6
7# MongoDB Atlas connection string
8"""
9Example connection strings:
10"mongodb+srv://<username>:<password>@cluster0.mongodb.net/?retryWrites=true&w=majority"
11"mongodb://localhost:27017/kern?authSource=admin"
12"""
13mdb_connection_string = "mongodb+srv://<username>:<password>@cluster0.mongodb.net/?retryWrites=true&w=majority"
14
15knowledge_base = Knowledge(
16    vector_db=MongoVectorDb(
17        collection_name="recipes",
18        db_url=mdb_connection_string,
19    ),
20)
21
22# Create and use the agent
23agent = Agent(knowledge=knowledge_base)
24
25if __name__ == "__main__":
26    # Load knowledge base asynchronously
27    asyncio.run(knowledge_base.ainsert(
28            url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
29        )
30    )
31
32    # Create and use the agent asynchronously
33    asyncio.run(agent.aprint_response("How to make Thai curry?", markdown=True))

Tip

Use aload() and aprint_response() methods with asyncio.run() for non-blocking operations in high-throughput applications.

MongoDB Params

Parameter	Type	Description	Default
`collection_name`	`str`	Name of the MongoDB collection	Required
`name`	`Optional[str]`	Name of the vector database	`None`
`description`	`Optional[str]`	Description of the vector database	`None`
`id`	`Optional[str]`	Unique identifier for the vector database	Auto-generated
`db_url`	`Optional[str]`	MongoDB connection string	`"mongodb://localhost:27017/"`
`database`	`str`	Database name	`"kern"`
`embedder`	`Optional[Embedder]`	Embedder instance for generating embeddings	`OpenAIEmbedder()`
`distance_metric`	`str`	Distance metric for similarity	`Distance.cosine`
`overwrite`	`bool`	Overwrite existing collection and index if True	`False`
`wait_until_index_ready_in_seconds`	`Optional[float]`	Time in seconds to wait until the index is ready	`3`
`wait_after_insert_in_seconds`	`Optional[float]`	Time in seconds to wait after inserting documents	`3`
`max_pool_size`	`int`	Maximum number of connections in the connection pool	`100`
`retry_writes`	`bool`	Whether to retry write operations	`True`
`client`	`Optional[MongoClient]`	An existing MongoClient instance	`None`
`search_index_name`	`Optional[str]`	Name of the search index	`"vector_index_1"`
`cosmos_compatibility`	`Optional[bool]`	Whether to use Azure Cosmos DB MongoDB vCore compatibility mode	`False`
`search_type`	`SearchType`	The search type to use when searching for documents	`SearchType.vector`
`hybrid_vector_weight`	`float`	Default weight for vector search results in hybrid search	`0.5`
`hybrid_keyword_weight`	`float`	Default weight for keyword search results in hybrid search	`0.5`
`hybrid_rank_constant`	`int`	Default rank constant (k) for Reciprocal Rank Fusion in hybrid search	`60`