Skip to main content

​
Setup

Follow the instructions in the Azure Cosmos DB Setup Guide to get the connection string. Install MongoDB packages: 
pip install "pymongo[srv]"

​
Example

agent_with_knowledge.py
import urllib.parse
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.mongodb import MongoVectorDb

# Azure Cosmos DB MongoDB connection string
"""
Example connection strings:
"mongodb+srv://<username>:<encoded_password>@cluster0.mongocluster.cosmos.azure.com/?tls=true&authMechanism=SCRAM-SHA-256&retrywrites=false&maxIdleTimeMS=120000"
"""
mdb_connection_string = f"mongodb+srv://<username>:<encoded_password>@cluster0.mongocluster.cosmos.azure.com/?tls=true&authMechanism=SCRAM-SHA-256&retrywrites=false&maxIdleTimeMS=120000"

knowledge_base = Knowledge(
    vector_db=MongoVectorDb(
        collection_name="recipes",
        db_url=mdb_connection_string,
        search_index_name="recipes",
        cosmos_compatibility=True,
    ),
)

knowledge.add_content(
    url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
)

# Create and use the agent
agent = Agent(knowledge=knowledge_base)
agent.print_response("How to make Thai curry?", markdown=True)

​
Azure Cosmos DB MongoDB vCore Params

ParameterTypeDescriptionDefault
collection_namestrName of the MongoDB collectionRequired
nameOptional[str]Name of the vector databaseNone
descriptionOptional[str]Description of the vector databaseNone
idOptional[str]Unique identifier for the vector databaseAuto-generated
db_urlOptional[str]MongoDB connection string"mongodb://localhost:27017/"
databasestrDatabase name"agno"
embedderOptional[Embedder]Embedder instance for generating embeddingsOpenAIEmbedder()
distance_metricstrDistance metric for similarityDistance.cosine
overwriteboolOverwrite existing collection and index if TrueFalse
wait_until_index_ready_in_secondsOptional[float]Time in seconds to wait until the index is ready3
wait_after_insert_in_secondsOptional[float]Time in seconds to wait after inserting documents3
max_pool_sizeintMaximum number of connections in the connection pool100
retry_writesboolWhether to retry write operationsTrue
clientOptional[MongoClient]An existing MongoClient instanceNone
search_index_nameOptional[str]Name of the search index"vector_index_1"
cosmos_compatibilityOptional[bool]Whether to use Azure Cosmos DB MongoDB vCore compatibility modeFalse
search_typeSearchTypeThe search type to use when searching for documentsSearchType.vector
hybrid_vector_weightfloatDefault weight for vector search results in hybrid search0.5
hybrid_keyword_weightfloatDefault weight for keyword search results in hybrid search0.5
hybrid_rank_constantintDefault rank constant (k) for Reciprocal Rank Fusion in hybrid search60

​
Developer Resources