Filtering on MongoDB

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.utils.media import (
    SampleDataFileExtension,
    download_knowledge_filters_sample_data,
)
from agno.vectordb.mongodb import MongoVectorDb

# Download all sample CVs and get their paths
downloaded_cv_paths = download_knowledge_filters_sample_data(
    num_files=5, file_extension=SampleDataFileExtension.PDF
)

mdb_connection_string = "mongodb+srv://<username>:<password>@cluster0.mongodb.net/?retryWrites=true&w=majority"

# Step 1: Initialize knowledge base with documents and metadata
# ------------------------------------------------------------------------------
# When initializing the knowledge base, we can attach metadata that will be used for filtering
# This metadata can include user IDs, document types, dates, or any other attributes

knowledge = Knowledge(
    name="MongoDB Knowledge Base",
    description="A knowledge base for MongoDB",
    vector_db=MongoVectorDb(
        collection_name="filters",
        db_url=mdb_connection_string,
        search_index_name="filters",
    ),
)

# Load all documents into the vector database
knowledge.add_contents(
    [
        {
            "path": downloaded_cv_paths[0],
            "metadata": {
                "user_id": "jordan_mitchell",
                "document_type": "cv",
                "year": 2025,
            },
        },
        {
            "path": downloaded_cv_paths[1],
            "metadata": {
                "user_id": "taylor_brooks",
                "document_type": "cv",
                "year": 2025,
            },
        },
        {
            "path": downloaded_cv_paths[2],
            "metadata": {
                "user_id": "morgan_lee",
                "document_type": "cv",
                "year": 2025,
            },
        },
        {
            "path": downloaded_cv_paths[3],
            "metadata": {
                "user_id": "casey_jordan",
                "document_type": "cv",
                "year": 2025,
            },
        },
        {
            "path": downloaded_cv_paths[4],
            "metadata": {
                "user_id": "alex_rivera",
                "document_type": "cv",
                "year": 2025,
            },
        },
    ]
)

# Step 2: Query the knowledge base with different filter combinations
# ------------------------------------------------------------------------------

agent = Agent(
    knowledge=knowledge,
    search_knowledge=True,
)

agent.print_response(
    "Tell me about Jordan Mitchell's experience and skills",
    knowledge_filters={"user_id": "jordan_mitchell"},
    markdown=True,
)