> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Team With Agentic Knowledge Filters

> Demonstrates AI-driven dynamic knowledge filtering for team retrieval.

```python team_with_agentic_knowledge_filters.py theme={null}
"""
Team With Agentic Knowledge Filters
===================================

Demonstrates AI-driven dynamic knowledge filtering for team retrieval.
"""

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.utils.media import (
    SampleDataFileExtension,
    download_knowledge_filters_sample_data,
)
from agno.vectordb.lancedb import LanceDb

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
downloaded_cv_paths = download_knowledge_filters_sample_data(
    num_files=5, file_extension=SampleDataFileExtension.PDF
)

vector_db = LanceDb(
    table_name="recipes",
    uri="tmp/lancedb",
)

knowledge = Knowledge(
    vector_db=vector_db,
)

knowledge.insert_many(
    [
        {
            "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,
            },
        },
    ]
)

# ---------------------------------------------------------------------------
# Create Members
# ---------------------------------------------------------------------------
web_agent = Agent(
    name="Knowledge Search Agent",
    role="Handle knowledge search",
    knowledge=knowledge,
    model=OpenAIResponses(id="gpt-5-mini"),
    instructions=["Always take into account filters"],
)

# ---------------------------------------------------------------------------
# Create Team
# ---------------------------------------------------------------------------
team_with_knowledge = Team(
    name="Team with Knowledge",
    members=[web_agent],
    model=OpenAIResponses(id="gpt-5-mini"),
    knowledge=knowledge,
    show_members_responses=True,
    markdown=True,
    enable_agentic_knowledge_filters=True,
)

# ---------------------------------------------------------------------------
# Run Team
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    team_with_knowledge.print_response(
        "Tell me about Jordan Mitchell's work and experience with user_id as jordan_mitchell"
    )
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno lancedb openai pyarrow pypdf
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `team_with_agentic_knowledge_filters.py`, then run:

    ```bash theme={null}
    python team_with_agentic_knowledge_filters.py
    ```
  </Step>
</Steps>

Full source: [cookbook/03\_teams/05\_knowledge/03\_team\_with\_agentic\_knowledge\_filters.py](https://github.com/agno-agi/agno/blob/main/cookbook/03_teams/05_knowledge/03_team_with_agentic_knowledge_filters.py)