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

# Filtering on Weaviate

> Learn how to filter knowledge base searches using Pdf documents with user-specific metadata in Weaviate.

## Code

```python theme={null}
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.weaviate import Distance, VectorIndex, Weaviate

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

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

vector_db = Weaviate(
    collection="recipes",
    vector_index=VectorIndex.HNSW,
    distance=Distance.COSINE,
    local=False,  # Set to False if using Weaviate Cloud and True if using local instance
)

knowledge = Knowledge(
    name="Weaviate Knowledge Base",
    description="A knowledge base for Weaviate",
    vector_db=vector_db,
)

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,
)

```

## Usage

<Steps>
  <Step title="Install libraries">
    ```bash theme={null}
    pip install -U agno weaviate-client openai
    ```
  </Step>

  <Step title="Set environment variables">
    ```bash theme={null}
    export OPENAI_API_KEY=xxx
    ```
  </Step>

  <Step title="Setup Weaviate">
    <CodeGroup>
      ```bash Weaviate Cloud theme={null}
      # 1. Create account at https://console.weaviate.cloud/
      # 2. Create a cluster and copy the "REST endpoint" and "Admin" API Key
      # 3. Set environment variables:
      export WCD_URL="your-cluster-url" 
      export WCD_API_KEY="your-api-key"
      # 4. Set local=False in the code
      ```

      ```bash Local Development theme={null}
      # 1. Install Docker from https://docs.docker.com/get-docker/
      # 2. Run Weaviate locally:
      docker run -d \
          -p 8080:8080 \
          -p 50051:50051 \
          --name weaviate \
          cr.weaviate.io/semitechnologies/weaviate:1.28.4
      # 3. Set local=True in the code
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/knowledge/filters/vector_dbs/filtering_weaviate.py
      ```

      ```bash Windows theme={null}
      python cookbook/knowledge/filters/vector_dbs/filtering_weaviate.py
      ```
    </CodeGroup>
  </Step>
</Steps>