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

# 在 Pinecone 中进行过滤

> 了解如何使用用户特定的元数据通过 PDF 文档在 Pinecone 中过滤知识库搜索。

## 代码

```python theme={null}
from os import getenv

from agno.agent import Agent
from agno.knowledge.pdf import PDFKnowledgeBase
from agno.utils.media import (
    SampleDataFileExtension,
    download_knowledge_filters_sample_data,
)
from agno.vectordb.pineconedb import PineconeDb

# 下载所有示例简历并获取其路径
downloaded_cv_paths = download_knowledge_filters_sample_data(
    num_files=5, file_extension=SampleDataFileExtension.PDF
)

# 初始化 Pinecone
api_key = getenv("PINECONE_API_KEY")
index_name = "thai-recipe-index"

vector_db = PineconeDb(
    name=index_name,
    dimension=1536,
    metric="cosine",
    spec={"serverless": {"cloud": "aws", "region": "us-east-1"}},
    api_key=api_key,
)


# 步骤 1：使用文档和元数据初始化知识库
knowledge_base = PDFKnowledgeBase(
    path=[
        {
            "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,
            },
        },
    ],
    vector_db=vector_db,
)

# 将所有文档加载到向量数据库中
knowledge_base.load(recreate=True, upsert=True)

# 步骤 2：使用不同的过滤组合查询知识库
# ------------------------------------------------------------------------------

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

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

## 用法

<Steps>
  <Step title="安装库">
    ```bash theme={null}
    pip install -U agno pinecone pinecone-text openai
    ```
  </Step>

  <Step title="运行示例">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/agent_concepts/knowledge/filters/filtering_pinecone.py
      ```

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