​
代码

from pathlib import Path

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.lancedb import LanceDb

# 下载所有样本简历并获取其路径
downloaded_cv_paths = download_knowledge_filters_sample_data(
    num_files=5, file_extension=SampleDataFileExtension.PDF
)

# 初始化 LanceDB
# 默认情况下，它将数据存储在 /tmp/lancedb
vector_db = LanceDb(
    table_name="recipes",
    uri="tmp/lancedb",  # 您可以将此路径更改为存储其他位置的数据
)

# 步骤 1：使用文档和元数据初始化知识库
# ------------------------------------------------------------------------------
# 在初始化知识库时，我们可以附加将用于过滤的元数据
# 此元数据可以包括用户 ID、文档类型、日期或任何其他属性

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)

# 步骤 2：使用 Agent 通过查询中的过滤器自动查询知识库
# -----------------------------------------------------------------------------------

# 启用智能过滤
agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
    enable_agentic_knowledge_filters=True,
)

# 查询 Jordan Mitchell 的经验和技能，并在查询中包含过滤器，以便 Agent 可以自动拾取它们
agent.print_response(
    "告诉我关于 Jordan Mitchell 的经验和技能，用户 ID 为 jordan_mitchell，文档类型为 cv",
    markdown=True,
)

​
用法

1

安装库

pip install -U agno openai lancedb
2

运行示例

python cookbook/agent_concepts/knowledge/filters/pdf/agentic_filtering.py