使用传统 RAG 进行知识过滤

了解如何使用用户 ID、文档类型和年份等元数据在传统 RAG 中过滤知识。本示例演示了如何设置带筛选器的知识库并进行有效查询。

代码

filtering-traditional-RAG.py

from agno.agent import Agent
from agno.knowledge.text import TextKnowledgeBase
from agno.utils.media import (
    SampleDataFileExtension,
    download_knowledge_filters_sample_data,
)
from agno.vectordb.lancedb import LanceDb

# 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.TXT
)

# 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",  # 您可以更改此路径以将数据存储在其他位置
)

# 步骤 1：使用文档和元数据初始化知识库
knowledge_base = TextKnowledgeBase(
    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：使用不同的过滤器组合查询知识库

# 选项 1：在 Agent 上设置过滤器
agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=False,
    add_references=True,
    knowledge_filters={"user_id": "jordan_mitchell"},
)

# 查询 Jordan Mitchell 的经验和技能
agent.print_response(
    "Tell me about Jordan Mitchell's experience and skills",
    markdown=True,
)

# 选项 2：在 run/print_response 上设置过滤器
# agent = Agent(
#     knowledge=knowledge_base,
#     add_references=True,
#     search_knowledge=False,
# )

# 将 Taylor Brooks 作为候选人进行查询
# agent.print_response(
#     "Tell me about Taylor Brooks as a candidate",
#     knowledge_filters={"user_id": "taylor_brooks"},
#     markdown=True,
# )

用法

1. 安装库

   pip install -U agno lancedb openai
   
2. 运行示例

   Mac

   python filtering-traditional-RAG.py