PgVector 混合搜索

代码

from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.models.openai import OpenAIChat
from agno.vectordb.pgvector import PgVector, SearchType

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=PgVector(
        table_name="recipes", db_url=db_url, search_type=SearchType.hybrid
    ),
)
# 加载知识库：首次运行时注释掉此行
knowledge_base.load(recreate=False)

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    knowledge=knowledge_base,
    search_knowledge=True,
    read_chat_history=True,
    markdown=True,
)
agent.print_response(
    "How do I make chicken and galangal in coconut milk soup", stream=True
)
agent.print_response("What was my last question?", stream=True)

使用方法

1. 创建虚拟环境

   打开 Terminal 并创建一个 python 虚拟环境。

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. 设置您的 API 密钥

   export OPENAI_API_KEY=xxx
   
3. 安装库

   pip install -U pgvector pypdf "psycopg[binary]" sqlalchemy openai agno
   
4. 运行 PgVector

   ./cookbook/scripts/run_pgvector.sh
   
5. 运行 Agent

   Mac

   python cookbook/agent_concepts/hybrid_search/pgvector/agent.py