Agentic RAG with Reranking

Code

from agno.agent import Agent
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reranker import CohereReranker
from agno.models.openai import OpenAIChat
from agno.vectordb.lancedb import LanceDb, SearchType

knowledge = Knowledge(
    vector_db=LanceDb(
        uri="tmp/lancedb",
        table_name="agno_docs",
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(
            id="text-embedding-3-small"
        ),
        reranker=CohereReranker(
            model="rerank-multilingual-v3.0"
        ),
    ),
)

knowledge.add_content(
    name="Agno Docs", url="https://docs.agno.com/introduction.md"
)

agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    knowledge=knowledge,
    markdown=True,
)

if __name__ == "__main__":
    # Load the knowledge base, comment after first run
    # agent.knowledge.load(recreate=True)
    agent.print_response("What are Agno's key features?")

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Set your API keys

   export OPENAI_API_KEY=xxx
   export COHERE_API_KEY=xxx
   
3. Install libraries

   pip install -U openai lancedb tantivy pypdf sqlalchemy agno cohere
   
4. Run Agent

   Mac

   python cookbook/agents/rag/agentic_rag_with_reranking.py