Qdrant Hybrid Search

Code

cookbook/08_knowledge/vector_db/qdrant_db/qdrant_db_hybrid_search.py

import typer
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.qdrant import Qdrant
from agno.vectordb.search import SearchType
from rich.prompt import Prompt

COLLECTION_NAME = "thai-recipes"

vector_db = Qdrant(
    collection=COLLECTION_NAME,
    url="http://localhost:6333",
    search_type=SearchType.hybrid,
)

knowledge = Knowledge(
    name="My Qdrant Vector Knowledge Base",
    vector_db=vector_db,
)

knowledge.insert(
    name="Recipes",
    url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
    metadata={"doc_type": "recipe_book"},
)

def qdrantdb_agent(user: str = "user"):
    agent = Agent(
        user_id=user,
        knowledge=knowledge,
        search_knowledge=True,
    )

    while True:
        message = Prompt.ask(f"[bold] :sunglasses: {user} [/bold]")
        if message in ("exit", "bye"):
            break
        agent.print_response(message)

if __name__ == "__main__":
    typer.run(qdrantdb_agent)

To use hybrid search without internet access, pre-cache the model and pass fastembed_kwargs={"local_files_only": True, "cache_dir": "/path/to/local/model/cache"} to load models from the cache and disable downloads:

Qdrant(
    collection="my_collection",
    search_type=SearchType.hybrid,
    fastembed_kwargs={
        "local_files_only": True,
        "cache_dir": "/path/to/cached/models",
    },
)

Usage

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U qdrant-client typer rich pypdf openai agno
   
3. Run Qdrant

   docker run -d --name qdrant -p 6333:6333 qdrant/qdrant:latest
   
4. Run Agent

   python cookbook/08_knowledge/vector_db/qdrant_db/qdrant_db_hybrid_search.py