RAG with LanceDB and SQLite

Code

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.knowledge.embedder.ollama import OllamaEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.ollama import Ollama
from agno.vectordb.lancedb import LanceDb

# Define the database URL where the vector database will be stored
db_url = "/tmp/lancedb"

# Configure the language model
model = Ollama(id="llama3.1:8b")

# Create Ollama embedder
embedder = OllamaEmbedder(id="nomic-embed-text", dimensions=768)

# Create the vector database
vector_db = LanceDb(
    table_name="recipes",  # Table name in the vector database
    uri=db_url,  # Location to initiate/create the vector database
    embedder=embedder,  # Without using this, it will use OpenAIChat embeddings by default
)

knowledge = Knowledge(
    vector_db=vector_db,
)

knowledge.add_content(
    name="Recipes", url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
)



db = SqliteDb(db_file="data.db")


agent = Agent(
    session_id="session_id", 
    user_id="user",  
    model=model,
    knowledge=knowledge,
    db=db,
)


agent.print_response(
    "What is the first step of making Gluai Buat Chi from the knowledge base?",
    markdown=True,
)

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. Install Ollama

   Follow the installation instructions at Ollama’s website

3. Install libraries

   pip install -U lancedb sqlalchemy agno
   
4. Run Agent

   Mac

   python cookbook/agents/rag/rag_with_lance_db_and_sqlite.py