LanceDB

Code

1from kern.agent import Agent
2from kern.knowledge.knowledge import Knowledge
3from kern.vectordb.lancedb import LanceDb
4
5vector_db = LanceDb(
6    table_name="vectors",
7    uri="tmp/lancedb",
8)
9
10knowledge = Knowledge(
11    name="Basic SDK Knowledge Base",
12    description="Kern 2.0 Knowledge Implementation with LanceDB",
13    vector_db=vector_db,
14)
15
16knowledge.insert(
17        name="Recipes",
18        url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
19        metadata={"doc_type": "recipe_book"},
20    )
21
22agent = Agent(knowledge=knowledge)
23agent.print_response("List down the ingredients to make Massaman Gai", markdown=True)
24
25vector_db.delete_by_name("Recipes")
26# or
27vector_db.delete_by_metadata({"doc_type": "recipe_book"})

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Install dependencies

1uv pip install -U lancedb pypdf openai kern-ai

Set environment variables

1export OPENAI_API_KEY=xxx

Run Agent

1python cookbook/08_knowledge/vector_db/lance_db/lance_db.py